CN109886995B - Multi-target tracking method in complex environment - Google Patents
Multi-target tracking method in complex environment Download PDFInfo
- Publication number
- CN109886995B CN109886995B CN201910034595.5A CN201910034595A CN109886995B CN 109886995 B CN109886995 B CN 109886995B CN 201910034595 A CN201910034595 A CN 201910034595A CN 109886995 B CN109886995 B CN 109886995B
- Authority
- CN
- China
- Prior art keywords
- target
- shooting
- tracked
- position data
- data
- 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.)
- Active
Links
Images
Abstract
The invention discloses a multi-target tracking method in a complex environment, which comprises the following steps: s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream; s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range; s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus; s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1; the invention has good practicability, effectively highlights individuals or needed people during shooting, and ensures the quality after shooting.
Description
Technical Field
The invention relates to the technical field of multi-target tracking, in particular to a multi-target tracking method in a complex environment.
Background
At present, people can shoot videos through a camera which is held by a hand or is provided with a holder when the people go out to play or get at a meeting, so that beautiful scenery during play and happy time of the people together with family friends can be recorded, and the existing camera can only confirm and detect the faces of people appearing in the shot videos when the video is shot, but cannot track the people appearing in the videos. When people in a video need to be tracked and shot, people appearing in the video can only be tracked and shot by changing the shooting area and shooting angle of a camera by a video photographer, and people with special needs or individuals cannot be well highlighted in a crowd, tracking processing can not be well performed on people with needs, and quality after shooting cannot be guaranteed, so that a multi-target tracking method in a complex environment is provided for solving the problems.
Disclosure of Invention
Based on the technical problems in the background technology, the invention provides a multi-target tracking method in a complex environment.
The invention provides a multi-target tracking method in a complex environment, which comprises the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: the target position to be tracked is marked, and then similarity between color information in the pixel area and the tracked object is evaluated, so that tracking of the target to be tracked is completed.
Preferably, in the step S1, the number of detected moving objects is set to 3-7, and it is required to ensure that the number of frames in the video stream remains stable, and by using a foreground detection method, it is determined whether the moving objects are detected from the video stream captured within a preset time, the video stream includes each video image.
Preferably, in the step S2, the interval time is set to 1-5S, the first position data is analyzed and processed, then the second position data is analyzed and processed, and the analyzed and processed data is recorded.
Preferably, in the step S2, the number of the first position data and the second position data is 3-7, and the average value is obtained after the data processing.
Preferably, in the step S3, the adjusted position of the photographing apparatus is located in an optimal photographing range, and when no crowd to be photographed is detected within a certain period of time, the photographing range of the photographing apparatus is adjusted according to a preset photographing angle.
Preferably, in the step S4, the target to be tracked is determined by manually tracking, the tracked target is manually determined according to the requirement, and then the determined tracked target is virtually marked by using a specific virtual mark.
Preferably, in S5, the position data includes motion information such as a current moving speed, a moving distance, and a moving direction to be tracked.
Preferably, in the step S5, the position of the target to be tracked is marked, so that the movement information such as the movement speed, the movement distance, the movement direction and the like of the target to be tracked is conveniently operated, and the data is automatically stored after the operation is finished.
Preferably, in S6, the shooting device is controlled to automatically track the target to be tracked.
Preferably, in the step S6, the data information after evaluating the similarity between the color information in the pixel area and the tracking object is sorted, when the sorted data information is always consistent with the initial data information, the sorted data is ignored, when the sorted data information is inconsistent with the initial data information, the comparison is continued, and when the sorted data information is still inconsistent with the initial data information, the user needs to be reminded of the voice broadcasting in time.
The invention has the beneficial effects that:
when the position of the shooting equipment is not located in the optimal shooting range, the position of the shooting equipment can be located in the optimal shooting range through adjusting the position of the shooting equipment, the shooting effect is good, the angle of the shooting equipment can be adjusted, shooting of the shooting equipment is facilitated, the position of a target to be tracked is marked manually, position data information of the target to be tracked is calculated, tracking processing of the target to be tracked is facilitated, the number of the targets to be tracked can be adjusted manually, individuals or needed people are effectively highlighted during shooting, and the quality after shooting is guaranteed.
