[go: up one dir, main page]

WO2018000732A1 - 危险物品检测方法和装置 - Google Patents

危险物品检测方法和装置 Download PDF

Info

Publication number
WO2018000732A1
WO2018000732A1 PCT/CN2016/108915 CN2016108915W WO2018000732A1 WO 2018000732 A1 WO2018000732 A1 WO 2018000732A1 CN 2016108915 W CN2016108915 W CN 2016108915W WO 2018000732 A1 WO2018000732 A1 WO 2018000732A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
tested
dangerous
item
dangerous article
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/108915
Other languages
English (en)
French (fr)
Inventor
刘均
刘新
宋朝忠
欧阳张鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Launch Technology Co Ltd
Original Assignee
Shenzhen Launch Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Launch Technology Co Ltd filed Critical Shenzhen Launch Technology Co Ltd
Publication of WO2018000732A1 publication Critical patent/WO2018000732A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
    • G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/03—Investigating materials by wave or particle radiation by transmission
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/10—Different kinds of radiation or particles
    • G01N2223/101—Different kinds of radiation or particles electromagnetic radiation
    • G01N2223/1016—X-ray

Definitions

  • the invention relates to the technical field of drones, and in particular to a method and a device for detecting dangerous goods.
  • Dangerous goods are items or substances that may be dangerous to human health, safety or damage to property, such as flammable and explosive materials, hazardous chemicals and radioactive materials. Therefore, how to quickly detect dangerous goods carried by criminals is an urgent problem to be solved.
  • X-ray machines are generally used to detect dangerous goods, that is, when the object to be tested enters the detection channel, the light barrier signal is blocked, the detection signal is sent to the control unit, and the radiation source is triggered to emit an X-ray beam, thereby obtaining the object to be tested. image.
  • existing X-ray machines are placed on the ground and occupy a part of the site. When there are many people, it is easy to cause people to block.
  • the existing X-ray machine can only complete the inspection work, can not automatically judge the existence of dangerous goods, and needs to manually judge the detection image, and the staff responsible for judging the detection image, such as the security inspector, need to undergo testing training.
  • it takes a long time to observe the monitoring screen which results in a large workload of the security inspector and a high requirement for the security inspector, which also leads to inefficiency in detecting dangerous goods.
  • the main object of the present invention is to provide a method and a device for detecting dangerous goods, aiming at solving the existing technology for occupying a site of an X-ray machine for detecting dangerous articles, detecting that the dangerous articles are inefficient, and not automatically determining the existence of dangerous articles. problem.
  • the present invention provides a dangerous article detecting method, and the dangerous article detecting method includes:
  • the drone detects the item to be tested within a preset range, and obtains an image of the item to be tested;
  • the method further includes:
  • the step of tracking the person carrying the dangerous article, obtaining the location information of the person carrying the dangerous goods, and transmitting the location information to the terminal connected to the drone further includes:
  • An alarm message carrying the location information is output to prompt the relevant law enforcement personnel.
  • the method further includes:
  • the prompt information is output.
  • the method further includes:
  • the step of comparing the image of the object to be tested with the image of the pre-existing dangerous article to obtain the similarity between the image of the object to be tested and the image of the pre-stored dangerous article includes:
  • the present invention also provides a dangerous article detecting device, which is applied to a drone, and the dangerous article detecting device includes:
  • a detecting module configured to detect an item to be tested within a preset range, and obtain an image of the item to be tested
  • a comparison module configured to compare an image of the object to be tested with a pre-stored dangerous article image to obtain a similarity between the image of the object to be tested and the image of the pre-stored dangerous article;
  • the determining module is configured to determine that the item to be tested is a dangerous item if the similarity is greater than a preset similarity.
  • the dangerous goods detecting device comprises:
  • a tracking module configured to track a person carrying the dangerous article, obtain location information of a person carrying the dangerous goods, and send the location information to a terminal connected to the drone.
  • the dangerous goods detecting device further comprises:
  • the first output module is configured to output alarm information carrying the location information to prompt the relevant law enforcement personnel.
  • the dangerous goods detecting device further comprises:
  • the second output module is configured to output alarm information if the dangerous degree of the dangerous article reaches a preset level, and is further configured to output prompt information if the dangerous degree of the dangerous article does not reach the preset level.
  • the dangerous goods detecting device further comprises:
  • a preprocessing module configured to preprocess an image of the object to be tested, to obtain an image of the preprocessed object to be tested
  • the comparison module includes:
  • An extracting unit configured to perform edge extraction on the image of the object to be tested after the pre-processing, to obtain a first image of the object to be tested, and to perform feature extraction on the first image of the object to be tested a second image of the item to be tested;
  • a comparing unit configured to compare the second image of the object to be tested with the pre-stored dangerous article image to obtain a similarity between the second image of the object to be tested and the pre-stored dangerous article image.
  • the invention obtains an image of the object to be tested by the drone, compares the image of the object to be tested with the image of the pre-stored dangerous article, and compares the image of the object to be tested with the image of the pre-stored dangerous article When the preset similarity is greater than the preset similarity, the drone determines that the item to be tested is a dangerous item.
  • the invention solves the problem that the traditional X-ray machine needs to occupy the site, realizes the automatic detection of the existence of the object by the drone, does not need to manually confirm the existence of the dangerous article, and improves the detection efficiency of the dangerous article.
  • FIG. 1 is a schematic flow chart of a first embodiment of a method for detecting a dangerous article according to the present invention
  • FIG. 2 is a schematic flow chart of a second embodiment of a method for detecting dangerous goods according to the present invention
  • FIG. 3 is a schematic flow chart of a third embodiment of a method for detecting dangerous goods according to the present invention.
  • FIG. 4 is a schematic diagram of functional modules of a first embodiment of a dangerous article detecting device of the present invention.
  • Figure 5 is a schematic diagram of the functional modules of the second embodiment of the dangerous article detecting device of the present invention.
  • Figure 6 is a schematic diagram of the functional modules of the third embodiment of the dangerous article detecting device of the present invention.
  • the invention provides a method for detecting dangerous goods.
  • FIG. 1 is a schematic flow chart of a first embodiment of a method for detecting dangerous goods according to the present invention.
  • the dangerous goods detecting method includes:
  • the drone When the drone receives the detection command sent by the terminal connected thereto, the drone flies from the parking area to the detection area, and detects the preset range by the detecting device installed in the drone
  • the item to be tested obtains an image of the item to be tested.
  • the terminal includes, but is not limited to, a smart phone, a personal computer, a palmtop computer, and the like.
  • the detecting device is a device in which X-rays are mounted. It should be noted that the detecting device includes, but is not limited to, a device in which X-rays are mounted, and may also be a device in which gamma rays are installed or other devices that can obtain an image of the object to be tested.
  • the preset range is a range that the drone can detect in the detection area.
  • Step S20 comparing the image of the object to be tested with the image of the pre-existing dangerous goods, to obtain the similarity between the image of the object to be tested and the image of the pre-stored dangerous goods;
  • the drone compares an image of the item to be tested with a pre-stored image of the dangerous item to obtain an image of the item to be tested and the image The similarity of pre-stored dangerous goods images.
  • An image of various dangerous articles is pre-stored in the drone. It can be understood that the drone compares the contour of the object to be tested in the image of the object to be tested with the contour of the pre-stored dangerous article.
  • the drone When the outline of the object to be tested obtained by the drone is smaller than the outline of the pre-stored dangerous article, the drone appropriately expands the object to be tested according to the contour of the pre-stored dangerous article And contouring, and then comparing the image of the item to be tested with the pre-stored dangerous item image to obtain a similarity between the image of the item to be tested and the pre-stored dangerous item image.
  • the drone When the outline of the item to be tested obtained by the drone is larger than the outline of the pre-stored dangerous item, the drone appropriately reduces the item to be tested according to the contour of the pre-stored dangerous item.
