CN116958142A - Target detection and tracking method based on compound eye event imaging and high-speed turntable - Google Patents
Target detection and tracking method based on compound eye event imaging and high-speed turntable Download PDFInfo
- Publication number
- CN116958142A CN116958142A CN202311212424.XA CN202311212424A CN116958142A CN 116958142 A CN116958142 A CN 116958142A CN 202311212424 A CN202311212424 A CN 202311212424A CN 116958142 A CN116958142 A CN 116958142A
- Authority
- CN
- China
- Prior art keywords
- target
- coordinate system
- tracking
- turntable
- compound eye
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 150000001875 compounds Chemical class 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000003384 imaging method Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000000694 effects Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/60—Rotation of a whole image or part thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
Abstract
The invention discloses a target detection and tracking method based on compound eye event imaging and a high-speed turntable, wherein the method comprises the steps of calibrating a compound eye event camera, a common camera and a two-dimensional turntable, and defining a plurality of coordinate systems; setting a time threshold, and receiving an event stream once at intervals by an event processing module and performing noise reduction processing; detecting a target by a target detection algorithm; the target tracking algorithm tracks the detected target. The method solves the problems of small field of view, low resolution, poor robustness, high bandwidth, large calculated amount and the like of the existing method, and realizes the detection and tracking of a plurality of special targets in specific scenes under a large field of view.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a target detection and tracking method based on compound eye event imaging and a high-speed turntable.
Background
Object tracking is an important technology in the field of computer vision, and its main purpose is to track the position and trajectory of an object in video, and object tracking technology has been widely used in many fields.
Most of the current target tracking methods use single or multiple traditional cameras for observation and another camera for tracking. However, conventional cameras may create motion blur when capturing high-speed objects, resulting in detection and tracking failures. Although a plurality of common cameras can solve the problem of motion blur caused by target high-speed movement to a certain extent, the bandwidth is increased along with the increase of the cameras, and the calculated amount and the calculated time are greatly increased. When no target moves, the common camera still can shoot continuously, so that the waste of calculation and storage resources is caused.
Event cameras, also known as dynamic vision sensors. Unlike conventional cameras, event cameras output not images, but rather asynchronous event streams according to brightness variations of individual pixels. Therefore, the event camera has the advantages of high dynamic range, high time resolution and the like, and has better detection and tracking effects when the target moves at a high speed. However, the field of view and resolution of a single event camera are limited, and it is difficult to detect and track a target with a large field of view.
Disclosure of Invention
In order to solve the problems, the invention provides a target detection and tracking method based on compound eye event imaging and a high-speed turntable.
The invention provides a target detection and tracking method based on compound eye event imaging and a high-speed turntable, which comprises the following steps:
calibrating a compound eye event camera, a common camera and a two-dimensional turntable, and defining a world coordinate system, a two-dimensional turntable initial coordinate system, a two-dimensional turntable coordinate system, a camera coordinate system, an image physical coordinate system and an image pixel coordinate system.
Step two, setting a time threshold valueEvent processing Module every ∈>And receiving the event stream of the compound eye event camera in the time period once and carrying out noise reduction processing.
Step three, the target detection and tracking module detects whether the noise-reduced event stream has a target or not, if the target can be detected currently, the target tracking module updates the target centroid coordinates according to the predicted value and the current observed value obtained by the Kalman filtering algorithm at the previous moment, and returns to the target centroidCalculating azimuth angle and pitch angle of target in world coordinate system according to target centroid>And->The method comprises the steps of carrying out a first treatment on the surface of the If the target cannot be detected currently, judging whether the current tracker is tracking the target, if the tracker is tracking the target, calculating the time difference t between the current moment and the last detected target, wherein the following cases exist:
and->At this time, the target is considered to be blocked, and when the target is blocked, every +.>Time predicts the position of the target at this time using kalman filtering.
At the moment, the target is considered to be lost or tracking is finished, the target motion track is returned, and the tracker is emptied.
And step four, acquiring the current state of the turntable through the theodolite, calculating the angle of the turntable to be changed according to the azimuth angle and the pitch angle of the target returned in the step three, and sending a signal to the control module.
And fifthly, the control module controls the turntable according to the received signal to enable the target to be at the center of the camera.