The invention has good practicability, effectively highlights individuals or needed people during shooting, and ensures the quality after shooting.
Description of the drawings:
FIG. 1 is a flow chart of a multi-target tracking method in a complex environment according to the present invention;
FIG. 2 is a flow chart of a multi-target tracking method preparation before shooting under a complex environment according to the present invention;
FIG. 3 is a flowchart of a multi-target tracking method according to the present invention when determining a tracking target;
fig. 4 is a flowchart of an automatic tracking method for multiple targets in a complex environment according to the present invention.
Detailed Description
The invention is further illustrated below in connection with specific embodiments.
Example 1
Referring to fig. 1-4, the embodiment provides a multi-target tracking method in a complex environment, which includes the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: the target position to be tracked is marked, and then similarity between color information in the pixel area and the tracked object is evaluated, so that tracking of the target to be tracked is completed.
In this embodiment, in the step S1, the number of detected moving objects is set to 3, and it is required to ensure that the number of frames in the video stream remains stable, by using a foreground detection method, it is determined whether a moving object is detected from the video stream captured within a preset time, the video stream includes each video image, in the step S2, the interval time is set to 1S, analysis processing is performed on first position data, then analysis processing is performed on second position data, the analyzed data is recorded, in the step S2, the number of the first position data and the number of the second position data are both 3, the average value is taken after the data processing, in the step S3, the position of the adjusted capturing device is located in an optimal capturing range, when no crowd to be captured is detected within a certain time, the capturing range of the capturing device is adjusted according to a preset capturing angle, in the step S4, it is determined that the target to be tracked is manually tracked, the tracking target is manually determined according to the requirement, then a specific virtual mark is used to perform virtual mark on the determined tracking target, in the step S5, the position data includes the current moving speed of the target to be tracked, the step S is the current moving speed of the target is calculated, after the moving speed is calculated, and the moving information is consistently is kept in the same with the moving range of the moving object, and after the moving speed is calculated, and after the moving information is calculated, and the moving information is equal to the moving information is calculated, when the moving information is calculated, and when the moving information is compared with the moving information, when the data information after arrangement is inconsistent with the initial data information, comparison is continued, and when the data information is still inconsistent with the initial data information, the user is required to be reminded in time through voice broadcasting.
Example 2
Referring to fig. 1-4, the embodiment provides a multi-target tracking method in a complex environment, which includes the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: the target position to be tracked is marked, and then similarity between color information in the pixel area and the tracked object is evaluated, so that tracking of the target to be tracked is completed.
In this embodiment, in the step S1, the number of detected moving objects is set to 4, and it is required to ensure that the number of frames in the video stream remains stable, by using a foreground detection method, it is determined whether a moving object is detected from the video stream captured within a preset time, the video stream includes each video image, in the step S2, the interval time is set to 2S, analysis processing is performed on first position data, then analysis processing is performed on second position data, the analyzed data is recorded, in the step S2, the number of the first position data and the second position data are both 4, the average value is taken after the data processing, in the step S3, the position of the adjusted capturing device is located in an optimal capturing range, when no crowd to be captured is detected within a certain time, the capturing range of the capturing device is adjusted according to a preset capturing angle, in the step S4, it is determined that the target to be tracked is manually tracked, the tracking target is manually determined according to the requirement, then virtual marking is performed on the determined tracking target, in the step S5, the position data includes the current moving direction of the target to be tracked, the step S is ignored, after the moving speed of the moving target is calculated, the moving speed is controlled, the moving information is consistently is calculated, and the moving information is kept in the moving direction is similar to the moving information, when the moving information is calculated, and the moving information is kept, and is the moving in the moving information is the moving information, when the data information after arrangement is inconsistent with the initial data information, comparison is continued, and when the data information is still inconsistent with the initial data information, the user is required to be reminded in time through voice broadcasting.
Example 3
Referring to fig. 1-4, the embodiment provides a multi-target tracking method in a complex environment, which includes the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: the target position to be tracked is marked, and then similarity between color information in the pixel area and the tracked object is evaluated, so that tracking of the target to be tracked is completed.