  • the range of expanding or reducing the outline of the article to be tested depends on the degree of difference between the contour of the article to be tested and the contour of the pre-stored dangerous article.
  • Step S30 if the similarity is greater than the preset similarity, determining that the item to be tested is a dangerous item.
  • the drone determines that the item to be tested is a dangerous item.
  • the similarity between the image of the item to be tested and the pre-stored dangerous item image is less than or equal to the preset similarity, the drone determines that the item to be tested is a normal item, not a dangerous item.
  • the preset similarity may be set according to specific needs, such as setting to 40%, or 50%, or 60%, and the like.
  • the method further includes:
  • Step a preprocessing the image of the item to be tested to obtain an image of the pre-processed item to be tested
  • the drone when the drone obtains an image of the item to be tested, the drone performs pre-processing on the image of the item to be tested to obtain an image of the pre-processed item to be tested.
  • the process of preprocessing the image of the object to be tested is: 1 image denoising; 2 image enhancement; 3 image segmentation.
  • the image denoising method includes, but is not limited to, a wavelet denoising, an averaging filter, and a morphological noise filter;
  • the image enhancement methods include, but are not limited to, contrast transform, image operation, spatial filtering, and multi-spectral transformation;
  • Methods of image segmentation include, but are not limited to, threshold segmentation, edge segmentation, and histogram methods.
  • Step b performing edge extraction on the image of the object to be tested after the pre-processing, to obtain a first image of the object to be tested;
  • Step c performing feature extraction on the first image of the object to be tested to obtain a second image of the object to be tested;
  • Step d comparing the second image of the object to be tested with the pre-stored dangerous article image to obtain a similarity between the second image of the object to be tested and the pre-stored dangerous article image.
  • the UAV When the UAV obtains an image of the pre-processed item to be tested, the UAV performs edge extraction on the image of the pre-processed item to be tested, and obtains the to-be-measured after edge extraction.
  • An image of the item that is, a first image of the item to be tested.
  • the UAV performs feature extraction on the first image of the object to be tested by using a contour invariant feature extraction method to obtain a second image of the object to be tested.
  • the method for edge extraction includes: 1 based on a fixed local operation algorithm, such as differential method, fitting method, etc.; 2 a global extraction method based on energy minimization, which is characterized by using strict mathematical methods. The problem is analyzed, and the one-dimensional cost function is given as the basis for optimal extraction.
  • edges are extracted from the global optimal point of view, such as relaxation method, neural network analysis method, etc. 3
  • wavelet transform mathematical morphology and analytical theory.
  • High-tech representation of image edge extraction methods such as wavelet transform based on multi-scale features to extract image edges.
  • an image of the item to be tested is acquired by the drone, and the image of the item to be tested is compared with the image of the pre-stored dangerous item, and the image of the item to be tested is similar to the image of the pre-stored dangerous item.
  • the drone determines that the item to be tested is a dangerous item.
  • FIG. 2 is a schematic flow chart of a second embodiment of a dangerous article detecting method according to the present invention. Based on the first embodiment, a second embodiment of the dangerous article detecting method of the present invention is proposed.
  • the dangerous goods detecting method includes:
  • Step S40 tracking the person carrying the dangerous article, obtaining the location information of the person carrying the dangerous goods, and transmitting the location information to the terminal connected to the drone.
  • the drone determines a person carrying the dangerous item, initiates a tracking function, tracks a person carrying the dangerous item, and installs the drone through the drone
  • the positioning device in the real-time acquires the location information of the person carrying the dangerous goods in real time.
  • the location information of the person carrying the dangerous goods is sent to the terminal connected to the drone, so that the terminal user can quickly find and carry the Personnel of dangerous goods.
  • the positioning device is equipped with GPS (Global Positioning System, or a component similar to GPS that can be used for positioning.
  • the dangerous goods detecting method includes:
  • An alarm message carrying the location information is output to prompt the relevant law enforcement personnel.
  • the alarm information is generated according to the location information of the person carrying the dangerous goods, so as to prompt the relevant law enforcement personnel to find the dangerous goods, The relevant law enforcement personnel quickly find the person carrying the dangerous goods according to the location information carried in the alarm information.
  • the person carrying the dangerous goods is tracked by the drone, and the location information of the person carrying the dangerous goods is acquired, and the location information is sent to the terminal connected to the drone.
  • the user of the terminal such as a security inspector, can quickly find the person carrying the dangerous article and improve the intelligence of the drone.
  • FIG. 3 is a schematic flow chart of a third embodiment of a dangerous article detecting method according to the present invention. Based on the first embodiment, a third embodiment of the dangerous article detecting method of the present invention is proposed.
  • the dangerous goods detecting method includes:
  • Step S50 determining a dangerous degree of the dangerous article according to a hidden relationship table between the dangerous article and the dangerous degree;
  • the drone determines that the item to be tested is a dangerous item, determining a degree of danger of the dangerous item according to a mapping relationship between the pre-stored dangerous item and the degree of danger, such as the dangerous item and the degree of danger
  • the mapping relationship between the guns, control tools and other items that may endanger human safety and property safety is 1.
  • the degree of danger corresponding to radioactive items is 2, flammable and explosive, and other dangerous levels are higher.
  • the chemical corresponds to a hazard level of 3. It should be noted that the implicit relationship between the dangerous goods and the degree of danger is not limited to the mapping relationship described in this embodiment.
  • Step S60 if the dangerous degree of the dangerous article reaches a preset level, outputting an alarm message
  • Step S70 If the dangerous degree of the dangerous article does not reach the preset level, the prompt information is output.
  • the drone determines whether the dangerous degree of the dangerous article reaches a preset level. If the dangerous degree of the dangerous article reaches the preset level, the drone outputs an alarm message to prompt the relevant personnel, and the dangerous area with high degree of danger exists in the detection area where the drone is located, please Handle as soon as possible. If the dangerous degree of the dangerous article does not reach the preset level, the prompt information is output to prompt the relevant personnel, and the dangerous object with a lower degree of danger exists in the detection area where the drone is located, so that the relevant personnel can Take corresponding measures according to the specific work situation.
  • the relevant personnel are the staff of the detection area where the drone is located, the user of the terminal connected to the drone, and related law enforcement personnel.
  • the preset degree may be set according to a required degree of security of the detection area in which the drone is located. As in the present embodiment, the preset degree can be set to 2. When the dangerous degree of the dangerous article is equal to 2 or greater than 2, the drone outputs an alarm message; when the dangerous degree of the dangerous article is less than 2, the drone outputs a prompt message.
  • the unmanned aerial vehicle outputs alarm information or prompt information according to the dangerous degree of the dangerous article, so that the relevant personnel can take corresponding measures according to the dangerous degree of the dangerous article, thereby improving the intelligence of the drone in detecting dangerous articles.
  • the invention further provides a dangerous article detecting device.
  • FIG. 4 there is shown a functional block diagram of a first embodiment of the dangerous article detecting apparatus of the present invention.
  • the dangerous goods detecting device is applied to a drone, and the dangerous goods detecting device includes:
  • the detecting module 10 is configured to detect an item to be tested within a preset range, and obtain an image of the item to be tested;
  • the drone When the drone receives the detection command sent by the terminal connected thereto, the drone flies from the parking area to the detection area, and detects the preset range by the detecting device installed in the drone
  • the item to be tested obtains an image of the item to be tested.
  • the terminal includes, but is not limited to, a smart phone, a personal computer, a palmtop computer, and the like.
  • the detecting device is a device in which X-rays are mounted. It should be noted that the detecting device includes, but is not limited to, a device in which X-rays are mounted, and may also be a device in which gamma rays are installed or other devices that can obtain an image of the object to be tested.
  • the preset range is a range that the drone can detect in the detection area.
  • a comparison module 20 configured to compare an image of the object to be tested with a pre-stored dangerous article image to obtain a similarity between the image of the object to be tested and the image of the pre-stored dangerous article;
