CN115841503A - Determination method of tracking object and tracking method of target person - Google Patents
Determination method of tracking object and tracking method of target person Download PDFInfo
- Publication number
- CN115841503A CN115841503A CN202211352403.3A CN202211352403A CN115841503A CN 115841503 A CN115841503 A CN 115841503A CN 202211352403 A CN202211352403 A CN 202211352403A CN 115841503 A CN115841503 A CN 115841503A
- Authority
- CN
- China
- Prior art keywords
- heads
- human
- target
- face
- preset threshold
- 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.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a determination method of a tracked object and a tracking method of a target person. The method for determining the tracking object comprises the following steps: acquiring a human head detection result in a specific area in a target image frame of a video; when the number of the human heads in the human head detection result is larger than a preset threshold value number, acquiring a human face posture estimation result in the specific area; screening out the number of the heads which is not more than a preset threshold value according to the face posture estimation result based on a preset rule, and defining the screened heads as target heads; and determining the person corresponding to the head of the target person as the tracked target person. The whole process determining process of the invention is insensitive to the target person, does not need to spend extra processes, is simple and reliable, and improves the scene adaptability of the target object because of not spending extra processes.
Description
Technical Field
The present invention relates to the field of video image processing technologies, and in particular, to a method for determining a tracked object, a method, an apparatus, a device, and a storage medium for tracking a target person.
Background
Artificial intelligence visual target tracking is widely used in various fields and scenarios, such as teacher tracking or student tracking in distance teaching, speaker tracking in distance conferences, etc. Generally, the target tracking is performed on the premise of identifying and locking a tracked object, and currently, a face recognition technology is generally used for identifying an object to be tracked and then locking the tracked object. If a target object is locked by using a face recognition technology, a face must be entered in advance, for example, in a teaching scene in which a teacher is tracked and photographed, the face of the teacher must be entered in advance. However, it takes extra time to input the face in advance and collect the face material of the target object, and the process is very tedious. In addition, in the teaching environment, the teacher is also a current thing, and the teacher has randomness, and the human face material is difficult to be determined in advance, so that the target object cannot be locked by adopting the human face recognition technology.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for determining a tracked object, aiming at overcoming the defect that face materials of the tracked object need to be input in advance.
In a first aspect, the present invention provides a method for determining a tracked object, including the steps of:
acquiring a human head detection result in a specific area in a target image frame of a video;
when the number of the human heads in the human head detection result is larger than a preset threshold value number, acquiring a human face posture estimation result in the specific area;
screening out the number of the heads which is not more than a preset threshold value according to the face posture estimation result based on a preset rule, and defining the screened heads as target heads;
and determining the person corresponding to the head of the target person as a tracked target person.
In one embodiment, the face pose estimation result comprises: the orientation of the human face;
the process of screening out the heads not more than the preset threshold number according to the face posture estimation result based on the preset rule and defining the screened heads as target heads comprises the following steps:
screening out the heads of the human faces within a set orientation threshold range;
and if the number of the human heads in the set orientation threshold interval is not more than the preset threshold number, defining the human heads in the set orientation threshold interval as target human heads.
In one embodiment, the method further comprises the steps of: the face pose estimation result further comprises: face coordinate positions;
the process of screening out the heads not greater than the preset threshold number according to the face posture estimation result based on the preset rule and defining the screened heads as target heads further comprises the following steps:
and if the number of the human heads in the set orientation threshold value interval is larger than the preset threshold value number, defining the human heads which are closer to the preset threshold value number on the upper edge of the specific area in the longitudinal direction of the picture as target human heads in the set orientation threshold value interval according to the human face coordinate position.
In an embodiment, the process of screening out, based on a preset rule and according to the face pose estimation result, a number of human heads not greater than a preset threshold, and defining the screened human heads as target human heads further includes the steps of:
if the obtained target heads are larger than the preset threshold number in the process of defining the heads closer to the upper edge of the specific area in the longitudinal direction of the picture as the target heads, according to the face coordinate position, the heads farther away from the center of the specific area in the transverse direction of the picture are removed from the target heads, so that the number of the target heads is equal to the preset threshold number.
