CN110245648A - The alert system of wisdom list based on Identification of Images - Google Patents

Abstract

The embodiment of the present invention discloses a smart single police system based on portrait recognition, including: a front-end collection device for collecting law enforcement data; an intelligent processing terminal for receiving and storing the law enforcement data, and determining targets according to the law enforcement data information, comparing the target information with pre-stored information; when the target information matches the pre-stored information, determine the alarm information according to the matched pre-stored information, and determine the matched pre-stored information and the alarm information The comparison result information; the output terminal is used to receive the comparison result information of the intelligent processing terminal. The present invention is used to solve the problem in the prior art that it is impossible to carry out image recognition on law enforcement objects and environments in real time. It is not affected by the network environment and the actual operation environment, and can effectively capture dynamic and static images under conditions such as public security moving and standing. portrait, and compare it effectively with the built-in portrait recognition software of the device.

Description

Intelligent single police system based on portrait recognition

technical field

The embodiment of the present invention relates to the technical field of mobile law enforcement, in particular to an intelligent single police system based on portrait recognition.

Background technique

With the development of computer technology and artificial intelligence, the means of scientific and technological informatization are constantly being introduced, and they are gradually applied to the field of police work. The monitoring front-end construction with high-definition video monitoring technology as the core provides strong support for cracking down on crimes and conducting rapid investigations. As an emerging technology in the field of video images, portrait recognition technology is playing an increasingly important role in the actual application of public security with the introduction of deep learning.

As an emerging technology in the field of video images, portrait recognition technology integrates computer graphics processing technology and biometrics principles, and uses computer graphics technology to extract portrait feature points from videos. Use the principle of biostatistics to analyze and supervise the mathematical model, that is, the face feature template. Use the built face feature template and the face image of the person under test to perform feature analysis, and give a similarity value according to the analysis result, and use this value to determine whether they are the same person.

Relying on face and human body recognition technology, portrait recognition products realize functions such as portrait storage, retrieval, comparison, and alarm through the structuring of portraits in video images.

Most of the functions of the mobile law enforcement system are limited to on-site collection, and then store relevant data as subsequent evidence. There is no real-time identification and matching function for on-site law enforcement, such as image recognition, etc., and it is impossible to perform real-time image recognition on the subject and environment of law enforcement, making law enforcement Efficiency and effectiveness of law enforcement are still not high enough.

Contents of the invention

To this end, the embodiment of the present invention provides a smart single police system based on portrait recognition to solve the problem in the prior art that it is impossible to perform real-time image recognition on law enforcement objects and environments.

In order to achieve the above object, embodiments of the present invention provide the following technical solutions:

The present invention provides a smart single police system based on portrait recognition, which is characterized in that it includes:

Front-end collection equipment for collecting law enforcement data;

The intelligent processing terminal is used to receive and store the law enforcement data, determine the target information according to the law enforcement data, and compare the target information with the pre-stored information; when the target information matches the pre-stored information, according to the The matched pre-stored information determines alarm information, and the matched pre-stored information and the alarm information are determined as comparison result information;

The output terminal is used to receive the comparison result information of the intelligent processing terminal.

In one embodiment of the present invention, the law enforcement data includes videos taken of law enforcement objects.

In another embodiment of the present invention, the front-end acquisition device is a panoramic law enforcement recorder.

In yet another embodiment of the present invention, the front-end acquisition device is a portable camera for glasses.

In yet another embodiment of the present invention, the front-end acquisition device is a portable camera hung on the ear.

In yet another embodiment of the present invention, the intelligent processing terminal includes a video decoding module, a portrait detection module, a portrait tracking module, a feature extraction module, a pre-judgment module, a portrait comparison module and a database connected in sequence.

In yet another embodiment of the present invention, the video decoding module decodes each frame of image, the portrait detection module detects the portrait area appearing in each frame of image, the portrait tracking module tracks the portrait area, the The feature extraction module selects the face snapshot with the best angle and clarity among all trajectories of the same person as the best snapshot, provides the best snapshot to the pre-judgment module, and compares it with the database through the portrait comparison module right.

In yet another embodiment of the present invention, it further includes a computer unit connected to the intelligent processing terminal for querying historical data and managing portrait information in the database.

The present invention is used to solve the problem in the prior art that it is impossible to carry out image recognition on law enforcement objects and environments in real time. It is not affected by the network environment and the actual operation environment, and can effectively capture dynamic and static images under conditions such as public security moving and standing. portrait, and compare it effectively with the built-in portrait recognition software of the device.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings that are required in the description of the embodiments or the prior art. Apparently, the drawings in the following description are only exemplary, and those skilled in the art can also obtain other implementation drawings according to the provided drawings without creative work.

Fig. 1 is a schematic diagram of a smart single police system based on portrait recognition provided by an embodiment of the present invention;

Fig. 2 is a schematic diagram of an intelligent processing terminal provided by another embodiment of the present invention.

In the figure: 1-intelligent processing terminal, 11-video decoding module, 12-portrait detection module, 13-portrait tracking module, 14-feature extraction module, 15-pre-judgment module, 16-portrait comparison module, 17-database, 2 - front-end acquisition equipment, 3 - output terminal.

Detailed ways

The implementation mode of the present invention is illustrated by specific specific examples below, and those who are familiar with this technology can easily understand other advantages and effects of the present invention from the contents disclosed in this description. Obviously, the described embodiments are a part of the present invention. , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The present invention provides a smart single police system based on portrait recognition, including:

The front-end collection device 2 is used to collect law enforcement data;

The intelligent processing terminal 1 is used to receive and store the law enforcement data, determine target information according to the law enforcement data, and compare the target information with pre-stored information; when the target information matches the pre-stored information, determining alarm information according to the matched pre-stored information, and determining the matched pre-stored information and the alarm information as comparison result information;

The output terminal 3 is used to receive the comparison result information of the intelligent processing terminal 1 .