  • the drone compares an image of the item to be tested with a pre-stored image of the dangerous item to obtain an image of the item to be tested and the image The similarity of pre-stored dangerous goods images.
  • An image of various dangerous articles is pre-stored in the drone. It can be understood that the drone compares the contour of the object to be tested in the image of the object to be tested with the contour of the pre-stored dangerous article.
  • the drone When the outline of the object to be tested obtained by the drone is smaller than the outline of the pre-stored dangerous article, the drone appropriately expands the object to be tested according to the contour of the pre-stored dangerous article And contouring, and then comparing the image of the item to be tested with the pre-stored dangerous item image to obtain a similarity between the image of the item to be tested and the pre-stored dangerous item image.
  • the drone When the outline of the item to be tested obtained by the drone is larger than the outline of the pre-stored dangerous item, the drone appropriately reduces the item to be tested according to the contour of the pre-stored dangerous item.
  • the range of expanding or reducing the outline of the article to be tested depends on the degree of difference between the contour of the article to be tested and the contour of the pre-stored dangerous article.
  • the determining module 30 is configured to determine that the item to be tested is a dangerous item if the similarity is greater than a preset similarity.
  • the drone determines that the item to be tested is a dangerous item.
  • the similarity between the image of the item to be tested and the pre-stored dangerous item image is less than or equal to the preset similarity, the drone determines that the item to be tested is a normal item, not a dangerous item.
  • the preset similarity may be set according to specific needs, such as setting to 40%, or 50%, or 60%, and the like.
  • the dangerous goods detecting device further includes:
  • a preprocessing module configured to preprocess an image of the object to be tested, to obtain an image of the preprocessed object to be tested
  • the drone when the drone obtains an image of the item to be tested, the drone performs pre-processing on the image of the item to be tested to obtain an image of the pre-processed item to be tested.
  • the process of preprocessing the image of the object to be tested is: 1 image denoising; 2 image enhancement; 3 image segmentation.
  • the image denoising method includes, but is not limited to, a wavelet denoising, an averaging filter, and a morphological noise filter;
  • the image enhancement methods include, but are not limited to, contrast transform, image operation, spatial filtering, and multi-spectral transformation;
  • Methods of image segmentation include, but are not limited to, threshold segmentation, edge segmentation, and histogram methods.
  • the comparison module 20 includes:
  • An extracting unit configured to perform edge extraction on the image of the object to be tested after the pre-processing, to obtain a first image of the object to be tested, and to perform feature extraction on the first image of the object to be tested a second image of the item to be tested;
  • a comparing unit configured to compare the second image of the object to be tested with the pre-stored dangerous article image to obtain a similarity between the second image of the object to be tested and the pre-stored dangerous article image.
  • the UAV When the UAV obtains an image of the pre-processed item to be tested, the UAV performs edge extraction on the image of the pre-processed item to be tested, and obtains the to-be-measured after edge extraction.
  • An image of the item that is, a first image of the item to be tested.
  • the UAV performs feature extraction on the first image of the object to be tested by using a contour invariant feature extraction method to obtain a second image of the object to be tested.
  • the method for edge extraction includes: 1 based on a fixed local operation algorithm, such as differential method, fitting method, etc.; 2 a global extraction method based on energy minimization, which is characterized by using strict mathematical methods. The problem is analyzed, and the one-dimensional cost function is given as the basis for optimal extraction.
  • edges are extracted from the global optimal point of view, such as relaxation method, neural network analysis method, etc. 3
  • wavelet transform mathematical morphology and analytical theory.
  • High-tech representation of image edge extraction methods such as wavelet transform based on multi-scale features to extract image edges.
  • an image of the item to be tested is acquired by the drone, and the image of the item to be tested is compared with the image of the pre-stored dangerous item, and the image of the item to be tested is similar to the image of the pre-stored dangerous item.
  • the drone determines that the item to be tested is a dangerous item.
  • FIG. 5 is a functional block diagram of a second embodiment of the dangerous article detecting device of the present invention
  • a second embodiment of the dangerous article detecting device of the present invention is proposed based on the first embodiment of the present invention.
  • the dangerous goods detecting device further includes:
  • the tracking module 40 is configured to track a person carrying the dangerous article, obtain location information of a person carrying the dangerous goods, and send the location information to a terminal connected to the drone.
  • the drone determines a person carrying the dangerous item, initiates a tracking function, tracks a person carrying the dangerous item, and installs the drone through the drone
  • the positioning device in the real-time acquires the location information of the person carrying the dangerous goods in real time.
  • the location information of the person carrying the dangerous goods is sent to the terminal connected to the drone, so that the terminal user can quickly find and carry the Personnel of dangerous goods.
  • the positioning device is equipped with GPS (Global Positioning System, or a component similar to GPS that can be used for positioning.
  • the first output module is configured to output alarm information carrying the location information to prompt the relevant law enforcement personnel.
  • the alarm information is generated according to the location information of the person carrying the dangerous goods, so as to prompt the relevant law enforcement personnel to find the dangerous goods, The relevant law enforcement personnel quickly find the person carrying the dangerous goods according to the location information carried in the alarm information.
  • the person carrying the dangerous goods is tracked by the drone, and the location information of the person carrying the dangerous goods is acquired, and the location information is sent to the terminal connected to the drone.
  • the user of the terminal such as a security inspector, can quickly find the person carrying the dangerous article and improve the intelligence of the drone.
  • FIG. 6 there is shown a functional block diagram of a third embodiment of the dangerous article detecting device of the present invention, and a third embodiment of the dangerous article detecting device of the present invention is proposed based on the first embodiment of the present invention.
  • the dangerous goods detecting device further includes:
  • a determining module 50 configured to determine a dangerous degree of the dangerous article according to a hidden relationship table between the dangerous article and the dangerous degree;
  • the drone determines that the item to be tested is a dangerous item, determining a degree of danger of the dangerous item according to a mapping relationship between the pre-stored dangerous item and the degree of danger, such as the dangerous item and the degree of danger
  • the mapping relationship between the guns, control tools and other items that may endanger human safety and property safety is 1.
  • the degree of danger corresponding to radioactive items is 2, flammable and explosive, and other dangerous levels are higher.
  • the chemical corresponds to a hazard level of 3. It should be noted that the implicit relationship between the dangerous goods and the degree of danger is not limited to the mapping relationship described in this embodiment.
  • the drone determines whether the dangerous degree of the dangerous article reaches a preset level. If the dangerous degree of the dangerous article reaches the preset level, the drone outputs an alarm message to prompt the relevant personnel, and the dangerous area with high degree of danger exists in the detection area where the drone is located, please Handle as soon as possible. If the dangerous degree of the dangerous article does not reach the preset level, the prompt information is output to prompt the relevant personnel, and the dangerous object with a lower degree of danger exists in the detection area where the drone is located, so that the relevant personnel can Take corresponding measures according to the specific work situation.
  • the relevant personnel are the staff of the detection area where the drone is located, the user of the terminal connected to the drone, and related law enforcement personnel.
  • the preset degree may be set according to a required degree of security of the detection area in which the drone is located. As in the present embodiment, the preset degree can be set to 2. When the dangerous degree of the dangerous article is equal to 2 or greater than 2, the drone outputs an alarm message; when the dangerous degree of the dangerous article is less than 2, the drone outputs a prompt message.
  • the unmanned aerial vehicle outputs alarm information or prompt information according to the dangerous degree of the dangerous article, so that the relevant personnel can take corresponding measures according to the dangerous degree of the dangerous article, thereby improving the intelligence of the drone in detecting dangerous articles.
  • the technical solution of the present invention which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • a storage medium such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Image Analysis (AREA)