In one embodiment, the face pose estimation result includes: face coordinate positions;
the process of screening out the heads not more than the preset threshold number according to the face posture estimation result based on the preset rule and defining the screened heads as target heads comprises the following steps:
and according to the face coordinate position, defining the heads of the preset threshold number closer to the specific position in the specific area as target heads.
In one embodiment, the method further comprises the steps of:
and extracting the face characteristics of the target person.
In a second aspect, the present invention provides a method for tracking a target person, including the steps of:
determining and locking a target person by using the determination method of the tracking object according to any one of the above embodiments;
tracking a shooting-locked target person;
extracting the face characteristics of the target person;
and when the tracked target person is lost, the target person is relocked by utilizing the face characteristics.
In a third aspect, the present invention provides a tracking object determining apparatus, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a human head detection result in a specific area in a target image frame of a video, and acquiring a human face posture estimation result in the specific area when the number of human heads in the human head detection result is greater than a preset threshold number;
the screening module is used for screening out the heads of which the number is not more than a preset threshold value according to the face posture estimation result based on a preset rule, and defining the screened heads as target heads;
and the determining module is used for determining the person corresponding to the head of the target person as the tracked target person.
In a fourth aspect, the present invention provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of the above embodiments when executing the program.
In a fifth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any of the above embodiments.
According to the method and the device, under the condition that the face of the target person does not need to be input in advance, the result of face posture estimation in the video is screened through the preset screening rule, the most consistent target person head is obtained, the person corresponding to the target person head is determined as the target person of video tracking, the whole process is insensitive to the target person, extra processes are not needed, simplicity and reliability are achieved, and the scene adaptability of the target object is improved due to the fact that the extra processes are not needed.
Drawings
FIG. 1 is a flow chart illustrating an embodiment of the present invention.
FIG. 2 is a diagram of a video frame according to the present invention.
FIG. 3 is a schematic flow chart of an embodiment of the present invention.
FIG. 4 is a schematic flow chart of another embodiment of the present invention.
FIG. 5 is a schematic flow chart of yet another embodiment of the present invention.
Fig. 6 is a schematic diagram of the overall structure of the embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It should be noted that the term "first \ second \ … …" referred to in the embodiments of the present invention is merely to distinguish similar objects, and does not represent a specific ordering for the objects, and it should be understood that "first \ second \ … …" may exchange a specific order or sequence order if allowed. It should be understood that the objects identified as "first \ second \ … …" may be interchanged where appropriate to enable the embodiments of the invention described herein to be practiced in sequences other than those illustrated or described herein.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart of a determination method for a tracked object according to an embodiment of the present invention, where the method includes step S110, step S120, step S130, and step S140. It should be noted that steps S110 to S140 are only reference numerals for clearly explaining the corresponding relationship between the embodiment and fig. 1, and do not represent a limitation on the order of the steps in the embodiment.
Step S110, acquiring a human head detection result in a specific area in a target image frame of a video;
step S120, when the number of the human heads in the human head detection result is larger than a preset threshold value number, obtaining a human face posture estimation result in the specific area;
step S130, screening out the number of the human heads which is not more than a preset threshold value according to the human face posture estimation result based on a preset rule, and defining the screened human heads as target human heads;
step S140, determining the person corresponding to the head of the target person as the tracked target person.
For convenience of explaining the method, the method will be described in detail later by taking a teaching scene as an example. As shown in fig. 2, fig. 2 is one of the image frames in the video of the teaching scene, which is used for determining the tracking object and is referred to as the target image frame in the method. In fig. 2, the area within the solid black line is a specific area, which may be defined by the user in advance according to actual needs. If the user does not determine the specific area, the user may default that the entire screen is the specific area. In a teaching scene, a target tracking object is a teacher usually, and a main activity space of the teacher is a platform, so that a platform area can be determined as a specific area in advance, and then, a human head detection result is obtained by performing human head detection on the specific area. Under normal conditions, if the specific area is a platform area, only one teacher exists in the platform area, so that the result of the human head detection is a human head, the human head is determined as a target tracking object, and the target tracking object can be tracked. However, in an actual environment, as shown in fig. 2, either the students are answering questions while standing, or the seats of the students in the classroom and the podium are compact, and the heads of some students can "rush" into a specific area, which leads to a situation that there are multiple heads in the specific area. First, a human head detection result in a specific area in a target image frame of a video is acquired in step S110.