The world coordinate system, the two-dimensional turntable initial coordinate system, the two-dimensional turntable coordinate system and the camera coordinate system in the step one are respectively、/>The method comprises the steps of carrying out a first treatment on the surface of the The physical coordinate system of the image and the pixel coordinate system of the image are respectively +.>。
Preferably, the centroid in the third stepIs the coordinates of the object in the camera coordinate system, wherein +.>For depth information, i.e. the distance of the object from the compound eye event camera, the coordinates of the object in the camera coordinate system are converted into itCoordinates in the world coordinate System>And returns:
wherein t represents the translation between the two,the translational components along the X, Y, Z axis in three directions, respectively, R representing the rotation matrix between the two:
wherein, the liquid crystal display device comprises a liquid crystal display device,the camera coordinate systems are respectively around->Is provided.
Preferably, in the third step, the azimuth angle and the pitch angle of the target in the world coordinate system are calculated according to the mass center of the targetAnd->：
In the third step, the coordinates of the mass center of the target are updated according to a Kalman filtering algorithm; let the state of the target be X:
wherein the method comprises the steps ofRespectively representing the change rate of the variable, wherein x, y and z are the coordinates of the current target in the world coordinate system, < + >>And->Is the current azimuth and pitch of the target.
Preferably, in the third step, when no target is detected at time k, the tracker is tracking the target, and the time difference between the current time and the last detected target is the sameAt this time, the target is considered to be shielded for a long time, and the predicted value obtained according to Kalman filtering at the previous time is recorded as the observed value at the current time: />
Wherein the method comprises the steps ofFor the predicted value of the current target state +.>For state transition matrix>For controlling the matrix +.>For external effects on the system->Is a prediction noise covariance matrix. At this time, the barycenter coordinate of the target is updated to be the predicted value of the last momentReturning to the target centroid.
Preferably, the step threeWhen the target can be detected, the Kalman filtering algorithm is used for updating the barycenter coordinates of the target, and the Kalman filtering is divided into two steps: predicting and updating; at the moment, updating the coordinates of the mass center of the target according to the predicted value and the current observed value obtained at the previous moment:
wherein K is Kalman gain, R is measurement noise covariance matrix, H is observation matrix, Z is observation value; at this time, the coordinates of the mass center of the target are updated to be the newly obtained X, and the mass center of the target is returned.
The invention has the advantages that:
calibrating a compound eye event camera, a common camera and a two-dimensional turntable, and defining a plurality of coordinate systems; setting a time threshold, and receiving an event stream once at intervals by an event processing module and performing noise reduction processing; detecting a target by a target detection algorithm; the target tracking algorithm tracks the detected target. The method solves the problems of small field of view, low resolution, poor robustness, high bandwidth, large calculated amount and the like of the existing method, and realizes the detection and tracking of a plurality of special targets in specific scenes under a large field of view.
Drawings
Fig. 1 is a schematic view of a two-dimensional turret structure according to the invention.
Fig. 2 is a schematic diagram of the various coordinate systems of the present invention.
Fig. 3 is a schematic view of the pitch angle of the present invention.
FIG. 4 is a flow chart of the object tracking of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1-4, the invention provides a target detection and tracking method based on compound eye event imaging and a high-speed turntable, which comprises the following steps:
calibrating a compound eye event camera, a common camera and a two-dimensional turntable, and defining a world coordinate system, a two-dimensional turntable initial coordinate system, a two-dimensional turntable coordinate system, a camera coordinate system, an image physical coordinate system and an image pixel coordinate system.
Step two, setting a time threshold valueEvent processing Module every ∈>And receiving the event stream of the compound eye event camera in the time period once and carrying out noise reduction processing.
Step three, the target detection and tracking module detects whether the noise-reduced event stream has a target or not, if the target can be detected currently, the target tracking module updates the target centroid coordinates according to the predicted value and the current observed value obtained by the Kalman filtering algorithm at the previous moment, and returns to the target centroidCalculating azimuth angle and pitch angle of target in world coordinate system according to target centroid>And->. If the target cannot be detected currently, judging whether the current tracker is tracking the target, if the tracker is tracking the target, calculating the time difference t between the current moment and the last detected target, wherein the following cases exist:
and->At this time, the target is considered to be blocked, and when the target is blocked, every other/>Time predicts the position of the target at this time using kalman filtering.
At the moment, the target is considered to be lost or tracking is finished, the target motion track is returned, and the tracker is emptied.
And step four, acquiring the current state of the turntable through the theodolite, calculating the angle of the turntable to be changed according to the azimuth angle and the pitch angle of the target returned in the step three, and sending a signal to the control module.
