CN114565638A - Multi-target tracking method and system based on tracking chain - Google Patents
Multi-target tracking method and system based on tracking chain Download PDFInfo
- Publication number
- CN114565638A CN114565638A CN202210086779.8A CN202210086779A CN114565638A CN 114565638 A CN114565638 A CN 114565638A CN 202210086779 A CN202210086779 A CN 202210086779A CN 114565638 A CN114565638 A CN 114565638A
- Authority
- CN
- China
- Prior art keywords
- tracking
- tracking chain
- chain
- calculating
- target
- 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; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a multi-target tracking method and a system based on a tracking chain; wherein the method comprises the following steps: identifying a first target object in the monitored image according to a preset interval, and generating a first tracking chain according to an identification result; modifying the state of the first tracking chain when the first target object fails to be identified; generating a second tracking chain for the newly identified second target object; calculating the similarity of the first tracking chain and the second tracking chain, and connecting the first tracking chain and the second tracking chain in series according to the similarity; the method can simply and efficiently realize the synchronous tracking of the multi-target object, cannot cause tracking failure due to shielding, and has higher reliability.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a multi-target tracking method and system based on a tracking chain, electronic equipment and a computer storage medium.
Background
In Multiple Object Tracking (Multiple Object Tracking), in brief, the main task is to give an image sequence, and after identifying an Object in the image, the same Object in different frames is represented by a Trace id, so that the task of target Tracking is completed. Of course, these objects may be arbitrary, such as pedestrians, vehicles, various animals, etc. Multi-target tracking is a hotspot of computer vision technology and is also a difficulty in practical application. In 2017, the SORT algorithm based on deep learning target detection has the advantages that the tracking effect and the speed are both considered, good results are obtained, and tracking failure is easily caused by shielding. Later, the deepSORT algorithm introducing appearance characteristic information appeared, which is directly reduced by nearly half compared with the SORT interchange index, but the hardware specification became higher.
Therefore, the multi-target tracking technology in the prior art has a plurality of technical problems, and actual requirements are difficult to meet.
Disclosure of Invention
In order to solve at least the technical problems in the background art, the invention provides a multi-target tracking method, a multi-target tracking system, an electronic device and a computer storage medium based on a tracking chain.
The invention provides a multi-target tracking method based on a tracking chain, which comprises the following steps:
identifying a first target object in the monitored image according to a preset interval, and generating a first tracking chain according to an identification result;
modifying the state of the first tracking chain when the first target object fails to be identified;
generating a second tracking chain for the newly identified second target object;
and calculating the similarity of the first tracking chain and the second tracking chain, and connecting the first tracking chain and the second tracking chain in series according to the similarity.
Optionally, before the identifying the plurality of target objects in the monitored image according to the preset interval, the method further includes:
acquiring monitoring images, and generating a first number of third tracking chains according to the monitoring images;
generating a first tracking chain according to the recognition result, including:
and assigning the third tracking chain to the identified target object according to the identification sequence.
Optionally, the generating a first number of third tracking chains according to the monitoring image includes:
identifying third target objects in the monitoring image in a preset period, wherein the identification result comprises the number and the speed of the third target objects;
determining a first number according to the number and the speed, and generating the third tracking chain according to the first number.
Optionally, the first tracking chain and the second tracking chain include speed data and position data;
then said calculating a similarity of said first tracking chain and said second tracking chain comprises:
calculating a predicted position of the first tracking chain at each first time instant from the velocity data and the position data;
calculating a residual error between the predicted position and position data at a second moment in the second tracking chain, and a standard deviation under a Kalman filter;
calculating similarity according to the residual error and the standard deviation by adopting a probability density function of Gaussian distribution;
and the distance between the first moment and the second moment is smaller than a preset threshold value.
Optionally, the status includes unconscious, coma;
modifying the state of the first tracking chain when the first target object identification fails, including:
if the first target object fails to be identified, modifying the state of the first tracking chain into a coma, adding 1 to the coma number n1, and recording the corresponding time;
and if the first target object identification fails, adding 1 to the unconsciousness number n2, and recording the corresponding time.
