Target tracking system based on video perception

Abstract

The invention discloses a target tracking system based on video perception. The target tracking system comprises a monitoring shooting unit, a data acquisition unit, a data transmission unit, a data storage unit, a data processing unit, a remote monitoring unit, an image correction unit, a feature extraction unit, a matching tracking unit and a UPS power supply unit. The monitoring shooting unit is used for carrying out video monitoring shooting through video shooting equipment; and the data acquisition unit is used for performing real-time acquisition on data generated in the process of performing video sensing tracking on the target. The invention belongs to the technical field of video tracking. By integrating the visibility, illuminance, light inlet amount, noise value and luminous flux multi-dimensional information acquisition module, the system can evaluate the shooting environment in real time, automatically adjust image parameters, effectively reduce noise interference and enhance image definition, so that the system can accurately identify target features, and the target features can be accurately identified even in a complex and changeable low-illumination environment. And rapid and accurate target tracking can be realized.

Description

Technical Field

[0001] The present invention relates to the field of video tracking technology, and more specifically discloses a target tracking system based on video perception. Background Art

[0002] With the rapid development of science and technology, video surveillance has been widely used in public safety, traffic management, smart home and other fields. However, under low light conditions, the noise level in the video images captured by video recording equipment usually increases, the video images are blurred, and the details in the video images are often lost, which makes it impossible to effectively extract the key features of the target, increasing the difficulty of target tracking. Summary of the invention

[0003] Purpose of the invention: The purpose of the present invention is to solve the problem that under low light conditions, the noise level in the video images taken by the video shooting equipment usually increases, the video images are blurred, and at the same time, the detail information in the video images is often seriously lost, which leads to the inability to effectively extract the key features of the target, increasing the difficulty of target tracking.

[0004] To solve the above technical problems, according to one aspect of the present invention, more specifically, a target tracking system based on video perception includes: a visibility acquisition module, an illumination acquisition module, an incoming light acquisition module, a noise value acquisition module and a luminous flux acquisition module;

[0005] Visibility acquisition module: used to collect visibility information data of the environment where the video shooting device is located in real time;

[0006] Illumination acquisition module: used to collect the illumination information data of the environment where the video shooting device is located in real time;

[0007] Light input amount acquisition module: used to collect light input amount information data of video shooting equipment in real time;

[0008] Noise value acquisition module: used to collect noise value information data of video shooting pictures in real time;

[0009] Luminous flux collection module: used to collect the sun's luminous flux numerical information data in real time.

[0010] Furthermore, the data processing unit includes: a data acquisition module, an analysis and judgment module, a report generation module and a result forwarding module;

[0011] Data acquisition module: used for real-time acquisition of information data stored in the data storage unit;

[0012] Analysis and judgment module: used to analyze and judge the information data obtained by the data acquisition module, so as to obtain the results of the analysis and judgment;

[0013] Report generation module: used to generate a video perception tracking report based on the analysis and judgment results of the analysis and judgment module;

[0014] Result forwarding module: used to forward the results of analysis and judgment by the analysis and judgment module and the video perception tracking report generated by the report generation module to the remote monitoring unit.

[0015] Furthermore, the remote monitoring unit includes: a data receiving module, a data display module and an abnormal alarm module;

[0016] Data receiving module: used for receiving the information data stored in the data storage unit and the analysis result information of the data processing unit in real time;

[0017] Data display module: used to display the information data received by the data receiving module on the background terminal display screen;

[0018] Abnormal alarm module: used to send an alarm prompt to the background terminal when the result obtained by the analysis and judgment module is abnormal.

[0019] Furthermore, the UPS power supply unit is used to provide an uninterruptible power supply for the entire video perception target tracking system to ensure that the system can still operate normally when the city power is cut off.

[0020] Furthermore, the analysis and judgment module can obtain the visibility and illumination information data of the environment in which the video shooting device is located from the data acquisition module, and obtain the adjustment index of the shooting environment through the analysis of the above acquired data:

[0021]

[0022] Among them, I en is the adjustment index of the shooting environment, t is the total time of data collection, S i is the visibility of the environment where the video shooting device is located at the i-th second, S max S is the maximum visibility value of the environment where the video shooting device is located within time t, min S is the minimum visibility value of the environment where the video shooting device is located within time t, e is the preset standard visibility value, L i is the illumination of the environment where the video shooting device is located at the i-th second, L max L is the maximum illuminance value of the environment where the video shooting device is located within time t. min It is the minimum illumination value of the environment where the video shooting device is located within the time t.