Continuing with the previous example, when a plurality of heads appear, the heads of the teachers need to be screened out from the heads, and the method adopts a method of carrying out face posture estimation on each head, obtaining a face posture estimation result in the specific area, and screening and determining the heads of the teachers by using the face posture estimation result. Usually, the human head is subjected to human face pose estimation, the obtained human face pose estimation result generally includes information such as the orientation of the human face and the specific coordinate position of the human head in the video frame, in step S130, the human head is screened by some set rules, such as the preset orientation angle of the human head facing inwards, the comparison of the height of the human head, etc., by using part or all of the information in the human face pose estimation result, so as to obtain a human head which best meets the motion characteristics of the teacher, and the best meeting human head is taken as the target human head, that is, the human head of the teacher. After the head of the teacher is identified, the person corresponding to the head can be determined to be the target person, namely the teacher, and then the target person can be locked for tracking shooting.
It should be noted that the above description is made for the teaching scene, and the method is also applicable to the case that the number of people in a specific area is more than the preset number of tracked people, so the triggering condition of step S120 is that the number of detected people is greater than the threshold, and step S130 is to perform the screening when the number of detected people is greater than the threshold, until people within the threshold number are screened.
According to the method, under the condition that the face of a target person does not need to be input in advance, the result of face posture estimation in a video is screened through a preset screening rule, the most consistent target person head is obtained, the person corresponding to the target person head is determined to be the target person tracked by the video, the whole process is insensitive to the target person, no additional process is needed, simplicity and reliability are achieved, and the scene adaptability of the locked target object is improved due to the fact that no additional process is needed.
In one embodiment, the face pose estimation result includes: the orientation of the human face;
as shown in fig. 3, step S130 includes: step S210 and step S220.
Step S210, screening out heads with faces facing within a set facing threshold interval;
in step S220, if the number of the human heads in the set orientation threshold interval is not greater than the preset threshold number, the human heads in the set orientation threshold interval are defined as the target human heads.
Taking the teaching scene of fig. 2 as an example, normally, the photographed teacher is generally the front face, and the photographed student is generally only the back head, so that the teacher can be effectively discriminated and the target person object to be tracked can be really discriminated through the face orientation.
Specifically, the euler angles (pitch angle, yaw angle and roll angle) of the face result at the moment are calculated by using the two-dimensionally predicted face key point coordinates and the key point coordinates of a standard face in a three-dimensional space according to a perspective multipoint conversion method (solvePNP), the face yaw angle is filtered, and the face in a set threshold interval (namely the face with smaller front face turning direction) is screened out.
It should be noted that, when the target person is screened according to the face orientation, the number of persons meeting the requirement may be smaller than the preset threshold number, and at this time, it is not mandatory to find the target persons meeting the preset threshold number, and only the persons meeting the requirement are taken as the target persons; in addition, there may be a case where the number of persons who meet the requirement is 0, and at this time, the target person is not defined, and it is considered that there is no target person in the video.
In one embodiment, the face pose estimation result includes: face coordinate positions;
as shown in fig. 4, step S130 further includes: step S230.
In step S230, if the number of the heads in the set orientation threshold interval is greater than the preset threshold number, among the heads in the set orientation threshold interval, the heads closer to the preset threshold number on the upper edge of the specific area in the longitudinal direction of the screen are defined as the target heads.
In the above embodiment, the number of persons meeting the requirement may be larger than the preset threshold number by the face facing the target person to be filtered, and at this time, further filtering is required.
As shown in fig. 2, in the video image, the people on the podium are generally high in the people under the podium, so the embodiment preferentially selects the higher head in the specific area until the number of the selected heads is equal to the preset threshold number.
In one embodiment, as shown in fig. 5, step S130 further includes: step S240.
Step S240, if the number of the target persons obtained in the process of step S230 is greater than the preset threshold number, removing the persons farther away from the center of the specific area in the transverse direction of the screen from the target persons, so that the number of the target persons is equal to the preset threshold number.