Optionally, the state further comprises immature, mature;
before the calculating the similarity of the first tracking chain and the second tracking chain, further performing a screening process on the first tracking chain and the second tracking chain, including:
if n1/len is smaller than a first threshold value, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
And/or calculating the number n2 of times that the first tracking chain and the second tracking chain are in non-coma at the same time, and if n2/len is larger than a second threshold value, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
Calculating the times n3 that the first tracking chain and the second tracking chain are close to each other at the same time, and if n3/len is smaller than a third threshold, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
Calculating an included angle alpha between the first tracking chain and the second tracking chain, and if alpha is larger than a fourth threshold, giving up calculating the similarity of the first tracking chain and the second tracking chain;
wherein, said len represents the maximum length of the tracking chain.
Optionally, the calculating an included angle α between the first tracking chain and the second tracking chain includes:
calculating the pixel speed U of the first tracking chain, and calculating a vector V of the chain tail of the first tracking chain and the chain tail of the second tracking chain;
the angle is calculated using the formula cos (α) ═ U × V/(| U | V |).
The invention provides a multi-target tracking system based on a tracking chain, which comprises a processing module, a storage module and an acquisition module, wherein the processing module is respectively connected with the storage module and the acquisition module; wherein the content of the first and second substances,
the storage module is used for storing executable computer program codes;
the acquisition module is used for acquiring the monitoring image and transmitting the monitoring image to the processing module;
the processing module is configured to execute the method according to any one of the preceding claims by calling the executable computer program code in the storage module.
A third aspect of the present invention provides an electronic device comprising:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to perform the method of any of the preceding claims.
A fourth aspect of the invention provides a computer storage medium having stored thereon a computer program which, when executed by a processor, performs a method as set forth in any one of the preceding claims.
According to the scheme, a first target object in a monitored image is identified according to a preset interval, and a first tracking chain is generated according to an identification result; modifying the state of the first tracking chain when the first target object fails to be identified; generating a second tracking chain for the newly identified second target object; and calculating the similarity of the first tracking chain and the second tracking chain, and connecting the first tracking chain and the second tracking chain in series according to the similarity. The method can simply and efficiently realize the synchronous tracking of the multi-target object, cannot cause tracking failure due to shielding, and has higher reliability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of a multi-target tracking method based on a tracking chain according to an embodiment of the present invention;
FIG. 2 is a scene diagram of a multi-target tracking method based on a tracking chain according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a multi-target tracking system based on a tracking chain according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings or the orientation or positional relationship which the product of the present invention is usually placed in when used, the description is only for convenience of describing the present invention and simplifying the description, but the indication or suggestion that the system or the element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, cannot be understood as limiting the present invention.
The terms "first," "second," "third," and "fourth," etc. in the description and in the claims of the present invention are used for distinguishing between different objects and not for describing a particular order of the objects. For example, the first input, the second input, the third input, the fourth input, etc. are used to distinguish between different inputs, rather than to describe a particular order of inputs.
In the embodiments of the present invention, words such as "exemplary" or "for example" are used to mean serving as examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "e.g.," an embodiment of the present invention is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
In the description of the embodiments of the present invention, unless otherwise specified, "a plurality" means two or more, for example, a plurality of processing units means two or more processing units; plural elements means two or more elements, and the like.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart of a multi-target tracking method based on a tracking chain according to an embodiment of the present invention. As shown in fig. 1, a multi-target tracking method based on a tracking chain in an embodiment of the present invention includes the following steps:
identifying a first target object in the monitored image according to a preset interval, and generating a first tracking chain according to an identification result;
modifying the state of the first tracking chain when the first target object fails to be identified;
generating a second tracking chain for the newly identified second target object;
and calculating the similarity of the first tracking chain and the second tracking chain, and connecting the first tracking chain and the second tracking chain in series according to the similarity.
In the embodiment of the invention, referring to fig. 2, a plurality of first target objects may exist in a monitored image, the invention identifies the target objects in the monitored image according to a preset interval, establishes a first tracking chain for each first target object, meanwhile, in the tracking process, when the first target object fails to track (for example, is blocked), modifies the state of the first tracking chain, and when a new second target object is identified subsequently, generates a second tracking chain for the first target object, so that after the tracking period, the first tracking chain and the second tracking chain are collected and the similarity is calculated, and when the similarity satisfies the condition, the corresponding first tracking chain and the second tracking chain can be connected in series, thereby realizing the continuous tracking of multiple targets. The method can simply and efficiently realize the synchronous tracking of the multi-target object, cannot cause tracking failure due to shielding, and has higher reliability.
