CN111368577A - an image processing system - Google Patents
an image processing system Download PDFInfo
- Publication number
- CN111368577A CN111368577A CN202010232705.1A CN202010232705A CN111368577A CN 111368577 A CN111368577 A CN 111368577A CN 202010232705 A CN202010232705 A CN 202010232705A CN 111368577 A CN111368577 A CN 111368577A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- acquisition
- image acquisition
- module
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
本发明公开了一种图像处理系统，包括：图像采集模块，用于采集内载二维码标签的目标图像，该二维码标签内载镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度；图像重构模块，用于获取该目标图像对应的镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度，并基于目标图像要求完成图像的预处理。本发明通过三维姿态传感器、GPS定位模块结合二维标签技术实现了图像采集终端与目标采集位置/参考位置之间相对姿态信息的获取，避免了由于标记物反光或部分遮挡因素影响时检测失败的情况。
The invention discloses an image processing system, comprising: an image acquisition module for acquiring a target image carrying a two-dimensional code label, wherein the two-dimensional code label contains a lens model, an image acquisition mode, and an image acquisition terminal during image acquisition. The three-dimensional attitude information and the distance and angle of the image acquisition terminal relative to the target acquisition position/reference position; the image reconstruction module is used to obtain the lens model corresponding to the target image, the image acquisition mode, and the three-dimensional attitude information of the image acquisition terminal during image acquisition. And the distance and angle of the image acquisition terminal relative to the target acquisition position/reference position, and complete the image preprocessing based on the target image requirements. The invention realizes the acquisition of relative attitude information between the image acquisition terminal and the target acquisition position/reference position through the three-dimensional attitude sensor, the GPS positioning module and the two-dimensional label technology, and avoids the failure of detection due to the influence of the reflection of the marker or the partial occlusion factor. Happening.
Description
技术领域technical field
本发明涉及图像处理领域，具体涉及一种图像处理系统。The invention relates to the field of image processing, in particular to an image processing system.
背景技术Background technique
目前，大多数图像采集时的相机的相对姿态信息计算都是基于标记物实现，这类标记物一般是规则的四边形，例如正方形，标记物外侧由一个黑色边框围绕，内部进行编码用于区分不同的标记物，标记物检测的目的是对标记物的四个角点进行定位，它的优点是结构简单、易于识别。但是也存在一些缺点，标记物识别过程中易受到标记物反光、遮挡等因素的影响，容易造成了标记物检测的失败。At present, most of the relative pose information of the camera during image acquisition is calculated based on markers. Such markers are generally regular quadrilaterals, such as squares. The outside of the marker is surrounded by a black border, and the inside is coded to distinguish different The purpose of marker detection is to locate the four corners of the marker, and its advantages are simple structure and easy identification. However, there are also some disadvantages. The marker recognition process is easily affected by factors such as reflection and occlusion of the marker, which easily causes the failure of marker detection.
发明内容SUMMARY OF THE INVENTION
为解决上述问题，本发明提供了一种图像处理系统，避免了由于标记物反光或部分遮挡因素影响时检测失败的情况。In order to solve the above problem, the present invention provides an image processing system, which avoids the situation of detection failure due to the influence of reflection or partial occlusion of the marker.
为实现上述目的，本发明采取的技术方案为：To achieve the above object, the technical scheme adopted in the present invention is:
一种图像处理系统，包括：An image processing system, comprising:
图像采集模块，用于采集内载二维码标签的目标图像，该二维码标签内载镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度；The image acquisition module is used to collect the target image containing the two-dimensional code label. The two-dimensional code label contains the lens model, the image acquisition mode, the three-dimensional attitude information of the image acquisition terminal during image acquisition, and the image acquisition terminal relative to the target acquisition position. / the distance and angle of the reference position;
图像重构模块，用于获取该目标图像对应的镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度，并基于目标图像要求完成图像的预处理；The image reconstruction module is used to obtain the lens model corresponding to the target image, the image capture mode, the three-dimensional attitude information of the image capture terminal during image capture, and the distance and angle of the image capture terminal relative to the target capture position/reference position, and based on the target The image requires image preprocessing;
图像分类模块，用于基于预设的目标检测模型实现图像的检测，并根据检测结果实现图像的分类。The image classification module is used to detect images based on a preset target detection model, and to classify images according to the detection results.