[0023] Furthermore, the analysis and judgment module can obtain the light input amount of the video shooting device and the noise value information data of the video shooting picture from the data acquisition module, and obtain the video shooting index through the above acquired data analysis, if:

[0024]

[0025] This means that the image captured by the video capture device is clear, where I ph is the shooting index of the video, t is the total time of data collection, F i is the amount of light entering the video capture device at the i-th second, F max F is the maximum amount of light entering the video capture device within time t, min is the minimum amount of light entering the video capture device within time t, Q is the total number of pixels in the video capture image, and noise i is the noise value of the i-th pixel, noise avg is the average noise value of the video pictures, and δ is the preset threshold parameter.

[0026] Furthermore, when correcting the image, the image correction unit can obtain the solar luminous flux numerical data from the data receiving module, and obtain the image correction coefficient by analyzing the obtained data:

[0027]

[0028] Furthermore, after obtaining the correction coefficient of the image, the grayscale value of each pixel in the image is corrected using the correction coefficient of the image, and the corrected grayscale value of each image pixel is obtained:

[0029]

[0030] in, is the image correction coefficient, I ph is the video shooting index, I en is the adjustment index of the shooting environment, β is the influence coefficient of the preset video shooting index, α is the influence coefficient of the preset shooting environment adjustment index, and α+β=1, t is the total time of data collection, LM i is the luminous flux of the sun at the i-th second, LM max is the maximum luminous flux of the sun within time t, LM min is the minimum luminous flux value of the sun within time t, new i After image correction, the gray value of the image at the i-th pixel is enhanced, past i It is the gray value of the image enhanced at the i-th pixel before image correction.

[0031] The beneficial effects of the target tracking system based on video perception of the present invention are as follows: by integrating visibility, illumination, light intake, noise value and luminous flux multi-dimensional information acquisition modules, the system can evaluate the shooting environment in real time, automatically adjust image parameters, effectively reduce noise interference, and enhance image clarity, thereby enabling the system to accurately identify target features, and achieve fast and accurate target tracking even in complex and changeable low-light environments. In addition, the provision of a UPS power supply unit ensures the continuous operation of the system in the event of a power outage, further enhancing the system's safety monitoring capabilities. Finally, when an abnormal situation occurs, an alarm can be sent to the background terminal, allowing staff to promptly understand the system's operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0033] Figure 1 This is a schematic diagram of the system principle. DETAILED DESCRIPTION

[0034] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0035] According to one aspect of the present invention, Figure 1 As shown, a target tracking system based on video perception is provided. First, the monitoring and shooting unit is used to shoot real-time images of the area that needs video security monitoring. Then, the visibility, illumination, light input of the video shooting device, noise value of the video shooting picture and the luminous flux information data of the sun are respectively collected in real time through the visibility collection module, illumination collection module, light input collection module, noise value collection module and luminous flux collection module.

[0036] Then, the collected data is transmitted to the data storage unit in real time through the data transmission unit, and then the information data is obtained from the data storage unit through the data acquisition module in the data analysis unit. Further, the obtained information data is processed and analyzed through the analysis and judgment module.

[0037] Afterwards, the data receiving module in the remote monitoring unit can receive the information data stored in the data storage unit and the analysis results of the data processing unit in real time, and display the received information data on the background terminal display screen through the data display module. At the same time, when the results analyzed and judged by the analysis and judgment module are abnormal, it means that the image taken by the video shooting device is blurred, which will trigger the abnormal alarm module to alarm the background terminal, and correct the blurred image through the image correction unit. Furthermore, the feature extraction unit extracts features from the corrected video image, and then the matching tracking unit compares the features extracted by the feature extraction unit with the target feature database, and confirms and tracks the target whose feature information completely matches.