It should be noted that the solution of the present invention may be implemented on the field side or on the server side. The field terminal can be a smart phone, a tablet computer, a notebook computer, a palm computer, a Mobile Internet Device (MID), a wearable device (such as a smart watch, a smart bracelet, and the like), a vehicle-mounted computer in an automatic driving system, and the like; the server side can be an independent physical server, can also be a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN (content delivery network) and big data and artificial intelligence platforms. The site end and the server end can communicate through the base station, and the site end can send the collected monitoring images to the server for multi-target tracking processing, so that the equipment requirements of the site end can be simplified. And the base station may include various forms of base stations, such as: macro base stations, micro base stations (also referred to as small stations), relay stations, access points, etc. Specifically, The Access point may be an Access Point (AP) in a Wireless Local Area Network (WLAN), a Base Station (BTS) in a Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), a Base Station (Node B, NB) in a Wideband Code Division Multiple Access (WCDMA), an Evolved Node B (e NB, or e Node B) in LTE, or a relay Station or Access point, or a Base Station in a vehicle-mounted device, a wearable device, and a Next Generation Node B (The Next Generation B, G NB) in a future 5G Network or a PLMN in a future Evolved Public Land Mobile Network (PLMN), and The like.
Optionally, before the identifying the plurality of target objects in the monitored image according to the preset interval, the method further includes:
acquiring monitoring images, and generating a first number of third tracking chains according to the monitoring images;
generating a first tracking chain according to the recognition result, including:
and assigning the third tracking chain to the identified target object according to the identification sequence.
In the embodiment of the invention, under some multi-target object tracking scenes, the motion of the target objects is very rapid, the number of the target objects is large, and a corresponding tracking chain is generated after the target objects are identified, so that delay is caused, and even a situation that a tracking frame lags behind the target objects may occur. In view of this, the first number of third tracking chains are generated in advance for standby at a certain time, and the third tracking chains are blank tracking chains with a certain length, so that after the target object is identified, the blank third tracking chains can be directly allocated according to the identification sequence, and compared with real-time generation, the asynchronous between the tracking chains and the target object can be effectively reduced.
It should be noted that, in the present invention, the third tracking chain is blank, which means that the link point in the third tracking chain does not fill in the content of time, position data, and the like, and when performing the subsequent concatenation analysis, the still blank part is also removed, and only the link point filled with the relevant data is reserved.
Optionally, the generating a first number of third tracking chains according to the monitoring image includes:
identifying third target objects in the monitoring image in a preset period, wherein the identification result comprises the number and the speed of the third target objects;
determining a first number according to the number and the speed, and generating the third tracking chain according to the first number.
In the embodiment of the invention, before formally tracking the multiple target objects, the third target object is pre-identified in a short preset period, and the first number of the third tracking chains is determined according to the number and the speed of the identified third target objects. Wherein, the first number may be determined as follows: the number and speed of the third target objects is positively correlated to the first number. With such a configuration, according to the scheme of the invention, more third tracking chains can be generated in advance under the condition that the number of the third target objects is more and the speed is faster, so as to meet the subsequent requirements.
It should be noted that the preset period in the present invention may be a previous tracking period corresponding to the current tracking period, and may be all or part of the previous tracking period, that is, the data of the target object in the previous period may be used to predict the data of the target object in the next period, and a corresponding number of third tracking chains are generated in advance according to the predicted data.
Optionally, the first tracking chain and the second tracking chain include speed data and position data;
then said calculating a similarity of said first tracking chain and said second tracking chain comprises:
calculating a predicted position of the first tracking chain at each first time instant from the velocity data and the position data;
calculating a residual error between the predicted position and position data at a second moment in the second tracking chain, and a standard deviation under a Kalman filter;
calculating the similarity according to the residual error and the standard deviation by adopting a probability density function of Gaussian distribution;
and the distance between the first moment and the second moment is smaller than a preset threshold value.