进一步地，所述二维码标签设置在目标图像的右下角，与目标图像的颜色融合成一体。Further, the two-dimensional code label is arranged at the lower right corner of the target image, and is integrated with the color of the target image.
进一步地，图像采集模块包括：Further, the image acquisition module includes:
图像采集终端，用于实现目标图像的预采集；The image acquisition terminal is used to realize the pre-acquisition of the target image;
二维码标签生成模块，用于通过搭载在图像采集终端内的三维姿态传感器实现图像采集终端三维姿态数据的采集，通过搭载在图像采集终端内的工况采集模块实现图像采集终端图像采集模式的采集，通过放置在目标采集位置/参考位置处的GPS定位模块以及搭载在图像采集终端上的另一GPS定位模块实现目标采集位置与图像采集终端之间距离、角度的获取，并基于数据处理终端上传的镜头型号生成目标图像的二维码标签；The two-dimensional code label generation module is used to realize the collection of three-dimensional attitude data of the image acquisition terminal through the three-dimensional attitude sensor mounted in the image acquisition terminal, and realize the image acquisition mode of the image acquisition terminal through the working condition acquisition module mounted in the image acquisition terminal. Acquisition, through the GPS positioning module placed at the target acquisition position/reference position and another GPS positioning module mounted on the image acquisition terminal to achieve the acquisition of the distance and angle between the target acquisition position and the image acquisition terminal, and based on the data processing terminal The uploaded lens model generates the QR code label of the target image;
二维码标签标记模块，用于通过图像颜色识别模块实现目标位置图像颜色的识别，并基于识别结果实现二维码标签颜色的重构，并经完成重构后的二维码标签标记在目标位置处。首先基于预设的图像标记框在目标图像右下角框出目标位置，然后通过图像颜色识别模块实现目标位置图像颜色的识别，再将识别所得的颜色与二维码当前标签颜色作差，根据差值实现二维码标签颜色的重构。The two-dimensional code label marking module is used to realize the identification of the image color of the target position through the image color recognition module, and realize the reconstruction of the color of the two-dimensional code label based on the identification result, and the reconstructed two-dimensional code label is marked on the target. location. First, frame the target position in the lower right corner of the target image based on the preset image marker frame, and then realize the image color recognition of the target position through the image color recognition module, and then make the difference between the recognized color and the current label color of the QR code. The value implements the reconstruction of the color of the QR code label.
进一步地，所述目标图像要求基于数据处理终端录入，以填空的方式录入，比如图像的偏转角度、饱和度、亮度、对比度、分辨率、锐化程度、图像比例等。Further, the target image is required to be entered based on the data processing terminal, and is entered in the form of filling in the blanks, such as the deflection angle, saturation, brightness, contrast, resolution, sharpness, and image scale of the image.
进一步地，所述手机app以图的形式实现距离、角度的计算，同时在该图上实现当前图像采集终端三维姿态信息的显示。Further, the mobile app realizes the calculation of the distance and the angle in the form of a graph, and at the same time realizes the display of the three-dimensional attitude information of the current image acquisition terminal on the graph.
进一步地，所述目标检测模型采用ssd_Inception_V3_coco模型,该模型采用ssd目标检测算法，用coco数据集预训练Inception_V3深度神经网络,然后用先前准备好的数据集训练该模型，微调深度神经网络中的各项参数，最后得到合适的目标检测模型。Further, the target detection model adopts the ssd_Inception_V3_coco model, which adopts the ssd target detection algorithm, pre-trains the Inception_V3 deep neural network with the coco data set, and then trains the model with the previously prepared data set, and fine-tunes each in the deep neural network. Item parameters, and finally get a suitable target detection model.