Abstract

一种危险物品检测方法及装置，所述方法包括：无人机检测预设范围内的待测物品，得到待测物品的图像（S10）；将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度（S20）；若所述相似度大于预设相似度，则判定所述待测物品为危险品（S30）。该方法解决了传统的X光机需要占用场地的问题，实现了通过无人机自动检测物品的存在，不需要人工去确认危险物品的存在，提高了危险物品的检测效率。

Description

危险物品检测方法和装置
技术领域
本发明涉及无人机技术领域，尤其涉及一种危险物品检测方法和装置。
背景技术
危险物品是可能明显地危险人身健康、安全或对财产造成损害的物品或物质，如易燃易爆物品、危险化学品和放射性物品等。因此，如何能快速检测出不法分子所携带的危险物品，是急需解决的问题。
目前一般都采用X光机的检测危险物品，即当待测物品进入检测通道后，将阻挡光障信号，检测信号被送至控制单元，触发射线源发射X射线束，从而得到待测物品的图像。但是现有的X光机都是放置在地面，会占用一部分场地。当人员较多时，容易造成人员堵塞。而且现有的X光机只能完成检测工作，不能自动判断危险物品的存在，需要人工对检测图像进行判断，而且负责对检测图像进行判断的工作人员，如安检员，是需要经过检测培训，且需要长时间观测监视屏幕，导致安检员的工作量较大，对安检员的要求较高，从而也导致检测危险物品的效率低下。
发明内容
本发明的主要目的在于提供一种危险物品检测方法和装置，旨在解决现有现有的用于检测危险物品的X光机占用场地，检测危险物品效率低下，不能自动判断危险物品存在的技术问题。
为实现上述目的，本发明提供的一种危险物品检测方法，所述危险物品检测方法包括：
无人机检测预设范围内的待测物品，得到待测物品的图像；
将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度；
若所述相似度大于预设相似度，则判定所述待测物品为危险物品。
优选地，所述若所述相似度大于预设相似度，则判定所述待测物品为危险物品的步骤之后，还包括：
跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。
优选地，所述跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端的步骤之后，还包括：
输出携带所述位置信息的报警信息，以提示相关的执法人员。
优选地，所述若所述相似度大于预设相似度，则判定所述待测物品为危险物品的步骤之后，还包括：
根据危险物品与危险程度之间的隐射关系表确定所述危险物品的危险程度；
若所述危险物品的危险程度达到预设程度，则输出报警信息；
若所述危险物品的危险程度未达到所述预设程度，则输出提示信息。
优选地，所述无人机检测预设范围内的待测物品，得到待测物品的图像的步骤之后，还包括：
对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
所述将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度的步骤包括：
对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；
对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
此外，为实现上述目的，本发明还提供一种危险物品检测装置，所述危险物品检测装置应用于无人机，所述危险物品检测装置包括：
检测模块，用于检测预设范围内的待测物品，得到待测物品的图像；
对比模块，用于将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度；
判定模块，用于若所述相似度大于预设相似度，则判定所述待测物品为危险物品。
优选地，所述危险物品检测装置包括：
跟踪模块，用于跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。
优选地，所述危险物品检测装置还包括：
第一输出模块，用于输出携带所述位置信息的报警信息，以提示相关的执法人员。
优选地，所述危险物品检测装置还包括：
确定模块，用于根据危险物品与危险程度之间的隐射关系表确定所述危险物品的危险程度；
第二输出模块，用于若所述危险物品的危险程度达到预设程度，则输出报警信息；还用于若所述危险物品的危险程度未达到所述预设程度，则输出提示信息。
优选地，所述危险物品检测装置还包括：
预处理模块，用于对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
所述对比模块包括：
提取单元，用于对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；还用于对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
对比单元，用于将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
本发明通过无人机获取待测物品的图像，将所述将所述待测物品的图像与预存危险物品图像进行对比，当所述待测物品的图像与所述预存危险物品图像的相似度大于预设相似度时，所述无人机判定所述待测物品为危险物品。解决了传统的X光机需要占用场地的问题，实现了通过无人机自动检测物品的存在，不需要人工去确认危险物品的存在，提高了危险物品的检测效率。
附图说明
图1为本发明危险物品检测方法第一实施例的流程示意图；
图2为本发明危险物品检测方法第二实施例的流程示意图；
图3为本发明危险物品检测方法第三实施例的流程示意图；
图4为本发明危险物品检测装置第一实施例的功能模块示意图；
图5为本发明危险物品检测装置第二实施例的功能模块示意图；
图6为本发明危险物品检测装置第三实施例的功能模块示意图。
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
本发明提供一种危险物品检测方法。
参照图1，图1为本发明危险物品检测方法第一实施例的流程示意图。
在本实施例中，所述危险物品检测方法包括：
步骤S10，无人机检测预设范围内的待测物品，得到待测物品的图像；
当所述无人机接收到与其连接的终端所发送的检测命令时，所述无人机从停留区域飞往检测区域，通过安装在所述无人机中的检测装置检测预设范围内的待测物品，得到所述待测物品的图像。所述终端包括但不限于智能手机、个人计算机和掌上电脑等。在本实施例中，所述检测装置为安装了X射线的装置。需要说明的是，所述检测装置包括但不限于安装了X射线的装置，还可以为安装了γ射线的装置或者其它可以得到所述待测物品图像的装置。可以理解的是，所述预设范围为所述无人机在所述检测区域所能检测到的范围。
步骤S20，将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度；
当所述无人机得到所述待测物品的图像时，所述无人机将所述待测物品的图像与预先存储的危险物品图像进行对比，得到所述待测物品的图像与所述预先存储的危险物品图像的相似度。所述无人机中预先存储了各种危险物品的图像。可以理解的是，所述无人机是将所述待测物品图像中所述待测物品的轮廓与预先存储的危险物品的轮廓进行对比。当所述无人机得到的所述待测物品的轮廓小于所述预先存储的危险物品的轮廓时，所述无人机根据所述预先存储的危险物品的轮廓适当扩大所述待测物品的轮廓，然后再将所述待测物品的图像与预先存储的危险物品图像进行对比，得到所述待测物品的图像与所述预先存储的危险物品图像的相似度。当所述无人机得到的所述待测物品的轮廓大于所述预先存储的危险物品的轮廓时，所述无人机根据所述预先存储的危险物品的轮廓适当缩小所述待测物品的轮廓，然后再将所述待测物品的图像与预先存储的危险物品图像进行对比，得到所述待测物品的图像与所述预先存储的危险物品图像的相似度。所述扩大或者缩小所述待测物品的轮廓的范围根据所述待测物品的轮廓与所述预先存储的危险物品的轮廓相差程度而定。