In the embodiment of the present invention, when the target object is tracked, the position of the corresponding time is recorded, the predicted position of the first target object at the next time, that is, the next link point of the first tracking chain, can be predicted according to the data, the predicted position and the position data of the second tracking chain at the second time close to the first time are calculated, the residual error and the standard deviation are respectively obtained, and the probability density function of gaussian distribution is used to calculate the residual error and the standard deviation, so that the similarity between the first tracking chain and the second tracking chain can be obtained.
It should be noted that the predicted position of the first tracking chain at the next moment can be obtained by fitting or clustering the previous position and then analyzing the motion trend thereof, and the invention is not described herein again because it belongs to the mature prior art. And, the calculation method using probability density function of gaussian distribution also belongs to the mature prior art, and the present invention is not repeated again.
Optionally, the status includes unconscious, coma;
modifying the state of the first tracking chain when the first target object identification fails, including:
if the first target object fails to be identified, modifying the state of the first tracking chain into a coma, adding 1 to the coma number n1, and recording the corresponding time;
and if the first target object identification fails, adding 1 to the unconsciousness number n2, and recording the corresponding time.
In the embodiment of the invention, in the process of identifying and tracking the target object, the identification of the target object fails due to reasons such as shielding, and the like, at this time, the invention modifies the state of the first tracking chain into coma, adds 1 to the coma frequency and records the time, otherwise, keeps the original unconscious state, and also carries out frequency accumulation and records the time. Therefore, the state change condition of each tracking chain in the tracking process can be clearly known, and the subsequent tandem analysis is facilitated.
Optionally, the state further comprises immature, mature;
before the calculating the similarity of the first tracking chain and the second tracking chain, further performing a screening process on the first tracking chain and the second tracking chain, including:
if n1/len is smaller than a first threshold value, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
And/or calculating the number n2 of times that the first tracking chain and the second tracking chain are in non-coma at the same time, and if n2/len is larger than a second threshold value, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
Calculating the times n3 that the first tracking chain and the second tracking chain are close to each other at the same time, and if n3/len is smaller than a third threshold, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
Calculating an included angle alpha between the first tracking chain and the second tracking chain, and if alpha is larger than a fourth threshold, giving up calculating the similarity of the first tracking chain and the second tracking chain;
wherein, said len represents the maximum length of the tracking chain.
In the embodiment of the invention, in order to reduce the calculated amount of similarity, a link of primary screening on the first tracking chain and the second tracking chain is set, namely, the primary screening principle is utilized to realize rapid screening of the first tracking chain and the second tracking chain which obviously do not belong to the same target object, so that the multi-target object tracking efficiency is improved.
It should be noted that, since the size of the monitored area corresponding to the monitored image is fixed, and the preset interval of the tracking chain for the target object in the monitored image is also fixed, the length of the tracking chain has an upper limit, that is, len. The value of len can be determined according to the size of the monitored area and the preset interval, and for a specific determination method, the present invention is not described herein again.
Based on the determination manner of len value, the determination manner of the length of the aforementioned third tracking chain may be: determining a first length according to the size of the corresponding monitored area in the monitored image and the preset interval, and correcting the first length according to the number and the speed of the third target objects: a correction coefficient is inversely related to the number and the velocity of the third target objects, and the correction coefficient is less than or equal to 1. Meanwhile, when the number of vehicles in the monitored area is more and the vehicle speed is higher, the probability of shielding between the vehicles is higher, so that the blank third tracking chain generated in advance can not be used basically, more waste exists, and storage resources are occupied.
And for the position approach judgment of the first tracking chain and the second tracking chain at the same time, the following mode can be adopted:
when the state of the first tracking chain at a certain moment is coma, the position data of the target object at the non-coma moment is backtracked, the predicted position is obtained according to a Kalman filter, the overlapping degree iou1 of the predicted position and the position data of the second tracking chain at the corresponding moment is calculated, if the iou1 is smaller than a threshold value iou2, the first tracking chain and the second tracking chain are considered to have large deviation, and the target object is judged not to be close.
Optionally, the calculating an included angle α between the first tracking chain and the second tracking chain includes:
calculating the pixel speed U of the first tracking chain, and calculating a vector V of the chain tail of the first tracking chain and the chain tail of the second tracking chain;
the angle is calculated using the formula cos (α) ═ U × V/(| U | V |).