Preferably, the law enforcement data includes videos taken by law enforcement objects; the front-end collection device 2 is a panoramic law enforcement recorder; the front-end collection device 2 is a portable camera for glasses; the front-end collection device 2 is a portable camera with ear hooks; The intelligent processing terminal 1 comprises a video decoding module 11, a portrait detection module 12, a portrait tracking module 13, a feature extraction module 14, a pre-judgment module 15, a portrait comparison module 16 and a database 17 connected in sequence; the video decoding module 11 decodes For each frame of image, the portrait detection module 12 detects the portrait area that appears in each frame of image, the portrait tracking module 13 tracks the portrait area, and the feature extraction module 14 selects the angle and clarity in all trajectories of the same person. The face snapshot with the best degree of accuracy is used as the best snapshot (that is, the image with the best visual effect), and the best snapshot is provided to the pre-judgment module 15, and compared with the portrait comparison module 16 and the database 17 Yes; it also includes a computer unit connected to the intelligent processing terminal 1 for querying historical data and managing portrait information in the database.

As shown in Figure 1, an embodiment of the present invention provides a smart single police system based on portrait recognition, including:

The front-end collection device 2 is used to collect law enforcement data;

The intelligent processing terminal 1 is used to receive and store the law enforcement data, determine target information according to the law enforcement data, and compare the target information with pre-stored information; when the target information matches the pre-stored information, determining alarm information according to the matched pre-stored information, and determining the matched pre-stored information and the alarm information as comparison result information;

The output terminal 3 is used to receive the comparison result information of the intelligent processing terminal 1 .

The front-end acquisition device 2 is various cameras, especially various types of network cameras that meet the GB28181 network protocol, and the camera form can be a panoramic law enforcement recorder, a portable camera with glasses or a portable camera with ear hooks, etc.; Captured video.

As shown in Fig. 2, the intelligent processing terminal 1 provided by another embodiment of the present invention, the intelligent processing terminal 1 includes a video decoding module 11, a portrait detection module 12, a portrait tracking module 13, a feature extraction module 14, a preset Judgment module 15, portrait comparison module 16 and database 17.

Wherein: the video decoding module 11 decodes each frame of images, the portrait detection module 12 detects the portrait area occurring in each frame of images, the portrait tracking module 13 tracks the portrait area, and the feature extraction module 14 selects The face snapshot with the best angle and clarity in all trajectories of the same person is used as the best snapshot (that is, the image with the best visual effect), and the best snapshot is provided to the pre-judgment module 15, and passed through the The portrait comparison module 16 is compared with the database 17 .

It also includes a computer unit connected to the intelligent processing terminal 1 for querying historical data and managing portrait information in the database.

The single police system provided by the present invention can obtain the information to be identified in the first video image during the public security law enforcement process; match the human body information to be identified with the portrait information in the portrait association database, and determine the identity information corresponding to the portrait to be identified .

Although the present invention has been described in detail with general descriptions and specific examples above, it is obvious to those skilled in the art that some modifications or improvements can be made on the basis of the present invention. Therefore, the modifications or improvements made on the basis of not departing from the spirit of the present invention all belong to the protection scope of the present invention.

Claims (8)

1. A smart single police system based on portrait recognition, characterized in that it comprises: Front-end collection equipment (2), used for collecting law enforcement data; An intelligent processing terminal (1), configured to receive and store the law enforcement data, determine target information according to the law enforcement data, and compare the target information with pre-stored information; when the target information matches the pre-stored information , determining the alarm information according to the matched pre-stored information, and determining the matched pre-stored information and the alarm information as the comparison result information; The output terminal (3) is used to receive the comparison result information of the intelligent processing terminal (1). 2. A smart individual police system based on portrait recognition as claimed in claim 1, characterized in that: said law enforcement data includes videos taken of law enforcement objects. 3. A kind of smart single police system based on portrait recognition as claimed in claim 1, characterized in that: the front-end acquisition device (2) is a panoramic law enforcement recorder. 4. A kind of intelligence single-police system based on portrait recognition as claimed in claim 1, is characterized in that: described front-end collection device (2) is glasses portable camera. 5. A smart single-police system based on portrait recognition as claimed in claim 1, characterized in that: said front-end acquisition device (2) is a portable camera with ear hooks. 6. a kind of intelligent single police system based on portrait recognition as claimed in claim 1, is characterized in that: described intelligent processing terminal (1) comprises video decoding module (11), portrait detection module (12), A portrait tracking module (13), a feature extraction module (14), a pre-judgment module (15), a portrait comparison module (16) and a database (17). 7. A kind of intelligent single police system based on portrait recognition as claimed in claim 6, is characterized in that: described video decoding module (11) decodes each frame image, and described portrait detection module (12) detects each frame The portrait area that occurs in the image, the portrait tracking module (13) tracks the portrait area, and the feature extraction module (14) selects the best snapshot of the face of the same person in all tracks with the best angle and clarity as the best snapshot , providing the best snapshot to the pre-judgment module (15), and comparing it with the portrait comparison module (16) and database (17). 8. A kind of intelligent single police system based on portrait recognition as claimed in claim 1, is characterized in that: also comprise computer unit, described computer unit is connected with described intelligent processing terminal (1), is used for querying historical data and management Portrait information in the database.