进一步地，所述图像重构模块内设有：Further, the image reconstruction module is provided with:
相对姿态计算模块，用于根据图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度实现图像采集终端相对姿态的计算；The relative attitude calculation module is used to calculate the relative attitude of the image acquisition terminal according to the three-dimensional attitude information of the image acquisition terminal during image acquisition and the distance and angle of the image acquisition terminal relative to the target acquisition position/reference position;
图像预处理模块，用于根据目标图像采集要求以及获取到的获取该目标图像对应的镜头型号、图像采集模式进行图像的预处理。The image preprocessing module is used for image preprocessing according to the acquisition requirements of the target image and the acquired lens model and image acquisition mode corresponding to the acquisition of the target image.
本发明具有以下有益效果：The present invention has the following beneficial effects:
1）通过三维姿态传感器、GPS定位模块结合二维标签技术实现了图像采集终端与目标采集位置/参考位置之间相对姿态信息的获取，避免了由于标记物反光或部分遮挡因素影响时检测失败的情况。1) The acquisition of the relative attitude information between the image acquisition terminal and the target acquisition position/reference position is realized through the three-dimensional attitude sensor, GPS positioning module and two-dimensional label technology, which avoids the failure of detection due to the reflection of markers or partial occlusion factors. Happening.
2）二维码标签设置在目标图像的右下角，且与目标图像的颜色融合成一体，从而可以避免二维码标签对目标图像的影响2) The QR code label is set in the lower right corner of the target image, and is integrated with the color of the target image, so that the influence of the QR code label on the target image can be avoided.
3）通过目标检测模型的应用可以实现目标图像的自动分类，减少了人为查看分类的工作量。3) The automatic classification of target images can be realized through the application of the target detection model, which reduces the workload of manual viewing and classification.
4）可根据不同的目标图像要求基于原始图像自动获取批量图像，省时省力。4) Batch images can be automatically acquired based on the original images according to different target image requirements, saving time and effort.
5）三维姿态传感器、GPS定位模块的应用还可以用来辅助实现标定的摄像机参数下目标图像的采集。5) The application of three-dimensional attitude sensor and GPS positioning module can also be used to assist in the acquisition of target images under the calibrated camera parameters.
附图说明Description of drawings
图1为本发明实施例1的一种图像处理系统的系统框图。FIG. 1 is a system block diagram of an image processing system according to Embodiment 1 of the present invention.
具体实施方式Detailed ways
为了使本发明的目的及优点更加清楚明白，以下结合实施例对本发明进行进一步详细说明。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。In order to make the objects and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.
如图1所示，本发明实施例提供了一种图像处理系统，包括：As shown in FIG. 1, an embodiment of the present invention provides an image processing system, including:
图像采集模块，用于采集内载二维码标签的目标图像，该二维码标签内载镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度；The image acquisition module is used to collect the target image containing the two-dimensional code label. The two-dimensional code label contains the lens model, the image acquisition mode, the three-dimensional attitude information of the image acquisition terminal during image acquisition, and the image acquisition terminal relative to the target acquisition position. / the distance and angle of the reference position;
图像重构模块，用于获取该目标图像对应的镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度，并基于目标图像要求完成图像的预处理；The image reconstruction module is used to obtain the lens model corresponding to the target image, the image capture mode, the three-dimensional attitude information of the image capture terminal during image capture, and the distance and angle of the image capture terminal relative to the target capture position/reference position, and based on the target The image requires image preprocessing;
图像分类模块，用于基于预设的目标检测模型实现图像的检测，并根据检测结果实现图像的分类。The image classification module is used to detect images based on a preset target detection model, and to classify images according to the detection results.
本实施例中，所述二维码标签设置在目标图像的右下角，与目标图像的颜色融合成一体。In this embodiment, the two-dimensional code label is set at the lower right corner of the target image, and is integrated with the color of the target image.