In the embodiment of the invention, the pixel speed U of the first tracking chain is calculated and calculated step by step, the vector V of the chain tail of the first tracking chain and the chain tail of the second tracking chain is calculated, and the included angle between the first tracking chain and the second tracking chain can be obtained by utilizing the included angle calculation formula. The vector V is derived from the chain end of the first tracking chain and the chain end of the second tracking chain, for example, the vector V is derived by directly connecting the chain ends of the first tracking chain and the second tracking chain.
Example two
Referring to fig. 3, fig. 3 is a schematic structural diagram of a multi-target tracking system based on a tracking chain according to an embodiment of the present invention. As shown in fig. 3, the multi-target tracking system (100) based on the tracking chain according to the embodiment of the present invention includes a processing module (101), a storage module (102), and an obtaining module (103), where the processing module (101) is connected to the storage module (102) and the obtaining module (103); wherein the content of the first and second substances,
the storage module (102) for storing executable computer program code;
the acquisition module (103) is used for acquiring a scene model and an AR label and transmitting the scene model and the AR label to the processing module (101);
the processing module (101) is configured to execute the method according to the first embodiment by calling the executable computer program code in the storage module (102).
For specific functions of the multi-target tracking system based on the tracking chain in this embodiment, reference is made to the first embodiment, and since the system in this embodiment adopts all technical solutions of the above embodiments, at least all beneficial effects brought by the technical solutions of the above embodiments are achieved, and details are not repeated here.
EXAMPLE III
Referring to fig. 4, fig. 4 is an electronic device according to an embodiment of the present invention, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute the method according to the first embodiment.
Example four
The embodiment of the invention also discloses a computer storage medium, wherein a computer program is stored on the storage medium, and the computer program executes the method in the first embodiment when being executed by a processor.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input system, and at least one output system.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing system, such that the program codes, when executed by the processor or controller, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display system (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing system (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of systems may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (10)
1. A multi-target tracking method based on a tracking chain is characterized by comprising the following steps:
identifying a first target object in the monitoring image according to a preset interval, and generating a first tracking chain according to an identification result;
modifying the state of the first tracking chain when the first target object fails to be identified;
generating a second tracking chain for the newly identified second target object;
and calculating the similarity of the first tracking chain and the second tracking chain, and connecting the first tracking chain and the second tracking chain in series according to the similarity.
2. The multi-target tracking method based on the tracking chain as claimed in claim 1, characterized in that: before the identifying of the target objects in the monitored image according to the preset interval, the method further comprises the following steps:
acquiring monitoring images, and generating a first number of third tracking chains according to the monitoring images;
generating a first tracking chain according to the recognition result, including:
and assigning the third tracking chain to the identified target object according to the identification sequence.
3. The multi-target tracking method based on the tracking chain as claimed in claim 2, characterized in that: the generating a first number of third tracking chains from the monitoring images includes:
identifying third target objects in the monitoring image in a preset period, wherein the identification result comprises the number and the speed of the third target objects;
determining a first number according to the number and the speed, and generating the third tracking chain according to the first number.
4. The multi-target tracking method based on the tracking chain as claimed in claim 1, characterized in that: the first tracking chain and the second tracking chain comprise speed data and position data;
then said calculating a similarity of said first tracking chain and said second tracking chain comprises:
calculating a predicted position of the first tracking chain at each first time instant from the velocity data and the position data;
calculating a residual error between the predicted position and position data at a second moment in the second tracking chain, and a standard deviation under a Kalman filter;
calculating similarity according to the residual error and the standard deviation by adopting a probability density function of Gaussian distribution;
and the distance between the first moment and the second moment is smaller than a preset threshold value.
5. The multi-target tracking method based on the tracking chain as claimed in claim 4, wherein: the states comprise unconsciousness and coma;
modifying the state of the first tracking chain when the first target object identification fails, including:
if the first target object fails to be identified, modifying the state of the first tracking chain into a coma, adding 1 to the coma number n1, and recording the corresponding time;
and if the first target object identification fails, adding 1 to the unconsciousness number n2, and recording the corresponding time.