[0038] The analysis and judgment module can obtain the visibility and illumination information data of the environment where the video shooting device is located from the data acquisition module, and obtain the adjustment index of the shooting environment through the analysis of the above acquired data:

[0039]

[0040] Adjustment index of shooting environment I en The smaller the value of is, the worse the lighting conditions of the video shooting device are, and the more blurred the image is. en is the adjustment index of the shooting environment, t is the total time of data collection, S i is the visibility of the environment where the video shooting device is located at the i-th second, S max S is the maximum visibility value of the environment where the video shooting device is located within time t, min S is the minimum visibility value of the environment where the video shooting device is located within time t, e is the preset standard visibility value, which is 25 kilometers, L i is the illumination of the environment where the video shooting device is located at the i-th second, L max L is the maximum illuminance value of the environment where the video shooting device is located within time t. min It is the minimum illumination value of the environment where the video shooting device is located within the time t.

[0041] The analysis and judgment module can obtain the light input amount of the video shooting device and the noise value information data of the video shooting picture from the data acquisition module, and obtain the video shooting index through the above acquired data analysis, if:

[0042]

[0043] This means that the images taken by the video camera are clear. This means that the image captured by the video capture device is blurred, which will trigger the abnormal alarm module to alarm the background terminal, and correct the blurred image through the image correction unit, where I ph is the shooting index of the video, t is the total time of data collection, F i is the amount of light entering the video capture device at the i-th second, F max F is the maximum amount of light entering the video capture device within time t, min is the minimum amount of light entering the video capture device within time t, Q is the total number of pixels in the video capture image, and noise i is the noise value of the i-th pixel, noise avg is the average noise value of the video pictures, and δ is the preset threshold parameter.

[0044] When correcting the image, the image correction unit can obtain the solar luminous flux numerical data from the data receiving module, and obtain the image correction coefficient by analyzing the above obtained data:

[0045]

[0046] Furthermore, after obtaining the correction coefficient of the image, the grayscale value of each pixel in the image is corrected using the correction coefficient of the image, and the corrected grayscale value of each image pixel is obtained, thereby making the image captured by the video clearer:

[0047]

[0048] in, is the image correction coefficient, I ph is the video shooting index, I en is the adjustment index of the shooting environment, β is the influence coefficient of the preset video shooting index, α is the influence coefficient of the preset shooting environment adjustment index, and α+β=1, where α=0.15, β=0.85, t is the total time for data collection, LM i is the luminous flux of the sun at the i-th second, LM max is the maximum luminous flux of the sun within time t, LM min is the minimum luminous flux value of the sun within time t, new i After image correction, the gray value of the image at the i-th pixel is enhanced, past i It is the gray value of the image enhanced at the i-th pixel before image correction.

[0049] The above-mentioned embodiment only expresses one implementation mode of the present invention, and its description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. A target tracking system based on video perception, characterized in that: include: Monitoring shooting unit, data acquisition unit, data transmission unit, data storage unit, data processing unit, remote monitoring unit, image correction unit, feature extraction unit, matching pursuit unit and UPS power supply unit; Monitoring and shooting unit: used for video monitoring and shooting through video shooting equipment; Data acquisition unit: used for real-time acquisition of data generated during the process of video perception and tracking of the target; Data transmission unit: used for real-time transmission of information data collected by the data collection unit; Data storage unit: used to store the information data transmitted in real time by the data transmission unit; Data processing unit: used to process and analyze the information data stored in the data storage unit, and obtain the processing and analysis results, and generate a video perception tracking report according to the processing and analysis results, and forward the obtained processing and analysis results to the remote monitoring unit; Remote monitoring unit: used to display the information data stored in the data storage unit and the analysis results of the data processing unit in real time on the background terminal. At the same time, when the analysis results obtained by the data processing unit are abnormal, an alarm is issued to the background terminal; Image correction unit: used to correct the video image when the result obtained by the data processing unit analysis is an abnormal result; Feature extraction unit: used for extracting features from the corrected video image; Matching tracking unit: used to confirm and track targets whose feature information completely matches by comparing the features extracted by the feature extraction unit with the target feature database.