步骤S30，若所述相似度大于预设相似度，则判定所述待测物品为危险物品。
当所述待测物品的图像与所述预先存储的危险物品图像的相似度大于预设相似度时，所述无人机则判定所述待测物品为危险物品。当所述待测物品的图像与所述预先存储的危险物品图像的相似度小于或者等于所述预设相似度时，所述无人机则判定所述待测物品为正常物品，不是危险物品。需要说明的是，所述预设相似度可以根据具体需要而设置，如设置为40%，或者50%，或者60%等。
进一步地，所述步骤S10之后，还包括：
步骤a，对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
进一步地，当所述无人机得到所述待测物品的图像时，所述无人机对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像。所述对所述待测物品的图像进行预处理的过程为：①图像去噪；②图像增强；③图像分割。所述图像去噪的方法包括但不限于小波去噪、均值滤波器和形态学噪声滤除器；所述图像增强的方法包括但不限于对比度变换、图像运算、空间滤波和多光谱变换；所述图像分割的方法包括但不限于阈值分割、边缘分割和直方图法。
所述步骤S20包括：
步骤b，对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；
步骤c，对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
步骤d，将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
当所述无人机得到预处理后的所述待测物品的图像时，所述无人机对预处理后的所述待测物品的图像进行边缘提取，得到经过边缘提取的所述待测物品的图像，即得到所述待测物品的第一图像。所述无人机利用轮廓不变量特征提取方法对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像。所述边缘提取的方法包括：①基于某种固定的局部运算算法，如微分法，拟合法等；②以能量最小化为准则的全局提取方法，该方法的特征是运用严格的数学方法对此问题进行分析，给出一维代价函数作为最优提取依据，从全局最优的观点提取边缘，如松弛法，神经网络分析法等；③以小波变换、数学形态学、分析理论等近年发展起来的高新技术为代表的图像边缘提取方法，如基于多尺度特征的小波变换提取图像边缘的方法。
当所述无人机得到所述待测物品的第二图像时，将所述待测物品的第二图像与预先存储的危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
本实施例通过无人机获取待测物品的图像，将所述将所述待测物品的图像与预存危险物品图像进行对比，当所述待测物品的图像与所述预存危险物品图像的相似度大于预设相似度时，所述无人机判定所述待测物品为危险物品。解决了传统的X光机需要占用场地的问题，实现了通过无人机自动检测物品的存在，不需要人工去确认危险物品的存在，提高了危险物品的检测效率。
参照图2，图2为本发明危险物品检测方法第二实施例的流程示意图，基于第一实施例提出本发明危险物品检测方法第二实施例。
在本实施例中，所述危险物品检测方法包括：
步骤S40，跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。
当所述无人机检测到危险物品的存在时，所述无人机确定携带所述危险物品的人员，启动追踪功能，跟踪携带所述危险物品的人员，并通过安装在所述无人机中的定位装置实时获取携带所述危险物品人员所在的位置信息。当所述无人机获取到携带所述危险物品人员所在位置信息时，将携带所述危险物品人员所在位置信息发送至与所述无人机连接的终端，以供终端用户快速找到携带所述危险物品的人员。可以理解的是，所述定位装置为安装了GPS（Global Positioning System，定位系统），或者安装了类似于GPS可以实现定位功能的组件。
进一步地，所述危险物品检测方法包括：
输出携带所述位置信息的报警信息，以提示相关的执法人员。
进一步地，当所述无人机获取到携带所述危险物品人员所在的位置信息时，根据携带所述危险物品的人员所在位置信息生成报警信息，以提示相关执法人员，已发现危险物品，以供相关执法人员根据所述报警信息中所携带的位置信息快速找到携带所述危险物品的人员。
本实施例通过无人机跟踪携带危险物品的人员，并获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。可以让所述终端的用户，如安检员，快速找到携带所述危险物品的人员，提高了无人机的智能性。
参照图3，图3为本发明危险物品检测方法第三实施例的流程示意图，基于第一实施例提出本发明危险物品检测方法第三实施例。
在本实施例中，所述危险物品检测方法包括：
步骤S50，根据危险物品与危险程度之间的隐射关系表确定所述危险物品的危险程度；
当所述无人机判定所述待测物品为危险物品时，根据预先存储的危险物品与危险程度之间的映射关系表确定所述危险物品的危险程度，如所述危险物品与危险程度之间的映射关系表为：枪支、管制刀具等可能会危及人体安全和财产安全的物品所对应的危险程度为1，放射性物品所对应的危险程度为2，易燃易爆及其它危险程度较高的化学物品所对应的危险程度为3。需要说明的是，所述危险物品与危险程度之间的隐射关系并不限制于本实施例中所描述的映射关系。
步骤S60，若所述危险物品的危险程度达到预设程度，则输出报警信息；
步骤S70，若所述危险物品的危险程度未达到所述预设程度，则输出提示信息。
当所述无人机确定所述危险物品的危险程度后，所述无人机判断所述危险物品的危险程度是否达到预设程度。若所述危险物品的危险程度达到所述预设程度，所述无人机则输出报警信息，以提示相关人员，所述无人机所在的检测区域中存在危险程度较高的危险物品，请尽快处理。若所述危险物品的危险程度未达到所述预设程度，则输出提示信息，以提示相关人员，所述无人机所在的检测区域中存在危险程度较低的危险物品，以供相关人员可以根据具体的工作情况采取相应的措施。所述相关人员为所述无人机所在检测区域的工作人员，与所述无人机连接的终端的用户和相关的执法人员等。所述预设程度可以根据所述无人机所在的检测区域所需要的安全程度来设置。如在本实施例中，可以将所述预设程度设置为2。如当所述危险物品的危险程度等于2或者大于2时，所述无人机输出报警信息；当所述危险物品的危险程度小于2时，所述无人机输出提示信息。
本实施例无人机通过根据危险物品的危险程度输出报警信息或者提示信息，以供相关人员根据危险物品的危险程度采取相应的措施，提高了无人机在检测危险物品方面的智能性。
本发明进一步提供一种危险物品检测装置。
参照图4，图4为本发明危险物品检测装置的第一实施例的功能模块示意图。
在本实施例中，所述危险物品检测装置应用于无人机，所述危险物品检测装置包括：
检测模块10，用于检测预设范围内的待测物品，得到待测物品的图像；
当所述无人机接收到与其连接的终端所发送的检测命令时，所述无人机从停留区域飞往检测区域，通过安装在所述无人机中的检测装置检测预设范围内的待测物品，得到所述待测物品的图像。所述终端包括但不限于智能手机、个人计算机和掌上电脑等。在本实施例中，所述检测装置为安装了X射线的装置。需要说明的是，所述检测装置包括但不限于安装了X射线的装置，还可以为安装了γ射线的装置或者其它可以得到所述待测物品图像的装置。可以理解的是，所述预设范围为所述无人机在所述检测区域所能检测到的范围。
对比模块20，用于将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度；