6. The multi-target tracking method based on the tracking chain as claimed in claim 5, characterized in that: the state also includes immature, mature;
before the calculating the similarity of the first tracking chain and the second tracking chain, further performing a screening process on the first tracking chain and the second tracking chain, including:
if n1/len is smaller than a first threshold value, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
And/or calculating the number n2 of times that the first tracking chain and the second tracking chain are in non-coma at the same time, and if n2/len is larger than a second threshold value, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
Calculating the times n3 that the first tracking chain and the second tracking chain are close to each other at the same time, and if n3/len is smaller than a third threshold, abandoning the calculation of the similarity of the first tracking chain and the second tracking chain; and/or
Calculating an included angle alpha between the first tracking chain and the second tracking chain, and if alpha is larger than a fourth threshold, giving up calculating the similarity of the first tracking chain and the second tracking chain;
wherein, said len represents the maximum length of the tracking chain.
7. The multi-target tracking method based on the tracking chain as claimed in claim 6, characterized in that: the calculating an included angle α between the first tracking chain and the second tracking chain includes:
calculating the pixel speed U of the first tracking chain, and calculating a vector V of the chain tail of the first tracking chain and the chain tail of the second tracking chain;
the angle is calculated using the formula cos (α) ═ U × V/(| U | V |).
8. A multi-target tracking system based on a tracking chain comprises a processing module, a storage module and an acquisition module, wherein the processing module is respectively connected with the storage module and the acquisition module; wherein the content of the first and second substances,
the storage module is used for storing executable computer program codes;
the acquisition module is used for acquiring the monitoring image and transmitting the monitoring image to the processing module;
the method is characterized in that: the processing module for executing the method according to any one of claims 1-7 by calling the executable computer program code in the storage module.
9. An electronic device, comprising:
a memory storing executable program code;
a processor coupled with the memory;
the method is characterized in that: the processor calls the executable program code stored in the memory to perform the method of any of claims 1-7.
10. A computer storage medium having a computer program stored thereon, characterized in that: the computer program, when executed by a processor, performs the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210086779.8A CN114565638B (en) | 2022-01-25 | 2022-01-25 | Multi-target tracking method and system based on tracking chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210086779.8A CN114565638B (en) | 2022-01-25 | 2022-01-25 | Multi-target tracking method and system based on tracking chain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114565638A true CN114565638A (en) | 2022-05-31 |
| CN114565638B CN114565638B (en) | 2022-10-28 |
Family
ID=81712892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210086779.8A Active CN114565638B (en) | 2022-01-25 | 2022-01-25 | Multi-target tracking method and system based on tracking chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114565638B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496009A (en) * | 2011-12-09 | 2012-06-13 | 北京汉邦高科数字技术股份有限公司 | Multi-face tracking method for intelligent bank video monitoring |
| CN104732187A (en) * | 2013-12-18 | 2015-06-24 | 杭州华为企业通信技术有限公司 | Method and equipment for image tracking processing |
| CN106897735A (en) * | 2017-01-19 | 2017-06-27 | 博康智能信息技术有限公司上海分公司 | The tracking and device of a kind of Fast Moving Object |
| CN106909935A (en) * | 2017-01-19 | 2017-06-30 | 博康智能信息技术有限公司上海分公司 | A kind of method for tracking target and device |
| CN110276780A (en) * | 2019-06-17 | 2019-09-24 | 广州织点智能科技有限公司 | A kind of multi-object tracking method, device, electronic equipment and storage medium |
| TW202026949A (en) * | 2019-01-13 | 2020-07-16 | 多方科技股份有限公司 | Object detection method and computing system thereof |
| CN112700478A (en) * | 2020-12-31 | 2021-04-23 | 北京澎思科技有限公司 | Target tracking method, system, computer-readable storage medium, and program product |
| CN113487650A (en) * | 2021-06-08 | 2021-10-08 | 中移(上海)信息通信科技有限公司 | Road congestion detection method, device and detection equipment |