2. The target tracking system based on video perception according to claim 1, characterized in that: The data acquisition unit includes: a visibility acquisition module, an illumination acquisition module, an incoming light acquisition module, a noise value acquisition module and a luminous flux acquisition module; Visibility acquisition module: used to collect visibility information data of the environment where the video shooting device is located in real time; Illumination acquisition module: used to collect the illumination information data of the environment where the video shooting device is located in real time; Light input amount acquisition module: used to collect light input amount information data of video shooting equipment in real time; Noise value acquisition module: used to collect noise value information data of video shooting pictures in real time; Luminous flux collection module: used to collect the sun's luminous flux numerical information data in real time.

3. The target tracking system based on video perception according to claim 2, characterized in that: The data processing unit includes: a data acquisition module, an analysis and judgment module, a report generation module and a result forwarding module; Data acquisition module: used for real-time acquisition of information data stored in the data storage unit; Analysis and judgment module: used to analyze and judge the information data obtained by the data acquisition module, so as to obtain the results of the analysis and judgment; Report generation module: used to generate a video perception tracking report based on the analysis and judgment results of the analysis and judgment module; Result forwarding module: used to forward the results of analysis and judgment by the analysis and judgment module and the video perception tracking report generated by the report generation module to the remote monitoring unit.

4. The target tracking system based on video perception according to claim 3, characterized in that: The remote monitoring unit includes: a data receiving module, a data display module and an abnormal alarm module; Data receiving module: used for receiving the information data stored in the data storage unit and the analysis result information of the data processing unit in real time; Data display module: used to display the information data received by the data receiving module on the background terminal display screen; Abnormal alarm module: used to send an alarm prompt to the background terminal when the result obtained by the analysis and judgment module is abnormal.

5. The target tracking system based on video perception according to claim 4, characterized in that: The UPS power supply unit is used to provide an uninterruptible power supply for the entire video perception target tracking system to ensure that the system can still operate normally when the city power is cut off.

6. The target tracking system based on video perception according to claim 5, characterized in that: The analysis and judgment module can obtain the visibility and illumination information data of the environment where the video shooting device is located from the data acquisition module, and obtain the adjustment index of the shooting environment through the analysis of the above acquired data: Among them, I en is the adjustment index of the shooting environment, t is the total time of data collection, S i is the visibility of the environment where the video shooting device is located at the i-th second, S max S is the maximum visibility value of the environment where the video shooting device is located within time t, min S is the minimum visibility value of the environment where the video shooting device is located within time t, e is the preset standard visibility value, L i is the illumination of the environment where the video shooting device is located at the i-th second, L max L is the maximum illuminance value of the environment where the video shooting device is located within time t. min It is the minimum illumination value of the environment where the video shooting device is located within the time t.

7. The target tracking system based on video perception according to claim 6, characterized in that: The analysis and judgment module can obtain the light input amount of the video shooting device and the noise value information data of the video shooting picture from the data acquisition module, and obtain the video shooting index through the above acquired data analysis, if: This means that the image captured by the video capture device is clear, where I ph is the shooting index of the video, t is the total time of data collection, F i is the amount of light entering the video capture device at the i-th second, F max F is the maximum amount of light entering the video capture device within time t, min is the minimum amount of light entering the video capture device within time t, Q is the total number of pixels in the video capture image, and noise i is the noise value of the i-th pixel, noise avg is the average noise value of the video pictures, and δ is the preset threshold parameter.

8. The target tracking system based on video perception according to claim 7, characterized in that: When correcting the image, the image correction unit can obtain the solar luminous flux numerical data from the data receiving module, and obtain the image correction coefficient by analyzing the obtained data: Furthermore, after obtaining the correction coefficient of the image, the grayscale value of each pixel in the image is corrected using the correction coefficient of the image, and the corrected grayscale value of each image pixel is obtained: in, is the image correction coefficient, I ph is the video shooting index, I en is the adjustment index of the shooting environment, β is the influence coefficient of the preset video shooting index, α is the influence coefficient of the preset shooting environment adjustment index, and α+β=1, t is the total time of data collection, LM i is the luminous flux of the sun at the i-th second, LM max is the maximum luminous flux of the sun within time t, LM min is the minimum luminous flux value of the sun within time t, new i After image correction, the gray value of the image at the i-th pixel is enhanced, past i It is the gray value of the image enhanced at the i-th pixel before image correction.

Images