In this embodiment, in the step S1, the number of detected moving objects is set to 5, and it is required to ensure that the number of frames in the video stream remains stable, by using a foreground detection method, it is determined whether a moving object is detected from the video stream captured within a preset time, the video stream includes each video image, in the step S2, the interval time is set to 3S, analysis processing is performed on first position data, then analysis processing is performed on second position data, the analyzed data is recorded, in the step S2, the number of the first position data and the second position data are both 5, the average value is taken after the data processing, in the step S3, the position of the adjusted capturing device is located in an optimal capturing range, when no crowd to be captured is detected within a certain time, the capturing range of the capturing device is adjusted according to a preset capturing angle, in the step S4, it is determined that the target to be tracked is manually tracked, the target is manually determined according to the requirement, then a specific virtual mark is used to perform virtual mark on the determined tracking target, in the step S5, the position data includes the current moving speed of the target to be tracked, the step S is calculated, after the moving speed of the moving target is calculated, and the moving speed of the moving target is consistently is calculated, and the moving speed is calculated, and the moving information is consistently equal to the moving information is calculated, when the moving information is calculated, and the moving information is 6, when the data information after arrangement is inconsistent with the initial data information, comparison is continued, and when the data information is still inconsistent with the initial data information, the user is required to be reminded in time through voice broadcasting.
Example 4
Referring to fig. 1-4, the embodiment provides a multi-target tracking method in a complex environment, which includes the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: the target position to be tracked is marked, and then similarity between color information in the pixel area and the tracked object is evaluated, so that tracking of the target to be tracked is completed.
In this embodiment, in the step S1, the number of detected moving objects is set to 6, and it is required to ensure that the number of frames in the video stream remains stable, by using a foreground detection method, it is determined whether a moving object is detected from the video stream captured within a preset time, the video stream includes each video image, in the step S2, the interval time is set to 4S, analysis processing is performed on first position data, then analysis processing is performed on second position data, the analyzed data is recorded, in the step S2, the number of the first position data and the second position data are both 6, the average value is taken after the data processing, in the step S3, the position of the adjusted capturing device is located in an optimal capturing range, when no crowd to be captured is detected within a certain time, the capturing range of the capturing device is adjusted according to a preset capturing angle, in the step S4, it is determined that the target to be tracked is manually tracked, the tracking target is manually determined according to the requirement, then virtual marking is performed on the determined tracking target, in the step S5, the position data includes the current moving direction of the target to be tracked, the moving speed is controlled, the moving speed is equal to the current moving speed is equal to the moving speed of the target, and the moving speed is equal to the calculated after the moving speed is equal to the moving speed of the moving target in the step S6, when the moving speed is equal to the moving speed is calculated, and the initial information is calculated, and when the moving speed is equal to the moving speed, when the data information after arrangement is inconsistent with the initial data information, comparison is continued, and when the data information is still inconsistent with the initial data information, the user is required to be reminded in time through voice broadcasting.
Example 5
Referring to fig. 1-4, the embodiment provides a multi-target tracking method in a complex environment, which includes the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after a certain time, and calculating through the second position data and the first position data to obtain an optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: determining a target to be tracked according to the acquired image information after detecting the moving target in the step S1;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: the target position to be tracked is marked, and then similarity between color information in the pixel area and the tracked object is evaluated, so that tracking of the target to be tracked is completed.
In this embodiment, in the step S1, the number of detected moving objects is set to 7, and it is required to ensure that the number of frames in the video stream remains stable, by using a foreground detection method, it is determined whether a moving object is detected from the video stream captured within a preset time, the video stream includes each video image, in the step S2, the interval time is set to 5S, analysis processing is performed on first position data, then analysis processing is performed on second position data, the analyzed data is recorded, in the step S2, the number of the first position data and the second position data are both 7, the average value is taken after the data processing, in the step S3, the position of the adjusted capturing device is located in an optimal capturing range, when no crowd to be captured is detected within a certain time, the capturing range of the capturing device is adjusted according to a preset capturing angle, in the step S4, it is determined that the target to be tracked is manually tracked, the target is manually determined according to the requirement, then a specific virtual mark is used to perform virtual mark on the determined tracking target, in the step S5, the position data includes the current moving speed of the target to be tracked, the current moving speed of the target is calculated, the moving speed of the moving target is calculated, and the moving speed of the moving target is calculated after the moving speed is calculated, and the moving speed of the moving target is calculated, and the moving speed is calculated and the moving information is consistently is equal to the moving speed of the moving object is calculated, when the moving information is calculated, and the moving information is 6, when the data information after arrangement is inconsistent with the initial data information, comparison is continued, and when the data information is still inconsistent with the initial data information, the user is required to be reminded in time through voice broadcasting.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (8)
1. The multi-target tracking method in the complex environment is characterized by comprising the following steps:
s1: preparing for shooting: the shooting equipment is placed stably, the shooting equipment is aimed at a crowd needing shooting, the stability of the shooting equipment is guaranteed, and then a moving target is detected from a shot video stream;
s2: pre-shooting test: acquiring first position data of a shooting crowd, acquiring second position data of the shooting crowd after an interval time within a range of 1-5s, and respectively acquiring average values of the first position data and the second position data according to the number of the first position data and the second position data so as to obtain an optimal shooting range, wherein the coordinate change from the average value of the first position data to the average value of the second position data is the optimal shooting range;
s3: adjusting the distance: according to the result obtained in S2, adjusting the position of the photographing apparatus when the optimal photographing distance is not within the range of the photographing apparatus;
s4: determining a tracking target: after the moving target is detected in the step S1, determining a target to be tracked according to the acquired image information;
s5: and (3) calculating: extracting images of adjacent frames of a target to be tracked, then calculating position data of the target to be tracked according to comparison of the images of the continuous adjacent frames, and marking the position of the target to be tracked;
s6: automatic tracking: marking the target position to be tracked, and evaluating the similarity between the color information in the pixel area and the tracked object to finish the tracking of the target to be tracked;
in the step S1, the number of detected moving objects is set to 3-7, and it is required to ensure that the number of frames in the video stream remains stable, and by using the foreground detection method, it is determined whether the moving objects are detected from the captured video stream within a preset time, where the video stream includes each video image.
2. The multi-target tracking method in a complex environment according to claim 1, wherein in S2, the first location data is analyzed and processed, then the second location data is analyzed and processed, and the analyzed and processed data is recorded.
3. The method for multi-target tracking in a complex environment according to claim 1, wherein in S2, the number of the first position data and the second position data is 3-7.
4. The method for multi-target tracking in a complex environment according to claim 1, wherein in S4, the determined tracking target is virtually marked using a virtual mark.
5. The method according to claim 1, wherein in S5, the position data includes a current moving speed, a moving distance, and a moving direction to be tracked.
6. The method for multi-target tracking in a complex environment according to claim 1, wherein in S5, the moving speed, moving distance and moving direction of the target to be tracked are conveniently calculated by marking the position of the target to be tracked, and the data is automatically stored after the calculation is finished.
7. The multi-target tracking method in a complex environment according to claim 1, wherein in S6, the shooting device is controlled to automatically track the target to be tracked.
8. The multi-target tracking method according to claim 1, wherein in S6, the data information after evaluating the similarity between the color information in the pixel area and the tracking object is sorted, when the sorted data information is always consistent with the initial data information, the sorted data is ignored, when the sorted data information is inconsistent with the initial data information, the comparison is continued, and when the sorted data information is still inconsistent with the initial data information, the user is reminded of timely voice broadcasting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910034595.5A CN109886995B (en) | 2019-01-15 | 2019-01-15 | Multi-target tracking method in complex environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910034595.5A CN109886995B (en) | 2019-01-15 | 2019-01-15 | Multi-target tracking method in complex environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109886995A CN109886995A (en) | 2019-06-14 |
| CN109886995B true CN109886995B (en) | 2023-05-23 |
Family
ID=66926121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910034595.5A Active CN109886995B (en) | 2019-01-15 | 2019-01-15 | Multi-target tracking method in complex environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886995B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580710A (en) * | 2019-08-21 | 2019-12-17 | 深圳码隆科技有限公司 | object tracking method, device, computer readable storage medium and computer equipment |
| CN111787379B (en) * | 2020-07-06 | 2022-06-14 | 海信视像科技股份有限公司 | Interactive method for generating video collection file, display device and intelligent terminal |
| CN112232257B (en) * | 2020-10-26 | 2023-08-11 | 青岛海信网络科技股份有限公司 | Traffic abnormality determination method, device, equipment and medium |
| CN112307936A (en) * | 2020-10-28 | 2021-02-02 | 江苏云从曦和人工智能有限公司 | Passenger flow volume analysis method, system and device based on head and shoulder detection |
| CN113115000B (en) * | 2021-04-12 | 2022-06-17 | 浙江商汤科技开发有限公司 | Map generation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2896731Y (en) * | 2006-03-20 | 2007-05-02 | 江军 | Synchronous pick-up tracing system |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| WO2012151777A1 (en) * | 2011-05-09 | 2012-11-15 | 上海芯启电子科技有限公司 | Multi-target tracking close-up shooting video monitoring system |
| CN104835182A (en) * | 2015-06-03 | 2015-08-12 | 上海建炜信息技术有限公司 | Method for realizing dynamic object real-time tracking by using camera |
| WO2018228410A1 (en) * | 2017-06-16 | 2018-12-20 | 杭州海康威视数字技术股份有限公司 | Target object capturing method and device, and video monitoring device |
-
2019
- 2019-01-15 CN CN201910034595.5A patent/CN109886995B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2896731Y (en) * | 2006-03-20 | 2007-05-02 | 江军 | Synchronous pick-up tracing system |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| WO2012151777A1 (en) * | 2011-05-09 | 2012-11-15 | 上海芯启电子科技有限公司 | Multi-target tracking close-up shooting video monitoring system |
| CN104835182A (en) * | 2015-06-03 | 2015-08-12 | 上海建炜信息技术有限公司 | Method for realizing dynamic object real-time tracking by using camera |
| WO2018228410A1 (en) * | 2017-06-16 | 2018-12-20 | 杭州海康威视数字技术股份有限公司 | Target object capturing method and device, and video monitoring device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109886995A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886995B (en) | Multi-target tracking method in complex environment | |
| JP4616702B2 (en) | Image processing | |
| CN103988227B (en) | The method and apparatus locked for image capturing target | |
| US9767568B2 (en) | Image processor, image processing method, and computer program | |
| KR101237673B1 (en) | A method in relation to acquiring digital images | |
| US10515471B2 (en) | Apparatus and method for generating best-view image centered on object of interest in multiple camera images | |
| CN106375706B (en) | method and device for measuring speed of moving object by using double cameras and mobile terminal | |
| CN107438173A (en) | Video process apparatus, method for processing video frequency and storage medium | |
| JP2008501172A (en) | Image comparison method | |
| JP2007129480A (en) | Imaging device | |
| CN110264493A (en) | A kind of multiple target object tracking method and device under motion state | |
| CN106331462A (en) | Method and device for shooting track pictures, as well as mobile terminal | |
| CN106713740B (en) | Positioning tracking camera shooting method and system | |
| JP2011234314A (en) | Image processing apparatus, image processing method and program | |
| US10574904B2 (en) | Imaging method and electronic device thereof | |
| CN112995507A (en) | Method and device for prompting object position | |
| KR101468347B1 (en) | Method and arrangement for identifying virtual visual information in images | |
| CN114270802A (en) | Information processing apparatus, information processing method, and program | |
| CN114040107B (en) | Intelligent automobile image shooting system, intelligent automobile image shooting method, intelligent automobile image shooting vehicle and intelligent automobile image shooting medium | |
| WO2019137186A1 (en) | Food identification method and apparatus, storage medium and computer device | |
| US11875080B2 (en) | Object sharing method and apparatus | |
| JP6548306B2 (en) | Image analysis apparatus, program and method for tracking a person appearing in a captured image of a camera | |
| CN112766033B (en) | Method for estimating common attention targets of downlinks in scene based on multi-view camera | |
| JP2022101519A (en) | Method of creating hyperspectral high speed camera image using generative adversarial network algorithm | |
| CN114697528A (en) | Image processor, electronic device and focusing control method |
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 |