当所述无人机得到所述待测物品的图像时，所述无人机将所述待测物品的图像与预先存储的危险物品图像进行对比，得到所述待测物品的图像与所述预先存储的危险物品图像的相似度。所述无人机中预先存储了各种危险物品的图像。可以理解的是，所述无人机是将所述待测物品图像中所述待测物品的轮廓与预先存储的危险物品的轮廓进行对比。当所述无人机得到的所述待测物品的轮廓小于所述预先存储的危险物品的轮廓时，所述无人机根据所述预先存储的危险物品的轮廓适当扩大所述待测物品的轮廓，然后再将所述待测物品的图像与预先存储的危险物品图像进行对比，得到所述待测物品的图像与所述预先存储的危险物品图像的相似度。当所述无人机得到的所述待测物品的轮廓大于所述预先存储的危险物品的轮廓时，所述无人机根据所述预先存储的危险物品的轮廓适当缩小所述待测物品的轮廓，然后再将所述待测物品的图像与预先存储的危险物品图像进行对比，得到所述待测物品的图像与所述预先存储的危险物品图像的相似度。所述扩大或者缩小所述待测物品的轮廓的范围根据所述待测物品的轮廓与所述预先存储的危险物品的轮廓相差程度而定。
判定模块30，用于若所述相似度大于预设相似度，则判定所述待测物品为危险物品。
当所述待测物品的图像与所述预先存储的危险物品图像的相似度大于预设相似度时，所述无人机则判定所述待测物品为危险物品。当所述待测物品的图像与所述预先存储的危险物品图像的相似度小于或者等于所述预设相似度时，所述无人机则判定所述待测物品为正常物品，不是危险物品。需要说明的是，所述预设相似度可以根据具体需要而设置，如设置为40%，或者50%，或者60%等。
进一步地，所述危险物品检测装置还包括：
预处理模块，用于对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
进一步地，当所述无人机得到所述待测物品的图像时，所述无人机对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像。所述对所述待测物品的图像进行预处理的过程为：①图像去噪；②图像增强；③图像分割。所述图像去噪的方法包括但不限于小波去噪、均值滤波器和形态学噪声滤除器；所述图像增强的方法包括但不限于对比度变换、图像运算、空间滤波和多光谱变换；所述图像分割的方法包括但不限于阈值分割、边缘分割和直方图法。
所述对比模块20包括：
提取单元，用于对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；还用于对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
对比单元，用于将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
当所述无人机得到预处理后的所述待测物品的图像时，所述无人机对预处理后的所述待测物品的图像进行边缘提取，得到经过边缘提取的所述待测物品的图像，即得到所述待测物品的第一图像。所述无人机利用轮廓不变量特征提取方法对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像。所述边缘提取的方法包括：①基于某种固定的局部运算算法，如微分法，拟合法等；②以能量最小化为准则的全局提取方法，该方法的特征是运用严格的数学方法对此问题进行分析，给出一维代价函数作为最优提取依据，从全局最优的观点提取边缘，如松弛法，神经网络分析法等；③以小波变换、数学形态学、分析理论等近年发展起来的高新技术为代表的图像边缘提取方法，如基于多尺度特征的小波变换提取图像边缘的方法。
当所述无人机得到所述待测物品的第二图像时，将所述待测物品的第二图像与预先存储的危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
本实施例通过无人机获取待测物品的图像，将所述将所述待测物品的图像与预存危险物品图像进行对比，当所述待测物品的图像与所述预存危险物品图像的相似度大于预设相似度时，所述无人机判定所述待测物品为危险物品。解决了传统的X光机需要占用场地的问题，实现了通过无人机自动检测物品的存在，不需要人工去确认危险物品的存在，提高了危险物品的检测效率。
参照图5，图5为本发明危险物品检测装置的第二实施例的功能模块示意图，基于本发明的第一实施例提出本发明危险物品检测装置的第二实施例。
在本实施例中，所述危险物品检测装置还包括：
跟踪模块40，用于跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。
当所述无人机检测到危险物品的存在时，所述无人机确定携带所述危险物品的人员，启动追踪功能，跟踪携带所述危险物品的人员，并通过安装在所述无人机中的定位装置实时获取携带所述危险物品人员所在的位置信息。当所述无人机获取到携带所述危险物品人员所在位置信息时，将携带所述危险物品人员所在位置信息发送至与所述无人机连接的终端，以供终端用户快速找到携带所述危险物品的人员。可以理解的是，所述定位装置为安装了GPS（Global Positioning System，定位系统），或者安装了类似于GPS可以实现定位功能的组件。
进一步地，所述危险物品检测装置还包括：
第一输出模块，用于输出携带所述位置信息的报警信息，以提示相关的执法人员。
进一步地，当所述无人机获取到携带所述危险物品人员所在的位置信息时，根据携带所述危险物品的人员所在位置信息生成报警信息，以提示相关执法人员，已发现危险物品，以供相关执法人员根据所述报警信息中所携带的位置信息快速找到携带所述危险物品的人员。
本实施例通过无人机跟踪携带危险物品的人员，并获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。可以让所述终端的用户，如安检员，快速找到携带所述危险物品的人员，提高了无人机的智能性。
参照图6，图6为本发明危险物品检测装置的第三实施例的功能模块示意图，基于本发明的第一实施例提出本发明危险物品检测装置的第三实施例。
在本实施例中，所述危险物品检测装置还包括：
确定模块50，用于根据危险物品与危险程度之间的隐射关系表确定所述危险物品的危险程度；
当所述无人机判定所述待测物品为危险物品时，根据预先存储的危险物品与危险程度之间的映射关系表确定所述危险物品的危险程度，如所述危险物品与危险程度之间的映射关系表为：枪支、管制刀具等可能会危及人体安全和财产安全的物品所对应的危险程度为1，放射性物品所对应的危险程度为2，易燃易爆及其它危险程度较高的化学物品所对应的危险程度为3。需要说明的是，所述危险物品与危险程度之间的隐射关系并不限制于本实施例中所描述的映射关系。
第二输出模块60，用于若所述危险物品的危险程度达到预设程度，则输出报警信息；还用于若所述危险物品的危险程度未达到所述预设程度，则输出提示信息。
当所述无人机确定所述危险物品的危险程度后，所述无人机判断所述危险物品的危险程度是否达到预设程度。若所述危险物品的危险程度达到所述预设程度，所述无人机则输出报警信息，以提示相关人员，所述无人机所在的检测区域中存在危险程度较高的危险物品，请尽快处理。若所述危险物品的危险程度未达到所述预设程度，则输出提示信息，以提示相关人员，所述无人机所在的检测区域中存在危险程度较低的危险物品，以供相关人员可以根据具体的工作情况采取相应的措施。所述相关人员为所述无人机所在检测区域的工作人员，与所述无人机连接的终端的用户和相关的执法人员等。所述预设程度可以根据所述无人机所在的检测区域所需要的安全程度来设置。如在本实施例中，可以将所述预设程度设置为2。如当所述危险物品的危险程度等于2或者大于2时，所述无人机输出报警信息；当所述危险物品的危险程度小于2时，所述无人机输出提示信息。
本实施例无人机通过根据危险物品的危险程度输出报警信息或者提示信息，以供相关人员根据危险物品的危险程度采取相应的措施，提高了无人机在检测危险物品方面的智能性。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质（如ROM/RAM、磁碟、光盘）中，包括若干指令用以使得一台终端设备（可以是手机，计算机，服务器，或者网络设备等）执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括 在本发明的专利保护范围内。