This embodiment is an operation mode of further screening on the basis of the above embodiment. And when the head heights of the target figures are the same and the number of the screened heads is larger than the preset threshold number, carrying out secondary judgment. In the present embodiment, the head closer to the center position of the specific area is considered to be more suitable for the activity habit of the target person, and therefore, the head closer to the center position within the specific area is preferentially selected until the number of selected heads is equal to the preset threshold number.
In one embodiment, the face pose estimation result further includes: face coordinate positions; step S130 further includes: step S250.
And step S250, defining the heads of the preset threshold quantity closer to the specific position in the specific area as target heads according to the face coordinate position.
A specific position is determined in the specific area, and the specific position may be determined based on the target object or the target person, such as the position of a table defined as the specific position, or the specific area itself, such as the center point or the golden section point in the lateral direction of the specific area. In the present embodiment, since the head closer to the specific position is considered to be more suitable for the activity habit of the target person, the head closer to the center position within the specific area is preferentially selected until the number of selected heads is equal to the preset threshold number.
In one embodiment, the method for determining the tracking object further includes step S150.
And step S150, extracting the face characteristics of the target person.
After the target person is determined, the target person is tracked, but in the tracking process, the target person may be lost. Extracting the face features for the target person may use face recognition techniques to relock the target object after the target person is lost.
Example two
The embodiment of the invention provides a method for tracking a target person, which comprises the following steps: step S310, step S320, step S330, and step S340. It should be noted that steps S310 to S340 are merely labels, and do not represent a limitation on the order of the steps in this embodiment.
Step S310, determining and locking a target person by using the determination method of the tracked object of the first embodiment;
step S320, tracking and shooting the locked target person;
step S330, extracting the face characteristics of the target person;
and step S340, when the tracked target person is lost, re-locking the target person by using the human face characteristics.
In the embodiment, a target person is locked by two methods, under the condition that no human face characteristics exist, the target person is determined by the method of the first embodiment, the determined target person is locked, tracking shooting is carried out on the target person, and the human face characteristics of the target person are extracted in the tracking shooting process; if the tracked target person is lost in the presence of the face feature, the target person is relocked with the face feature. The whole tracking process is completed at one step, the target object is locked by using the face recognition technology, and the face materials of the target object are not required to be additionally collected.
EXAMPLE III
Corresponding to the method of the first embodiment, as shown in fig. 6, the present invention further provides a determination apparatus 7 for tracking an object, including: an acquisition module 710, a screening module 720, and a determination module 730.
An obtaining module 710, configured to obtain a human head detection result in a specific area in a target image frame of a video, and obtain a human face pose estimation result in the specific area when the number of human heads in the human head detection result is greater than a preset threshold number;
a screening module 720, configured to screen out, based on a preset rule, heads that are not greater than a preset threshold number according to the face pose estimation result, and define the screened heads as target heads;
the determining module 730 is configured to determine a person corresponding to the head of the target person as a tracked target person.
The device screens the result of the face posture estimation in the video through the preset screening rule under the condition that the face of a target person is not required to be input in advance, the most consistent target person is obtained, the person corresponding to the target person is determined as the target person of the video tracking, the whole process is insensitive to the target person, extra processes are not required to be spent, simplicity and reliability are achieved, and the scene adaptability of the target object is improved due to the fact that extra processes are not required to be spent.
In one embodiment, the face pose estimation result includes: the orientation of the human face;
the screening module executes the process of screening out the human heads which are not more than the preset threshold number according to the human face posture estimation result based on the preset rule, and defining the screened human heads as target human heads, and the process comprises the following steps:
screening out the heads of the human faces within a set orientation threshold range;
and if the number of the human heads in the set orientation threshold interval is not more than the preset threshold number, defining the human heads in the set orientation threshold interval as target human heads.
In one embodiment, the face pose estimation result further includes: face coordinate positions;
the screening module executes the process of screening out the human heads which are not more than the preset threshold number according to the human face posture estimation result based on the preset rule, and defining the screened human heads as target human heads, and the process comprises the following steps:
if the number of the heads in the set orientation threshold interval is larger than the preset threshold number, among the heads in the set orientation threshold interval, defining the heads, closer to the preset threshold number on the upper edge of the specific area in the longitudinal direction of the picture, as target heads.