本实施例中，图像采集模块包括：In this embodiment, the image acquisition module includes:
图像采集终端，用于实现目标图像的预采集，采用相机；The image acquisition terminal is used to realize the pre-acquisition of the target image, using a camera;
二维码标签生成模块，用于通过搭载在图像采集终端内的三维姿态传感器实现图像采集终端三维姿态数据的采集（当图像采集终端处于水平状态时，镜头水平向前，三维姿态传感器所采集到的姿态信息为（0，0,0）），通过搭载在图像采集终端内的工况采集模块实现图像采集终端图像采集模式的采集，通过放置在目标采集位置/参考位置处的GPS定位模块以及搭载在图像采集终端上的另一GPS定位模块实现目标采集位置与图像采集终端之间距离、角度的获取，并基于数据处理终端上传的镜头型号生成目标图像的二维码标签；The two-dimensional code label generation module is used to collect the three-dimensional attitude data of the image acquisition terminal through the three-dimensional attitude sensor mounted in the image acquisition terminal (when the image acquisition terminal is in a horizontal state, the lens is horizontally forward, and the data collected by the three-dimensional attitude sensor The attitude information of the image acquisition terminal is (0, 0, 0)), the image acquisition mode acquisition of the image acquisition terminal is realized through the working condition acquisition module mounted in the image acquisition terminal, and the GPS positioning module placed at the target acquisition position/reference position and Another GPS positioning module mounted on the image acquisition terminal realizes the acquisition of the distance and angle between the target acquisition position and the image acquisition terminal, and generates a QR code label of the target image based on the lens model uploaded by the data processing terminal;
二维码标签标记模块，用于通过图像颜色识别模块实现目标位置图像颜色的识别，并基于识别结果实现二维码标签颜色的重构，并经完成重构后的二维码标签标记在目标位置处。首先基于预设的图像标记框在目标图像右下角框出目标位置，然后通过图像颜色识别模块实现目标位置图像颜色的识别，再将识别所得的颜色与二维码当前标签颜色作差，根据差值实现二维码标签颜色的重构。The two-dimensional code label marking module is used to realize the identification of the image color of the target position through the image color recognition module, and realize the reconstruction of the color of the two-dimensional code label based on the identification result, and the reconstructed two-dimensional code label is marked on the target. location. First, frame the target position in the lower right corner of the target image based on the preset image marker frame, and then realize the image color recognition of the target position through the image color recognition module, and then make the difference between the recognized color and the current label color of the QR code. The value implements the reconstruction of the color of the QR code label.
本实施例中，所述目标图像要求基于数据处理终端录入，以填空的方式录入，比如图像的偏转角度、饱和度、亮度、对比度、分辨率、锐化程度、图像比例等。所述手机app以图的形式实现距离、角度的计算，同时在该图上实现当前图像采集终端三维姿态信息的显示。In this embodiment, the target image is required to be entered based on the data processing terminal, and is entered by filling in the blanks, such as the deflection angle, saturation, brightness, contrast, resolution, sharpness, and image scale of the image. The mobile phone app realizes the calculation of distance and angle in the form of a graph, and at the same time realizes the display of three-dimensional attitude information of the current image acquisition terminal on the graph.
本实施例中，所述目标检测模型采用ssd_Inception_V3_coco模型,该模型采用ssd目标检测算法，用coco数据集预训练Inception_V3深度神经网络,然后用先前准备好的数据集训练该模型，微调深度神经网络中的各项参数，最后得到合适的目标检测模型。In this embodiment, the target detection model adopts the ssd_Inception_V3_coco model, which adopts the ssd target detection algorithm, uses the coco data set to pre-train the Inception_V3 deep neural network, and then uses the previously prepared data set to train the model, fine-tuning the deep neural network. parameters, and finally obtain a suitable target detection model.
本实施例中，所述图像重构模块内设有：In this embodiment, the image reconstruction module is provided with:
相对姿态计算模块，用于根据图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度实现图像采集终端相对姿态的计算；The relative attitude calculation module is used to calculate the relative attitude of the image acquisition terminal according to the three-dimensional attitude information of the image acquisition terminal during image acquisition and the distance and angle of the image acquisition terminal relative to the target acquisition position/reference position;
图像预处理模块，用于根据目标图像采集要求以及获取到的获取该目标图像对应的镜头型号、图像采集模式进行图像的预处理。The image preprocessing module is used for image preprocessing according to the acquisition requirements of the target image and the acquired lens model and image acquisition mode corresponding to the acquisition of the target image.