Claims (16)

  1. 一种危险物品检测方法，其特征在于，所述危险物品检测方法包括：
    无人机检测预设范围内的待测物品，得到待测物品的图像；
    将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度；
    若所述相似度大于预设相似度，则判定所述待测物品为危险物品。
  2. 如权利要求1所述的危险物品检测方法，其特征在于，所述若所述相似度大于预设相似度，则判定所述待测物品为危险物品的步骤之后，还包括：
    跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。
  3. 如权利要求2所述的危险物品检测方法，其特征在于，所述跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端的步骤之后，还包括：
    输出携带所述位置信息的报警信息，以提示相关的执法人员。
  4. 如权利要求1所述的危险物品检测方法，其特征在于，所述若所述相似度大于预设相似度，则判定所述待测物品为危险物品的步骤之后，还包括：
    根据危险物品与危险程度之间的隐射关系表确定所述危险物品的危险程度；
    若所述危险物品的危险程度达到预设程度，则输出报警信息；
    若所述危险物品的危险程度未达到所述预设程度，则输出提示信息。
  5. 如权利要求1所述的危险物品检测方法，其特征在于，所述无人机检测预设范围内的待测物品，得到待测物品的图像的步骤之后，还包括：
    对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度的步骤包括：
    对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；
    对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  6. 如权利要求2所述的危险物品检测方法，其特征在于，所述无人机检测预设范围内的待测物品，得到待测物品的图像的步骤之后，还包括：
    对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度的步骤包括：
    对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；
    对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  7. 如权利要求3所述的危险物品检测方法，其特征在于，所述无人机检测预设范围内的待测物品，得到待测物品的图像的步骤之后，还包括：
    对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度的步骤包括：
    对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；
    对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  8. 如权利要求4所述的危险物品检测方法，其特征在于，所述无人机检测预设范围内的待测物品，得到待测物品的图像的步骤之后，还包括：
    对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度的步骤包括：
    对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；
    对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  9. 一种危险物品检测装置，其特征在于，所述危险物品检测装置应用于无人机，所述危险物品检测装置包括：
    检测模块，用于检测预设范围内的待测物品，得到待测物品的图像；
    对比模块，用于将所述待测物品的图像与预存危险物品图像进行对比，得到所述待测物品的图像与所述预存危险物品图像的相似度；
    判定模块，用于若所述相似度大于预设相似度，则判定所述待测物品为危险物品。
  10. 如权利要求9所述的危险物品检测装置，其特征在于，所述危险物品检测装置包括：
    跟踪模块，用于跟踪携带所述危险物品的人员，获取携带所述危险物品人员所在的位置信息，并将所述位置信息发送至与所述无人机连接的终端。
  11. 如权利要求10所述的危险物品检测装置，其特征在于，所述危险物品检测装置还包括：
    第一输出模块，用于输出携带所述位置信息的报警信息，以提示相关的执法人员。
  12. 如权利要求9所述的危险物品检测装置，其特征在于，所述危险物品检测装置还包括：
    确定模块，用于根据危险物品与危险程度之间的隐射关系表确定所述危险物品的危险程度；
    第二输出模块，用于若所述危险物品的危险程度达到预设程度，则输出报警信息；还用于若所述危险物品的危险程度未达到所述预设程度，则输出提示信息。
  13. 如权利要求9所述的危险物品检测装置，其特征在于，所述危险物品检测装置还包括：
    预处理模块，用于对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述对比模块包括：
    提取单元，用于对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；还用于对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    对比单元，用于将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  14. 如权利要求10所述的危险物品检测装置，其特征在于，所述危险物品检测装置还包括：
    预处理模块，用于对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述对比模块包括：
    提取单元，用于对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；还用于对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    对比单元，用于将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  15. 如权利要求11所述的危险物品检测装置，其特征在于，所述危险物品检测装置还包括：
    预处理模块，用于对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述对比模块包括：
    提取单元，用于对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；还用于对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    对比单元，用于将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
  16. 如权利要求12所述的危险物品检测装置，其特征在于，所述危险物品检测装置还包括：
    预处理模块，用于对所述待测物品的图像进行预处理，得到预处理后的所述待测物品的图像；
    所述对比模块包括：
    提取单元，用于对预处理后的所述待测物品的图像进行边缘提取，得到所述待测物品的第一图像；还用于对所述待测物品的第一图像进行特征提取，得到所述待测物品的第二图像；
    对比单元，用于将所述待测物品的第二图像与预存危险物品图像进行对比，得到所述待测物品的第二图像与所述预存危险物品图像的相似度。
PCT/CN2016/108915 2016-06-28 2016-12-07 危险物品检测方法和装置 Ceased WO2018000732A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610486706.2 2016-06-28
CN201610486706.2A CN106203264A (zh) 2016-06-28 2016-06-28 危险物品检测方法和装置

Publications (1)

Publication Number Publication Date
WO2018000732A1 true WO2018000732A1 (zh) 2018-01-04

Family

ID=57460888

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/108915 Ceased WO2018000732A1 (zh) 2016-06-28 2016-12-07 危险物品检测方法和装置

Country Status (2)

Country Link
CN (1) CN106203264A (zh)
WO (1) WO2018000732A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110032956A (zh) * 2019-03-27 2019-07-19 阿里巴巴集团控股有限公司 危险物品识别方法和装置
CN110998299A (zh) * 2018-03-31 2020-04-10 筑波科技株式会社 无人机用x射线检查装置、使用无人机的x射线检查装置、无人机用x射线发生装置
CN111751896A (zh) * 2019-03-27 2020-10-09 北京快安科技有限公司 一种安检结果三维显示方法
CN114037939A (zh) * 2021-11-11 2022-02-11 中国铁路设计集团有限公司 一种危险品识别方法、识别装置、电子设备及存储介质
CN114255410A (zh) * 2021-11-08 2022-03-29 康大创新(广东)科技有限公司 异常行为监测预警方法、装置、设备及可读存储介质
CN120534147A (zh) * 2025-07-29 2025-08-26 成都赛力斯科技有限公司 一种车辆的温度控制方法、车辆、电子设备及存储介质