In one embodiment, the process of screening out, based on the preset rule, heads not greater than a preset threshold number according to the face pose estimation result, and defining the screened heads as target heads by the screening module includes the steps of:
if the obtained target heads are larger than the preset threshold number in the process of defining the heads, which are closer to the upper edge of the specific area in the longitudinal direction of the picture, as the target heads, the heads farther away from the center of the specific area in the transverse direction of the picture are removed from the target heads, so that the number of the target heads is equal to the preset threshold number.
In one embodiment, the face pose estimation result includes: face coordinate positions;
the screening module executes the process of screening out the human heads which are not more than the preset threshold number according to the human face posture estimation result based on the preset rule, and defining the screened human heads as target human heads, and the process comprises the following steps:
and according to the face coordinate position, defining the heads of the preset threshold number closer to the specific position in the specific area as target heads.
In one embodiment, the device for determining a tracked object 7 further comprises: and the extraction module 740, wherein the extraction module 740 is used for extracting the face features of the target person.
Example four
An embodiment of the present invention further provides a storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the method for determining a tracked object or the method for tracking a target person according to any of the above embodiments is implemented.
Those skilled in the art will understand that: all or part of the steps of implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer-readable storage medium, and when executed, executes the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Random Access Memory (RAM), a Read-Only Memory (ROM), a magnetic disk, and an optical disk.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a RAM, a ROM, a magnetic or optical disk, or various other media that can store program code.
Corresponding to the computer storage medium, in an embodiment, there is further provided a computer device including a memory, an encoder, and a computer program stored on the memory and executable on the encoder, wherein the encoder implements the determination method of the tracked object or the tracking method of the target person according to any one of the embodiments described above when executing the program.
According to the computer equipment, under the condition that the face of a target person does not need to be input in advance, the result of face posture estimation in a video is screened through a preset screening rule, the most consistent target person head is obtained, the person corresponding to the target person head is determined as the target person of video tracking, the whole process is insensitive to the target person, extra processes do not need to be spent, simplicity and reliability are achieved, and the scene adaptability of the target object is improved due to the fact that the extra processes do not need to be spent.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A determination method of a tracked object, characterized by comprising the steps of:
acquiring a human head detection result in a specific area in a target image frame of a video;
when the number of the human heads in the human head detection result is larger than a preset threshold value number, acquiring a human face posture estimation result in the specific area;
screening out the number of the human heads which is not more than a preset threshold value according to the human face posture estimation result based on a preset rule, and defining the screened human heads as target human heads;
and determining the person corresponding to the head of the target person as a tracked target person.
2. The method for determining a tracked object according to claim 1, wherein the face pose estimation result comprises: the orientation of the human face;
the process of screening out the heads not more than the preset threshold number according to the face posture estimation result based on the preset rule and defining the screened heads as target heads comprises the following steps:
screening out the heads of the human faces within a set orientation threshold range;
and if the number of the human heads in the set orientation threshold interval is not more than the preset threshold number, defining the human heads in the set orientation threshold interval as target human heads.
3. The method for determining the tracked object according to claim 2, further comprising the steps of: the face pose estimation result further comprises: face coordinate positions;
the process of screening out the heads not greater than the preset threshold number according to the face posture estimation result based on the preset rule and defining the screened heads as target heads further comprises the following steps:
and if the number of the human heads in the set orientation threshold value interval is larger than the preset threshold value number, defining the human heads which are closer to the preset threshold value number on the upper edge of the specific area in the longitudinal direction of the picture as target human heads in the set orientation threshold value interval according to the human face coordinate position.
4. The method for determining the tracked object according to claim 3, wherein the process of screening out the number of the human heads not greater than a preset threshold value according to the result of the estimation of the human face pose based on a preset rule, and defining the screened out human heads as the target human heads further comprises the steps of:
if the obtained target heads are larger than the preset threshold number in the process of defining the heads closer to the upper edge of the specific area in the longitudinal direction of the picture as the target heads, according to the face coordinate position, the heads farther away from the center of the specific area in the transverse direction of the picture are removed from the target heads, so that the number of the target heads is equal to the preset threshold number.