本实施例中，所述图像采集终端上设有用于启动三维姿态传感器、工况采集模块、GPS定位模块的按钮，在按下快门的同时需按下该按钮从而实现当前图像的图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度数据的自动生成，照片生成后，三维姿态传感器、工况采集模块、GPS定位模块自动关闭，该自动关闭功能基于定时模块实现，根据不同的相机图像生成时间可定时自动关闭的时间。In this embodiment, the image acquisition terminal is provided with a button for starting the three-dimensional attitude sensor, the working condition acquisition module, and the GPS positioning module. When pressing the shutter, the button needs to be pressed to realize the image acquisition mode of the current image, The three-dimensional attitude information of the image acquisition terminal and the distance and angle data of the image acquisition terminal relative to the target acquisition position/reference position are automatically generated during image acquisition. After the photo is generated, the three-dimensional attitude sensor, the working condition acquisition module, and the GPS positioning module are automatically closed. The automatic shutdown function is implemented based on a timing module, and the automatic shutdown time can be timed according to different camera image generation times.
本具体实施使用时，首先通过手机app上传镜头型号以及目标图像采集要求，然后镜头型号的识别实现三维姿态传感器、工况采集模块、GPS定位模块自动关闭时间的自动设置，完成后，即可进行目标图像的采集，在按下快门的同时按下用于启动三维姿态传感器、工况采集模块、GPS定位模块的按钮，从而实现当前图像的图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度数据的自动生成，数据处理终端接收目标图像信息、图像采集模式信息、图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度信息，根据数据生成的时间完成数据的一一对应分类，分类结束后，二维码标签生成模块启动，生成目标图像的二维码标签，紧接着二维码标签标记模块启动，通过图像颜色识别模块实现目标位置图像颜色的识别，并基于识别结果实现二维码标签颜色的重构，并经完成重构后的二维码标签标记在目标位置处，完成标记后，图像重构模块启动，通过识别二维码标签获取该目标图像对应的镜头型号、图像采集模式、图像采集时图像采集终端的三维姿态信息以及图像采集终端相对于目标采集位置/参考位置的距离和角度，实现图像采集终端相对姿态的计算，并基于目标图像要求完成图像的预处理，基于图像分类模块采用ssd_Inception_V3_coco模型实现图像的自动分类储存。When this specific implementation is used, first upload the lens model and target image acquisition requirements through the mobile phone app, and then the recognition of the lens model realizes the automatic setting of the three-dimensional attitude sensor, the working condition acquisition module, and the automatic closing time of the GPS positioning module. To collect the target image, press the button for starting the 3D attitude sensor, working condition collection module, and GPS positioning module while pressing the shutter, so as to realize the image collection mode of the current image and the 3D attitude information of the image collection terminal during image collection. And the automatic generation of the distance and angle data of the image acquisition terminal relative to the target acquisition position/reference position, the data processing terminal receives the target image information, the image acquisition mode information, the three-dimensional attitude information of the image acquisition terminal, and the image acquisition terminal relative to the target acquisition position. / Refer to the distance and angle information of the position, and complete the one-to-one correspondence classification of the data according to the time of data generation. After the classification, the QR code label generation module starts to generate the QR code label of the target image, followed by the QR code label mark The module is started, and the image color recognition of the target position is realized through the image color recognition module, and the reconstruction of the color of the QR code label is realized based on the recognition result, and the reconstructed QR code label is marked at the target position. , the image reconstruction module starts, and obtains the lens model corresponding to the target image, the image acquisition mode, the three-dimensional attitude information of the image acquisition terminal during image acquisition, and the distance of the image acquisition terminal relative to the target acquisition position/reference position by identifying the QR code label. and angle, realize the calculation of the relative posture of the image acquisition terminal, and complete the image preprocessing based on the target image requirements. Based on the image classification module, the ssd_Inception_V3_coco model is used to realize the automatic classification and storage of images.