And fifthly, the control module controls the turntable according to the received signal to enable the target to be at the center of the camera.
The world coordinate system, the two-dimensional turntable initial coordinate system, the two-dimensional turntable coordinate system and the camera coordinate system in the first step are respectively shown in FIG. 2、/>. The physical coordinate system of the image and the pixel coordinate system of the image are respectively +.>。
The mass center in the third stepIs the coordinates of the object in the camera coordinate system, wherein +.>For depth information, i.e. the distance of the object to the compound eye event camera, the coordinates of the object in the camera coordinate system are converted into their coordinates in the world coordinate system +.>And returns:
wherein t represents the translation between the two,the translational components along the X, Y, Z axis in three directions, respectively, R representing the rotation matrix between the two:
wherein, the liquid crystal display device comprises a liquid crystal display device,the camera coordinate systems are respectively around->Is provided.
In the third step, the azimuth angle and the pitch angle of the target under the world coordinate system are calculated according to the mass center of the targetAnd：
and in the third step, the coordinates of the mass center of the target are updated according to a Kalman filtering algorithm. Let the state of the target be X:
wherein the method comprises the steps ofRespectively representing the change rate of the variable, wherein x, y and z are the coordinates of the current target in the world coordinate system, < + >>And->Is the current azimuth and pitch of the target.
In the third step, when the target cannot be detected at the time k, the tracker is tracking the target, and the time difference between the current time and the last detected targetAt this time, the target is considered to be shielded for a long time, and the predicted value obtained according to Kalman filtering at the previous time is recorded as the observed value at the current time:
wherein the method comprises the steps ofFor the predicted value of the current target state +.>For state transition matrix>For controlling the matrix +.>For external effects on the system->Is a prediction noise covariance matrix. At this time, the barycenter coordinate of the target is updated to be the predicted value of the last momentReturning to the target centroid.
In the third step, when the target can be detected, the Kalman filtering algorithm is used for updating the barycenter coordinates of the target, and the Kalman filtering is divided into two steps: prediction and updating. At the moment, updating the coordinates of the mass center of the target according to the predicted value and the current observed value obtained at the previous moment:
where K is the kalman gain, R is the measurement noise covariance matrix, H is the observation matrix, and Z is the observation value. At this time, the coordinates of the mass center of the target are updated to be the newly obtained X, and the mass center of the target is returned.
Although the invention has been disclosed in detail with reference to the accompanying drawings, it is to be understood that such description is merely illustrative and is not intended to limit the application of the invention. The scope of the invention is defined by the appended claims and may include various modifications, alterations and equivalents of the invention without departing from the scope and spirit of the invention.
Claims (6)
1. The target detection and tracking method based on compound eye event imaging and high-speed turntable is characterized by comprising the following steps of:
calibrating a compound eye event camera, a common camera and a two-dimensional turntable, and defining a world coordinate system, a two-dimensional turntable initial coordinate system, a two-dimensional turntable coordinate system, a camera coordinate system, an image physical coordinate system and an image pixel coordinate system;
step two, setting a time threshold valueEvent processing Module every ∈>Receiving an event stream of a compound eye event camera in the time period and carrying out noise reduction treatment;
step three, the target detection and tracking module detects whether the noise-reduced event stream has a target or not, if the target can be detected currently, the target tracking module updates the target centroid coordinates according to the predicted value and the current observed value obtained by the Kalman filtering algorithm at the previous moment, and returns to the target centroidCalculating azimuth angle of target in world coordinate system according to target centroid>And pitch angle->；
If the target cannot be detected currently, judging whether the current tracker is tracking the target, if the tracker is tracking the target, calculating the time difference t between the current moment and the last detected target, wherein the following cases exist:
and->At this time, the target is considered to be blocked, and when the target is blocked, every +.>Predicting the position of the target at the moment by using Kalman filtering;
at the moment, the target is considered to be lost or tracking is finished, and the target motion track is returned and the tracker is emptied;
step four, acquiring the current state of the turntable through a theodolite, calculating the angle of the turntable to be changed according to the azimuth angle and the pitch angle of the target returned in the step three, and sending a signal to a control module;
and fifthly, the control module controls the turntable according to the received signal to enable the target to be at the center of the camera.