5. The method for determining a tracked object according to claim 1, wherein the face pose estimation result comprises: face coordinate positions;
the process of screening out the heads of which the number is not more than a preset threshold value according to the face posture estimation result based on a preset rule and defining the screened heads as target heads comprises the following steps:
and according to the face coordinate position, defining the heads of the preset threshold number closer to the specific position in the specific area as target heads.
6. The determination method of the tracking object according to any one of claims 1 to 5, characterized by further comprising the steps of:
and extracting the face characteristics of the target person.
7. A method for tracking a target person, comprising the steps of:
determining and locking a target person by using the determination method of the tracked object according to any one of claims 1 to 5;
tracking a shooting-locked target person;
extracting the face characteristics of a target figure;
and when the tracked target person is lost, re-locking the target person by utilizing the face characteristics.
8. An apparatus for determining a tracked object, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a human head detection result in a specific area in a target image frame of a video, and acquiring a human face posture estimation result in the specific area when the number of human heads in the human head detection result is greater than a preset threshold number;
the screening module is used for screening out the human heads of which the number is not more than a preset threshold value according to the human face posture estimation result based on a preset rule, and defining the screened human heads as target human heads;
and the determining module is used for determining the person corresponding to the head of the target person as the tracked target person.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211352403.3A CN115841503A (en) | 2022-10-31 | 2022-10-31 | Determination method of tracking object and tracking method of target person |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211352403.3A CN115841503A (en) | 2022-10-31 | 2022-10-31 | Determination method of tracking object and tracking method of target person |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115841503A true CN115841503A (en) | 2023-03-24 |
Family
ID=85576718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211352403.3A Pending CN115841503A (en) | 2022-10-31 | 2022-10-31 | Determination method of tracking object and tracking method of target person |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115841503A (en) |
-
2022
- 2022-10-31 CN CN202211352403.3A patent/CN115841503A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5001260B2 (en) | Object tracking method and object tracking apparatus | |
| KR101971866B1 (en) | Method and apparatus for detecting object in moving image and storage medium storing program thereof | |
| JP5227911B2 (en) | Surveillance video retrieval device and surveillance system | |
| US8995714B2 (en) | Information creation device for estimating object position and information creation method and program for estimating object position | |
| KR20110053820A (en) | Method and apparatus for processing image | |
| KR102486986B1 (en) | Objects detecting system, method and computer readable recording medium | |
| CN110969045A (en) | Behavior detection method and device, electronic equipment and storage medium | |
| JP2020135551A (en) | Object recognition device, object recognition method and object recognition program | |
| CN113705510A (en) | Target identification tracking method, device, equipment and storage medium | |
| CN111401238A (en) | Method and device for detecting character close-up segments in video | |
| JP4821355B2 (en) | Person tracking device, person tracking method, and person tracking program | |
| CN117218703A (en) | Intelligent learning emotion analysis method and system | |
| CN112257492A (en) | Real-time intrusion detection and tracking method for multiple cameras | |
| CN115841503A (en) | Determination method of tracking object and tracking method of target person | |
| JP2020123105A (en) | Learning device, learning method, learning program, and object recognition device | |
| CN114170506A (en) | Robot-oriented scene graph-based visual scene understanding system and method | |
| CN111242189B (en) | Feature extraction method and device and terminal equipment | |
| CN111862100A (en) | Image segmentation method, device, equipment and storage medium | |
| CN112766230A (en) | Video streaming personnel online time length estimation method and corresponding system | |
| CN111325185A (en) | Face fraud prevention method and system | |
| CN116311494A (en) | Method, device, equipment and storage medium for identifying blackboard writing behaviors | |
| JP7211495B2 (en) | Training data generator | |
| JP7349288B2 (en) | Object recognition device, object recognition method, and object recognition program | |
| JP7211496B2 (en) | Training data generator | |
| CN113392776B (en) | Seat leaving behavior detection method and storage device combining seat information and machine vision |
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 |