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以作出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。The above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be It is regarded as the protection scope of the present invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010232705.1A CN111368577B (en) | 2020-03-28 | 2020-03-28 | Image processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010232705.1A CN111368577B (en) | 2020-03-28 | 2020-03-28 | Image processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111368577A true CN111368577A (en) | 2020-07-03 |
| CN111368577B CN111368577B (en) | 2023-04-07 |
Family
ID=71209140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010232705.1A Active CN111368577B (en) | 2020-03-28 | 2020-03-28 | Image processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111368577B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111775934A (en) * | 2020-07-21 | 2020-10-16 | 湖南汽车工程职业学院 | Intelligent driving obstacle avoidance system of automobile |
| CN111891129A (en) * | 2020-08-17 | 2020-11-06 | 湖南汽车工程职业学院 | Intelligent driving system of electric automobile |
| CN111899514A (en) * | 2020-08-19 | 2020-11-06 | 陇东学院 | Artificial intelligence's detection system that blocks up |
| CN112188251A (en) * | 2020-09-24 | 2021-01-05 | 青岛海信移动通信技术股份有限公司 | Image processing method and image processing apparatus |
| CN112766250A (en) * | 2020-12-28 | 2021-05-07 | 合肥联宝信息技术有限公司 | Image processing method, device and computer readable storage medium |
| CN113191388A (en) * | 2021-03-31 | 2021-07-30 | 中国船舶重工集团公司第七一九研究所 | Image acquisition system for target detection model training and sample generation method |
| CN114568185A (en) * | 2022-04-08 | 2022-06-03 | 西藏自治区农牧科学院蔬菜研究所 | Method for preventing and treating diseases and insect pests of fruit trees |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6814291B1 (en) * | 2003-12-15 | 2004-11-09 | Pitney Bowes Inc. | Robust barcode reader |
| WO2007124116A2 (en) * | 2006-04-20 | 2007-11-01 | Metrologic Instruments, Inc. | Method of and apparatus for dynamically and adaptively controlling system control parameters in a digital image capture and processing system |
| US20140002329A1 (en) * | 2012-06-29 | 2014-01-02 | Sony Computer Entertainment Inc. | Image processing device, image processing method, and image processing system |
| CN104748746A (en) * | 2013-12-29 | 2015-07-01 | 刘进 | Attitude determination and virtual reality roaming method of intelligent machine |
| US20170212520A1 (en) * | 2016-01-27 | 2017-07-27 | Hon Hai Precision Industry Co., Ltd. | Computer vision positioning system and method for the same |
| CN107205219A (en) * | 2016-03-16 | 2017-09-26 | 伊姆西公司 | Method and apparatus for positioning |
| CN107526329A (en) * | 2017-08-28 | 2017-12-29 | 吉林农业科技学院 | Robot management system based on artificial intelligence design |
| CN108225303A (en) * | 2018-01-18 | 2018-06-29 | 水岩智能科技（宁波）有限公司 | Two-dimensional code positioning label, and positioning navigation system and method based on two-dimensional code |
| CN109543489A (en) * | 2019-01-04 | 2019-03-29 | 广州广电研究院有限公司 | Localization method, device and storage medium based on two dimensional code |
-
2020
- 2020-03-28 CN CN202010232705.1A patent/CN111368577B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6814291B1 (en) * | 2003-12-15 | 2004-11-09 | Pitney Bowes Inc. | Robust barcode reader |
| WO2007124116A2 (en) * | 2006-04-20 | 2007-11-01 | Metrologic Instruments, Inc. | Method of and apparatus for dynamically and adaptively controlling system control parameters in a digital image capture and processing system |
| US20140002329A1 (en) * | 2012-06-29 | 2014-01-02 | Sony Computer Entertainment Inc. | Image processing device, image processing method, and image processing system |
| CN104748746A (en) * | 2013-12-29 | 2015-07-01 | 刘进 | Attitude determination and virtual reality roaming method of intelligent machine |
| US20170212520A1 (en) * | 2016-01-27 | 2017-07-27 | Hon Hai Precision Industry Co., Ltd. | Computer vision positioning system and method for the same |
| CN107205219A (en) * | 2016-03-16 | 2017-09-26 | 伊姆西公司 | Method and apparatus for positioning |