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108205643B (zh) * 2016-12-16 2020-05-15 同方威视技术股份有限公司 图像匹配方法和装置
WO2019028852A1 (zh) * 2017-08-11 2019-02-14 深圳前海达闼云端智能科技有限公司 一种安检物品的检测方法、装置及电子设备
CN107620988B (zh) * 2017-09-27 2019-07-05 珠海格力电器股份有限公司 微波炉的告警方法和装置
CN108414527B (zh) * 2018-02-06 2025-07-11 深圳丰链科技有限公司 存储柜、手机外观完整性采集的方法和计算机存储介质
CN108764328A (zh) * 2018-05-24 2018-11-06 广东工业大学 太赫兹图像危险品识别方法、装置、设备及可读存储介质
CN110807753A (zh) * 2018-07-20 2020-02-18 苏州微木智能系统有限公司 放射源的监控方法、装置及电子设备
CN109187598A (zh) * 2018-10-09 2019-01-11 青海奥越电子科技有限公司 基于数字图像处理的违禁物品检测系统及方法
CN109584907A (zh) * 2018-11-29 2019-04-05 北京奇虎科技有限公司 一种异常报警的方法和装置
CN109664321B (zh) * 2018-12-27 2024-12-17 四川文理学院 机械臂、排爆小车及搜寻方法
CN111753582B (zh) * 2019-03-27 2024-06-28 杭州海康威视数字技术股份有限公司 一种危险物品定位方法和装置
CN110619276B (zh) * 2019-08-15 2021-12-21 杭州电子科技大学 基于无人机移动监控的异常及暴力检测系统和方法
CN110529897A (zh) * 2019-08-20 2019-12-03 珠海格力电器股份有限公司 一种油烟机及其应用的安全系统
CN111798628A (zh) * 2020-07-03 2020-10-20 陈泽坤 一种锁扣式劳动工具的管理方法
CN111679695B (zh) * 2020-08-11 2020-11-10 中航金城无人系统有限公司 一种基于深度学习技术的无人机巡航及追踪系统和方法
CN113850306A (zh) * 2021-09-13 2021-12-28 北京科技大学 基于改进yolox的古建筑消防危险物品快速检测方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070221863A1 (en) * 2005-12-12 2007-09-27 Zipf Edward C Emission detector for the remote detection of explosives and illegal drugs
CN101358936A (zh) * 2007-08-02 2009-02-04 同方威视技术股份有限公司 一种利用双视角多能量透射图像进行材料识别的方法及系统
CN201514387U (zh) * 2009-07-03 2010-06-23 公安部第一研究所 利用多视角x射线对行李中爆炸物进行自动探测的系统
US20100170383A1 (en) * 2008-05-23 2010-07-08 Willner Byron J Methods and apparatuses for detecting and neutralizing remotely activated explosives
CN105092485A (zh) * 2015-08-27 2015-11-25 泉州装备制造研究所 危险物品检测方法和装置
CN105424644A (zh) * 2016-01-18 2016-03-23 中国工程物理研究院流体物理研究所 一种用于安全检查的近红外激光照明成像系统及方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104345350A (zh) * 2013-07-23 2015-02-11 清华大学 人体安全检查方法和人体安全检查系统
CN103577840B (zh) * 2013-10-30 2017-05-31 汕头大学 物品识别方法
CN103926199B (zh) * 2014-04-16 2016-08-31 黄晓鹏 危险品检测方法
CN103900973B (zh) * 2014-04-24 2017-01-04 黄晓鹏 危险品检测方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070221863A1 (en) * 2005-12-12 2007-09-27 Zipf Edward C Emission detector for the remote detection of explosives and illegal drugs
CN101358936A (zh) * 2007-08-02 2009-02-04 同方威视技术股份有限公司 一种利用双视角多能量透射图像进行材料识别的方法及系统
US20100170383A1 (en) * 2008-05-23 2010-07-08 Willner Byron J Methods and apparatuses for detecting and neutralizing remotely activated explosives
CN201514387U (zh) * 2009-07-03 2010-06-23 公安部第一研究所 利用多视角x射线对行李中爆炸物进行自动探测的系统
CN105092485A (zh) * 2015-08-27 2015-11-25 泉州装备制造研究所 危险物品检测方法和装置
CN105424644A (zh) * 2016-01-18 2016-03-23 中国工程物理研究院流体物理研究所 一种用于安全检查的近红外激光照明成像系统及方法

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110998299A (zh) * 2018-03-31 2020-04-10 筑波科技株式会社 无人机用x射线检查装置、使用无人机的x射线检查装置、无人机用x射线发生装置
CN110032956A (zh) * 2019-03-27 2019-07-19 阿里巴巴集团控股有限公司 危险物品识别方法和装置
CN111751896A (zh) * 2019-03-27 2020-10-09 北京快安科技有限公司 一种安检结果三维显示方法
CN110032956B (zh) * 2019-03-27 2023-01-24 创新先进技术有限公司 危险物品识别方法和装置
CN114255410A (zh) * 2021-11-08 2022-03-29 康大创新(广东)科技有限公司 异常行为监测预警方法、装置、设备及可读存储介质
CN114037939A (zh) * 2021-11-11 2022-02-11 中国铁路设计集团有限公司 一种危险品识别方法、识别装置、电子设备及存储介质
CN120534147A (zh) * 2025-07-29 2025-08-26 成都赛力斯科技有限公司 一种车辆的温度控制方法、车辆、电子设备及存储介质

Also Published As

Publication number Publication date
CN106203264A (zh) 2016-12-07

Similar Documents

Publication Publication Date Title
WO2018000732A1 (zh) 危险物品检测方法和装置
WO2015160207A1 (en) System and method for detecting region of interest
WO2016187964A1 (zh) 智能控制受控设备的方法和装置
WO2019047378A1 (zh) 星体快速识别方法、装置及望远镜
WO2018205545A1 (zh) 数据生成方法、装置、终端及计算机可读存储介质
WO2018036086A1 (zh) 车辆监测方法及装置
WO2020138803A1 (ko) 영상 분석 장치 및 방법
WO2018223857A1 (zh) 文本行识别方法及系统
WO2016088960A1 (ko) 야간 환경에서의 운전자 보조 시스템을 위한 위험 보행자 검출 방법 및 시스템
WO2018149300A1 (zh) 疾病概率的检测方法、装置、设备及计算机可读存储介质
WO2019009664A1 (en) APPARATUS FOR OPTIMIZING THE INSPECTION OF THE OUTSIDE OF A TARGET OBJECT AND ASSOCIATED METHOD
WO2019164281A1 (en) Electronic device and control method thereof
WO2017197802A1 (zh) 字符串模糊匹配方法及装置
WO2014079327A1 (zh) 信息推送方法和系统、数字电视接收终端及计算机存储介质
WO2021029582A1 (en) Co-reference understanding electronic apparatus and controlling method thereof
WO2017148035A1 (zh) 图像处理方法及装置
WO2018097677A1 (en) Image processing apparatus, image processing method, and computer-readable recording medium thereof
WO2015199354A1 (ko) 인접 합산 이진화를 이용한 동공 추출 방법 및 이를 이용한 동공 추출 제어장치
WO2020091337A1 (ko) 영상 분석 장치 및 방법
WO2018082186A1 (zh) 电视机的emi定位方法及装置
WO2018098879A1 (zh) 数字水印加密方法及装置
WO2017101259A1 (zh) 图片显示方法及装置
WO2016169219A1 (zh) 提取人脸纹理的方法及装置
WO2018076560A1 (zh) 画面显示方法和装置
WO2014185714A1 (ko) 의료 영상 화질 개선 방법 및 그 장치

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16907121

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16907121

Country of ref document: EP

Kind code of ref document: A1