2. The compound eye event imaging and high speed turntable based target detection and tracking method according to claim 1, wherein,
the world coordinate system, the two-dimensional turntable initial coordinate system, the two-dimensional turntable coordinate system and the camera coordinate system in the step one are respectively、/>The method comprises the steps of carrying out a first treatment on the surface of the The physical coordinate system of the image and the pixel coordinate system of the image are respectively +.>。
3. The compound eye event imaging and high speed turntable based target detection and tracking method according to claim 2, wherein,
the mass center in the third stepIs the coordinates of the object in the camera coordinate system, wherein +.>For depth information, i.e. the distance of the object to the compound eye event camera, the coordinates of the object in the camera coordinate system are converted into their coordinates in the world coordinate system +.>And returns:
wherein t represents a translation between the two, < >>The translational components along the X, Y, Z axis in three directions, respectively, R representing the rotation matrix between the two:
wherein->The camera coordinate systems are respectively around->Is provided.
4. The method for detecting and tracking a target based on compound eye event imaging and high-speed turntable according to claim 3, wherein,
in the third step, the coordinates of the mass center of the target are updated according to a Kalman filtering algorithm; let the state of the target be X:
wherein->Respectively representing the change rate of the variable, wherein x, y and z are the coordinates of the current target in the world coordinate system, and in the third step, the azimuth angle +/of the target in the world coordinate system is calculated according to the mass center of the target>And pitch angle->：
。
5. The compound eye event imaging and high speed turntable based target detection and tracking method according to claim 4, wherein,
in the third step, when the target cannot be detected at the time k, the tracker is tracking the target, and the time difference between the current time and the last detected targetAt this time, the target is considered to be shielded for a long time, and the predicted value obtained according to Kalman filtering at the previous time is recorded as the observed value at the current time:
wherein->For the predicted value of the current target state +.>For state transition matrix>For controlling the matrix +.>For external effects on the system->In order to predict the noise covariance matrix, the target centroid coordinates are updated to be the predicted value +.>Returning to the target centroid.
6. The compound eye event imaging and high speed turntable based target detection and tracking method according to claim 5, wherein,
in the third step, when the target can be detected, the Kalman filtering algorithm is used for updating the barycenter coordinates of the target, and the Kalman filtering is divided into two steps: predicting and updating; at the moment, updating the coordinates of the mass center of the target according to the predicted value and the current observed value obtained at the previous moment:
wherein K is Kalman gain, R is measurement noise covariance matrix, H is observation matrix, Z is observation value; at this time, the coordinates of the mass center of the target are updated to be the newly obtained X, and the mass center of the target is returned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311212424.XA CN116958142B (en) | 2023-09-20 | 2023-09-20 | Target detection and tracking method based on compound eye event imaging and high-speed turntable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311212424.XA CN116958142B (en) | 2023-09-20 | 2023-09-20 | Target detection and tracking method based on compound eye event imaging and high-speed turntable |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116958142A true CN116958142A (en) | 2023-10-27 |
| CN116958142B CN116958142B (en) | 2023-12-15 |
Family
ID=88462474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311212424.XA Active CN116958142B (en) | 2023-09-20 | 2023-09-20 | Target detection and tracking method based on compound eye event imaging and high-speed turntable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958142B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160110773A (en) * | 2015-03-12 | 2016-09-22 | 숙명여자대학교산학협력단 | Method and apparatus for tracking moving object by using kalman filter |
| US10345447B1 (en) * | 2018-06-27 | 2019-07-09 | Luminar Technologies, Inc. | Dynamic vision sensor to direct lidar scanning |
| CN112800860A (en) * | 2021-01-08 | 2021-05-14 | 中电海康集团有限公司 | Event camera and visual camera cooperative high-speed scattered object detection method and system |
| CN113888607A (en) * | 2021-09-02 | 2022-01-04 | 中国电子科技南湖研究院 | Target detection and tracking method and system based on event camera and storage medium |
| WO2022106233A1 (en) * | 2020-11-19 | 2022-05-27 | Sony Group Corporation | Tracking camera, tracking camera systems, and operation thereof |
| CN115035470A (en) * | 2022-06-08 | 2022-09-09 | 中国电子科技南湖研究院 | Low, small and slow target identification and positioning method and system based on mixed vision |
| CN116363163A (en) * | 2023-03-07 | 2023-06-30 | 华中科技大学 | Space target detection tracking method, system and storage medium based on event camera |
| CN116402852A (en) * | 2023-03-24 | 2023-07-07 | 西安电子科技大学广州研究院 | Dynamic high-speed target tracking method and device based on event camera |
-
2023
- 2023-09-20 CN CN202311212424.XA patent/CN116958142B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160110773A (en) * | 2015-03-12 | 2016-09-22 | 숙명여자대학교산학협력단 | Method and apparatus for tracking moving object by using kalman filter |
| US10345447B1 (en) * | 2018-06-27 | 2019-07-09 | Luminar Technologies, Inc. | Dynamic vision sensor to direct lidar scanning |
| WO2022106233A1 (en) * | 2020-11-19 | 2022-05-27 | Sony Group Corporation | Tracking camera, tracking camera systems, and operation thereof |
| CN112800860A (en) * | 2021-01-08 | 2021-05-14 | 中电海康集团有限公司 | Event camera and visual camera cooperative high-speed scattered object detection method and system |
| CN113888607A (en) * | 2021-09-02 | 2022-01-04 | 中国电子科技南湖研究院 | Target detection and tracking method and system based on event camera and storage medium |
| CN115035470A (en) * | 2022-06-08 | 2022-09-09 | 中国电子科技南湖研究院 | Low, small and slow target identification and positioning method and system based on mixed vision |
| CN116363163A (en) * | 2023-03-07 | 2023-06-30 | 华中科技大学 | Space target detection tracking method, system and storage medium based on event camera |
| CN116402852A (en) * | 2023-03-24 | 2023-07-07 | 西安电子科技大学广州研究院 | Dynamic high-speed target tracking method and device based on event camera |
Non-Patent Citations (4)
| Title |
|---|
| GUILLERMO GALLEGO, ET AL.: "Event-based Camera Pose Tracking using a Generative Event Model", ARXIV:1510.01972V1, pages 1 - 7 * |
| 祝朝政;何明;杨晟;吴春晓;刘斌;: "单目视觉里程计研究综述", 计算机工程与应用, no. 07, pages 25 - 33 * |
| 粟傈 等: "基于事件相机的机器人感知与控制综述", 自动化学报, vol. 50, no. 10, pages 1869 - 1889 * |
| 郭文强;高晓光;侯勇严;: "基于卡尔曼预测算法的云台三维空间目标跟踪", 陕西科技大学学报, no. 03, pages 92 - 95 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116958142B (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872341B (en) | High-altitude parabolic detection method and system based on computer vision | |
| CN108521554B (en) | Large-scene multi-target cooperative tracking method, intelligent monitoring system and traffic system | |
| US8803978B2 (en) | Computer vision-based object tracking system | |
| CN113286194A (en) | Video processing method and device, electronic equipment and readable storage medium | |
| US20180249090A1 (en) | Image processing apparatus, solid-state imaging device, and electronic apparatus | |
| KR20080072826A (en) | Robust online face tracking | |
| CN112991391A (en) | Vehicle detection and tracking method based on radar signal and vision fusion | |
| US20210185231A1 (en) | Image stabilization apparatus, method of controlling same, and storage medium | |
| CN110555868A (en) | method for detecting small moving target under complex ground background | |
| WO2020014864A1 (en) | Pose determination method and device, and computer readable storage medium | |
| CN110827321A (en) | Multi-camera cooperative active target tracking method based on three-dimensional information | |
| CN116030099A (en) | PTZ camera-based multi-target tracking method and device | |
| Chan et al. | On the hardware/software design and implementation of a high definition multiview video surveillance system | |
| JP2002374521A (en) | Method and device for monitoring mobile object | |
| Mao et al. | Automated multiple target detection and tracking in UAV videos | |
| CN116958142B (en) | Target detection and tracking method based on compound eye event imaging and high-speed turntable | |
| CN110647173B (en) | Video tracking system and method | |
| CN114095780A (en) | Panoramic video editing method, device, storage medium and equipment | |
| JPH04345396A (en) | Traveling object tracing method | |
| CN113554552A (en) | Micro-scanning super-resolution method for infrared point target detection | |
| CN114359338A (en) | Pose estimation method and device, terminal equipment and computer readable storage medium | |
| US10708501B2 (en) | Prominent region detection in scenes from sequence of image frames | |
| JP2000011134A (en) | Device and method for detecting moving amount | |
| Zhu et al. | Surf points based moving target detection and long-term tracking in aerial videos | |
| KR101070448B1 (en) | The method for tracking object and the apparatus thereof |
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 |