| CN107526329A (en) * | 2017-08-28 | 2017-12-29 | 吉林农业科技学院 | Robot management system based on artificial intelligence design |
| CN108225303A (en) * | 2018-01-18 | 2018-06-29 | 水岩智能科技（宁波）有限公司 | Two-dimensional code positioning label, and positioning navigation system and method based on two-dimensional code |
| CN109543489A (en) * | 2019-01-04 | 2019-03-29 | 广州广电研究院有限公司 | Localization method, device and storage medium based on two dimensional code |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111775934A (en) * | 2020-07-21 | 2020-10-16 | 湖南汽车工程职业学院 | Intelligent driving obstacle avoidance system of automobile |
| CN111891129A (en) * | 2020-08-17 | 2020-11-06 | 湖南汽车工程职业学院 | Intelligent driving system of electric automobile |
| CN111899514A (en) * | 2020-08-19 | 2020-11-06 | 陇东学院 | Artificial intelligence's detection system that blocks up |
| CN112188251A (en) * | 2020-09-24 | 2021-01-05 | 青岛海信移动通信技术股份有限公司 | Image processing method and image processing apparatus |
| CN112766250A (en) * | 2020-12-28 | 2021-05-07 | 合肥联宝信息技术有限公司 | Image processing method, device and computer readable storage medium |
| CN113191388A (en) * | 2021-03-31 | 2021-07-30 | 中国船舶重工集团公司第七一九研究所 | Image acquisition system for target detection model training and sample generation method |
| CN114568185A (en) * | 2022-04-08 | 2022-06-03 | 西藏自治区农牧科学院蔬菜研究所 | Method for preventing and treating diseases and insect pests of fruit trees |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111368577B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111368577A (en) | an image processing system | |
| CN109155078B (en) | Method and device for generating set of sample images, electronic equipment and storage medium | |
| CN109934848B (en) | A method for precise positioning of moving objects based on deep learning | |
| JP3624353B2 (en) | Three-dimensional shape measuring method and apparatus | |
| CN110168562B (en) | Depth-based control method, depth-based control device and electronic device | |
| CN111860652B (en) | Method, device, equipment and medium for measuring animal body weight based on image detection | |
| WO2019035155A1 (en) | Image processing system, image processing method, and program | |
| WO2018075053A1 (en) | Object pose based on matching 2.5d depth information to 3d information | |
| CN104361353A (en) | Application of area-of-interest positioning method to instrument monitoring identification | |
| CN104715238A (en) | Pedestrian detection method based on multi-feature fusion | |
| CN111738988A (en) | Face depth image generation method, device, electronic device and storage medium | |
| CN109242900B (en) | Focal plane positioning method, processing device, focal plane positioning system and storage medium | |
| CN111967288A (en) | Intelligent three-dimensional object identification and positioning system and method | |
| CN103810475A (en) | Target object recognition method and apparatus | |
| CN112807108B (en) | Method for detecting tooth correction state in orthodontic correction process | |
| CN105825543A (en) | Multi-view dense point cloud generation method and system based on low-altitude remote sensing images | |
| CN106155299A (en) | A kind of method and device that smart machine is carried out gesture control | |
| CN106651959A (en) | Optical field camera micro-lens array geometric parameter calibration method | |
| CN112150448A (en) | Image processing method, device and equipment, storage medium | |
| CN114708519A (en) | Elk identification and morphological contour parameter extraction method based on unmanned aerial vehicle remote sensing | |
| CN111399634A (en) | Gesture-guided object recognition method and device | |
| CN106235486B (en) | Personalized clothing method based on 3D anthropometric scanning instrument | |
| CN101661623A (en) | Three-dimensional tracking method of deformable body based on linear programming | |
| CN110059537A (en) | A kind of three-dimensional face data acquisition methods and device based on Kinect sensor | |
| CN112365578A (en) | Three-dimensional human body model reconstruction system and method based on double cameras |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |