CN116188811A

CN116188811A - Tracking target loss detection method and system based on color histogram distance

Info

Publication number: CN116188811A
Application number: CN202211624981.8A
Authority: CN
Inventors: 姜柯; 张聪; 钟啸; 李爱华; 蔡艳平; 苏延召; 韩德帅; 王涛; 冯国彦
Original assignee: Rocket Force University of Engineering of PLA
Current assignee: Rocket Force University of Engineering of PLA
Priority date: 2022-12-16
Filing date: 2022-12-16
Publication date: 2023-05-30

Abstract

The invention discloses a tracking target loss detection method based on a color histogram distance, which comprises the following steps: acquiring an image to be tracked, wherein the image to be tracked comprises a target area and a background area; determining a tracking frame scaling ratio based on a target area of the tracking image to adjust tracking frame parameters to obtain a target central area, so that the ratio of the number of pixels of a target object in the target central area to the number of pixels of a background meets a preset condition; generating a color histogram according to the target central region; storing the characteristic values of the color histogram according to time sequence based on the color histogram so as to detect target loss according to the characteristic values; the tracking frame is rectangular, and the parameters of the tracking frame comprise side length and rotation angle. The invention can accurately detect the occurrence of abnormal characteristic values and improve the long-term working reliability and the intelligent level of a target tracking algorithm and an application system.

Description

Tracking target loss detection method and system based on color histogram distance

Technical Field

The invention belongs to the field of target tracking, and particularly relates to a tracking target loss detection method and system based on a color histogram distance.

Background

Along with the rapid development of computer vision technology, the application of the computer vision technology in the military and civil fields is increasingly popular, and the target tracking technology is taken as an important branch of the computer vision application and has wide application in the fields of battlefield target reconnaissance, target attack locking, monitoring scene specific target tracking and the like.

In the prior art, in the target tracking application system, when the hit tracking target disappears, deviates from the video field of view, is blocked by an obstacle, and the like, the tracking system and the algorithm can search in the adjacent range of the last target occurrence and incorrectly locate the object most similar to the target. Therefore, in general, the target tracking system needs to monitor and the operator continuously observe and monitor the scene with naked eyes to manually judge the target loss.

However, the prior art has the following drawbacks: 1. the continuous analysis and application of the tracking result confidence mechanism or the result confidence data cannot detect and utilize abnormal values appearing in the opposite confidence data, and a confidence characteristic model of the target from the whole period of tracking initiation, tracking process and tracking loss is not established; 2. when the target is partially blocked, temporarily disappears and the like, the traditional target tracking algorithm can consider that tracking is failed so as to stop tracking, and the usability of the system is poor; 3. the traditional target tracking method only depends on the characteristics used in the tracking algorithm to search and track, and has poor effect.

Disclosure of Invention

In order to solve the problems in the prior art, the invention provides a tracking target loss detection method and a tracking target loss detection system based on a color histogram distance. The technical problems to be solved by the invention are realized by the following technical scheme:

a tracking target loss detection method based on a color histogram distance comprises the following steps:

acquiring an image to be tracked, wherein the image to be tracked comprises a target area and a background area;

determining a tracking frame scaling ratio based on a target area of the tracking image to adjust tracking frame parameters to obtain a target central area, so that the ratio of the number of pixels of a target object in the target central area to the number of pixels of a background meets a preset condition;

generating a color histogram according to the target central region;

storing the characteristic values of the color histogram according to time sequence based on the color histogram so as to detect target loss according to the characteristic values; the tracking frame is rectangular, and the parameters of the tracking frame comprise side length and rotation angle.

In one specific embodiment, the target loss detection according to the characteristic value includes:

setting a first time sliding window, a second time sliding window and a third time sliding window;

taking the average value of the characteristic values in each time sliding window as a median Q2 of the box graph, and calculating a lower quartile Q1, an upper quartile Q3 and a quartile range IQR of the box graph;

calculating the upper sliding window limit number and the lower sliding window limit number according to the lower quartile Q1, the upper quartile Q3 and the quartile range IQR so as to determine a threshold range according to the upper sliding window limit number and the lower sliding window limit number;

and determining a target state according to the first time sliding window, the second time sliding window, the third time sliding window and the abnormal threshold value, wherein the target state comprises a normal state, a local shielding state, a complete shielding state and a lost state.

In one embodiment, determining the target state based on the first time sliding window, the second time sliding window, the third time sliding window, and the anomaly threshold value includes:

when the characteristic value in the first time sliding window is detected to be beyond the threshold range and the characteristic values in the second time sliding window and the third time sliding window are not beyond the threshold range, determining that the target state is a local shielding state;

when the characteristic values in the first time sliding window and the second time sliding window are detected to exceed the threshold range and the characteristic value in the third time sliding window is detected to not exceed the threshold range, determining that the target state is a complete shielding state;

when the characteristic values in the first time sliding window, the second time sliding window and the third time sliding window are detected to be beyond the threshold range, determining that the target state is a lost state;

and when the characteristic values in the first time sliding window, the second time sliding window and the third time sliding window are detected not to exceed the threshold range, determining that the target state is a normal state.

In one embodiment, the sliding window upper limit number = upper quartile q3+1.5 x quartile range IQR;

the sliding window lower limit number=lower quartile Q1-1.5 x quartile range IQR.

In one embodiment, the color histogram includes a YUV or RGB color space.

The invention also provides a tracking target loss detection system based on the color histogram distance, which comprises:

the image acquisition module is used for acquiring an image to be tracked, wherein the image to be tracked comprises a target area and a background area;

the central region generation module is used for determining the scaling of the tracking frame based on the target region of the tracking image so as to adjust the tracking frame parameters to obtain a target central region, so that the ratio of the number of pixels of a target object in the target central region to the number of pixels of the background meets the preset condition;

a color histogram generation module for generating a color histogram according to the target center region;

the target detection module is used for storing the characteristic values of the color histogram according to time sequence based on the color histogram so as to detect target loss according to the characteristic values; the tracking frame is rectangular, and the parameters of the tracking frame comprise side length and rotation angle.

In one embodiment, the object detection module includes:

a sliding window setting unit for setting a first time sliding window, a second time sliding window and a third time sliding window;

the calculating unit module is used for taking the average value of the characteristic values in each time sliding window as the median Q2 of the box graph and calculating the lower quartile Q1, the upper quartile Q3 and the quartile range IQR of the box graph;

a threshold range determining unit, configured to calculate an upper sliding window limit number and a lower sliding window limit number according to the lower quartile Q1, the upper quartile Q3, and the quartile range IQR, so as to determine a threshold range according to the upper sliding window limit number and the lower sliding window limit number;

and the state detection unit is used for determining a target state according to the first time sliding window, the second time sliding window, the third time sliding window and the abnormal threshold value, wherein the target state comprises a normal state, a local shielding state, a complete shielding state and a lost state.

In one embodiment, the state detection unit is specifically configured to:

The invention also provides an electronic device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing the tracking target loss detection method based on the color histogram distance when executing the program stored in the memory.

The invention has the beneficial effects that:

1. according to the tracking target loss detection method based on the color histogram distance, the color histogram characteristic value is built by selecting the target center local range, the characteristic value time sequence is built, and the abnormal value data analysis method is combined, so that the occurrence of the abnormal characteristic value can be accurately detected, and the long-term working reliability and the intelligent level of a target tracking algorithm and an application system can be improved;

2. the tracking target loss detection method based on the color histogram distance can dynamically adjust the parameter according to specific target characteristics, and the components of the target object in the reduced rectangular frame are far greater than background pixel components, so that the accuracy of the subsequent color histogram characteristic description is ensured;

3. the tracking target loss detection method based on the color histogram distance adopts a multi-box graph detection method, and adopts three time sliding windows with different lengths, so that the requirements of different working scenes can be met, the practicability is higher, and the stability of a target tracking algorithm can be improved.

The present invention will be described in further detail with reference to the accompanying drawings and examples.

Drawings

Fig. 1 is a schematic flow chart of a tracking target loss detection method based on a color histogram distance according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a state detection and judgment logic provided in an embodiment of the present invention;

FIG. 3 is a block diagram of a tracking target loss detection system based on a color histogram distance according to an embodiment of the present invention;

fig. 4 is a schematic diagram of an electronic device provided by the present invention.

Detailed Description

The present invention will be described in further detail with reference to specific examples, but embodiments of the present invention are not limited thereto.

Example 1

Referring to fig. 1, fig. 1 is a schematic flow chart of a tracking target loss detection method based on a color histogram distance according to an embodiment of the present invention, including:

s1, acquiring an image to be tracked, wherein the image to be tracked comprises a target area and a background area; the image to be tracked of the present embodiment generally refers to target video data or image data that needs to be tracked. When the target tracking system works, a target frame containing a tracked target object and a scene background where part of the target is located is usually generated, the target frame is usually rectangular, and the aspect ratio of the rectangular frame is consistent with the outline size of the target. The target area is the area inside the rectangular frame, and generally includes a complete target pixel, and the area outside the rectangular frame becomes the background area, and the Beijing area does not include the target pixel.

S2, determining a tracking frame scaling ratio based on a target area of the tracking image to adjust tracking frame parameters to obtain a target central area, so that the ratio of the number of pixels of a target object in the target central area to the number of pixels of a background meets a preset condition;

it should be noted that rectangular boxes can be classified into two types, rotatable and non-rotatable, according to the difference of algorithms. Under the condition of stable tracking, the tracking system locks the target object at the center of the rectangular frame, and a large number of background pixels exist in the edge area of the rectangular tracking frame due to irregular appearance and inconsistent rotation angle of the target and the length-width direction of the video image, which causes great trouble to tracking. In this embodiment, by setting a track frame scaling parameter λ (e.g., 0.5< λ < 0.9), the tracking system can dynamically adjust the parameter according to specific target features, and the component of the target object in the reduced rectangular frame will be much larger than the background pixel component (e.g., the preset condition of setting the scale to 1:0.05-1:0.01), so as to ensure the accuracy of the subsequent color histogram feature description.

The tracking target loss detection method based on the color histogram distance can dynamically adjust the parameter according to specific target characteristics, and the components of the target object in the reduced rectangular frame are far greater than background pixel components, so that the accuracy of the subsequent color histogram characteristic description is ensured.

S3, generating a color histogram according to the target central area;

the color histogram of the embodiment can adopt two color spaces of YUV and RGB, and can be specifically selected according to the image data format of the video source; for YUV format, it is preferable to increase the weight of the Y channel when the image quality is poor, with emphasis on the luminance channel.

S4, storing characteristic values of the color histogram according to time sequence based on the color histogram so as to detect target loss according to the characteristic values; the tracking frame is rectangular, and the parameters of the tracking frame comprise side length and rotation angle.

s41, setting a first time sliding window, a second time sliding window and a third time sliding window;

s42, calculating the upper sliding window limit number and the lower sliding window limit number according to the lower quartile Q1, the upper quartile Q3 and the quartile range IQR so as to determine a threshold range according to the upper sliding window limit number and the lower sliding window limit number;

s43, determining a target state according to the first time sliding window, the second time sliding window, the third time sliding window and the abnormal threshold value, wherein the target state comprises a normal state, a partial shielding state, a complete shielding state and a lost state.

In one embodiment, step S43 specifically includes:

In the above-mentioned determination, referring specifically to fig. 2, the determination logic is configured to determine, in order, the characteristic values of the first time sliding window, the second time sliding window and the third time sliding window, that is, if the first time sliding window is not abnormal, the second time sliding window and the third time sliding window may be considered to be normal, and the determination is directly determined to be normal, if the first time sliding window is abnormal, it is necessary to further determine whether the second time sliding window is abnormal, if the second time sliding window is not abnormal, it is considered that the third time sliding window is normal, and it is determined to be a local shielding state, if the second time sliding window is abnormal, it is necessary to continuously determine whether the third time sliding window is the same, that the characteristic values in the first time sliding window, the second time sliding window and the third time sliding window are all out of the threshold range, and determine that the target state is lost, otherwise, it is considered that the target is completely shielded, and the target is determined to be a complete shielding state. It should be noted that the time of the first time sliding window, the second time sliding window, and the third time sliding window may be set according to circumstances. The tracking target loss detection method based on the color histogram distance adopts a multi-box graph detection method, and adopts three time sliding windows with different lengths, so that the requirements of different working scenes can be met, the practicability is higher, and the stability of a target tracking algorithm can be improved.

The tracking target loss detection method based on the color histogram distance of the invention constructs the characteristic value of the color histogram by selecting the local range of the center of the target, establishes the characteristic value time sequence and combines with the abnormal value data analysis method, thereby being capable of accurately detecting the occurrence of the abnormal characteristic value and improving the long-term working reliability and the intelligent level of a target tracking algorithm and an application system

Referring to fig. 3, the present invention also provides a tracking target loss detection system based on a color histogram distance, including:

an image acquisition module 31, configured to acquire an image to be tracked, where the image to be tracked includes a target area and a background area;

a central region generating module 32, configured to determine a tracking frame scaling based on the target region of the tracking image, so as to adjust tracking frame parameters to obtain a target central region, so that a ratio of the number of pixels of the target object in the target central region to the number of pixels of the background meets a preset condition;

a color histogram generation module 33 for generating a color histogram from the target center region;

a target detection module 34, configured to store the characteristic values of the color histogram in time sequence based on the color histogram, so as to perform target loss detection according to the characteristic values; the tracking frame is rectangular, and the parameters of the tracking frame comprise side length and rotation angle.

In one embodiment, the object detection module includes:

In one embodiment, the state detection unit is specifically configured to:

The embodiment of the invention also provides an electronic device, as shown in fig. 4, which comprises a processor 41, a communication interface 42, a memory 43 and a communication bus 44, wherein the processor 41, the communication interface 42 and the memory 43 complete communication with each other through the communication bus 44,

a memory 43 for storing a computer program;

the processor 41 is configured to execute the program stored in the memory 43, and implement the following steps:

s1, acquiring an image to be tracked;

s3, generating a color histogram according to the target central area;

and S4, storing the characteristic value of the color histogram according to time sequence based on the color histogram so as to detect target loss according to the characteristic value.

The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the electronic device and other devices.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

The method provided by the embodiment of the invention can be applied to electronic equipment. Specifically, the electronic device may be: desktop computers, portable computers, intelligent mobile terminals, servers, etc. Any electronic device capable of implementing the present invention is not limited herein, and falls within the scope of the present invention.

For the apparatus/electronic device/storage medium embodiments, the description is relatively simple as it is substantially similar to the method embodiments, as relevant see the section description of the method embodiments.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Further, one skilled in the art can engage and combine the different embodiments or examples described in this specification.

Although the present application has been described herein in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the figures, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system (apparatus), or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects all generally referred to herein as a "module" or "system. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. A computer program may be stored/distributed on a suitable medium supplied together with or as part of other hardware, but may also take other forms, such as via the Internet or other wired or wireless telecommunication systems.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, systems (devices) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.

Claims

1. The method for detecting the loss of the tracking target based on the distance of the color histogram is characterized by comprising the following steps:

generating a color histogram according to the target central region;

2. The color histogram distance-based tracking target loss detection method according to claim 1, wherein target loss detection is performed according to the feature value, comprising:

3. The color histogram distance-based tracking target loss detection method according to claim 1, wherein determining a target state from the first time sliding window, the second time sliding window, the third time sliding window, and the abnormality threshold value includes:

4. The method for detecting the loss of tracking target based on the distance of the color histogram according to claim 2, wherein,

the sliding window upper limit number = upper quartile q3+1.5 x quartile range IQR;

5. The tracking target loss detection method based on a color histogram distance according to claim 1, wherein the color histogram includes a YUV or RGB color space.

6. A color histogram distance-based tracking target loss detection system, comprising:

7. The color histogram distance-based tracking target loss detection system of claim 6, wherein said target detection module comprises:

8. The tracking target loss detection system based on a color histogram distance according to claim 1, wherein the state detection unit is specifically configured to:

9. The color histogram distance-based tracking target loss detection system of claim 7,

10. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the method of any of claims 1-5 when executing a program stored on a memory.