| CN113838095A (en) * | 2021-08-30 | 2021-12-24 | 天津港集装箱码头有限公司 | Personnel tracking ball machine control method based on speed control |
| CN113868948A (en) * | 2021-09-28 | 2021-12-31 | 核电运行研究(上海)有限公司 | User-oriented dynamic threshold model training system and method |
-
2022
- 2022-01-25 CN CN202210086779.8A patent/CN114565638B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496009A (en) * | 2011-12-09 | 2012-06-13 | 北京汉邦高科数字技术股份有限公司 | Multi-face tracking method for intelligent bank video monitoring |
| CN104732187A (en) * | 2013-12-18 | 2015-06-24 | 杭州华为企业通信技术有限公司 | Method and equipment for image tracking processing |
| CN106897735A (en) * | 2017-01-19 | 2017-06-27 | 博康智能信息技术有限公司上海分公司 | The tracking and device of a kind of Fast Moving Object |
| CN106909935A (en) * | 2017-01-19 | 2017-06-30 | 博康智能信息技术有限公司上海分公司 | A kind of method for tracking target and device |
| TW202026949A (en) * | 2019-01-13 | 2020-07-16 | 多方科技股份有限公司 | Object detection method and computing system thereof |
| CN110276780A (en) * | 2019-06-17 | 2019-09-24 | 广州织点智能科技有限公司 | A kind of multi-object tracking method, device, electronic equipment and storage medium |
| CN112700478A (en) * | 2020-12-31 | 2021-04-23 | 北京澎思科技有限公司 | Target tracking method, system, computer-readable storage medium, and program product |
| CN113487650A (en) * | 2021-06-08 | 2021-10-08 | 中移(上海)信息通信科技有限公司 | Road congestion detection method, device and detection equipment |
| CN113838095A (en) * | 2021-08-30 | 2021-12-24 | 天津港集装箱码头有限公司 | Personnel tracking ball machine control method based on speed control |
| CN113868948A (en) * | 2021-09-28 | 2021-12-31 | 核电运行研究(上海)有限公司 | User-oriented dynamic threshold model training system and method |
Non-Patent Citations (3)
| Title |
|---|
| ALEX BEWLEY等: "Alextrac: Affinity learning by exploring temporal reinforcement within association chains", 《2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)》 * |
| 郑舟轩等: "基于多目标跟踪的商场热点图生成方法", 《电脑知识与技术》 * |
| 黄鑫: "基于视频的车流量智能交通检测系统研究", 《中国优秀硕士学位论文全文数据库_工程科技Ⅱ辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114565638B (en) | 2022-10-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10002309B2 (en) | Real-time object analysis with occlusion handling | |
| CN115471805B (en) | Point cloud processing and deep learning model training method and device and automatic driving vehicle | |
| CN113326773A (en) | Recognition model training method, recognition method, device, equipment and storage medium | |
| CN114449343A (en) | Video processing method, device, equipment and storage medium | |
| CN113538235A (en) | Training method and device of image processing model, electronic equipment and storage medium | |
| CN111428535A (en) | Image processing apparatus and method, and image processing system | |
| CN116434325A (en) | Method, device, equipment and storage medium for detecting specific action | |
| CN111652181A (en) | Target tracking method and device and electronic equipment | |
| CN114565638B (en) | Multi-target tracking method and system based on tracking chain | |
| CN114169425A (en) | Training target tracking model and target tracking method and device | |
| CN113780578A (en) | Model training method and device, electronic equipment and readable storage medium | |
| CN113298852A (en) | Target tracking method and device, electronic equipment and computer readable storage medium | |
| CN116935287A (en) | Video understanding method and device | |
| CN113361519B (en) | Target processing method, training method of target processing model and device thereof | |
| CN113989720A (en) | Target detection method, training method, device, electronic equipment and storage medium | |
| CN113657596A (en) | Method and device for training model and image recognition | |
| CN116309689B (en) | Obstacle track prediction method, device, equipment and medium | |
| CN115482809B (en) | Keyword retrieval method, keyword retrieval device, electronic equipment and storage medium | |
| CN112486677B (en) | Data graph transmission method and device | |
| CN116866669A (en) | Video recommendation method, apparatus and computer program product | |
| US20240054757A1 (en) | Methods and systems for temporal action localization of video data | |
| CN113378858A (en) | Image detection method, apparatus, device, vehicle, and medium | |
| CN117746418A (en) | Target detection model construction method, target detection method and related device | |
| CN115131709A (en) | Video category prediction method, and training method and device of video category prediction model | |
| CN116494969A (en) | Vehicle driving planning method, device, equipment and storage medium |
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 |