CN111369586A - Video image correction method, device, equipment and readable storage medium - Google Patents
Video image correction method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111369586A CN111369586A CN201811605189.1A CN201811605189A CN111369586A CN 111369586 A CN111369586 A CN 111369586A CN 201811605189 A CN201811605189 A CN 201811605189A CN 111369586 A CN111369586 A CN 111369586A
- Authority
- CN
- China
- Prior art keywords
- target
- tracking
- image frame
- detection
- frame
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
-
- 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
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The text discloses a video image correction method, a device, equipment and a readable storage medium, belonging to the technical field of image processing, wherein the method comprises the following steps: acquiring a moving target from a video image as a detection target; tracking the detection target to acquire the position of the detection target in a tracking image frame; acquiring the position of the detection target in a detection image frame in a frame extraction mode; correcting the target position in the tracking image frame by the target position in the detection image frame; the target position is corrected in time in combination with target detection in the tracking process, the accuracy of tracking the moving target in the monitoring video is improved, and the problem of increased deviation between the tracking target position and the target actual position caused by the imperfection of a tracking algorithm is solved.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for correcting a video image.
Background
Visual sensors are widely adopted to monitor scenes in the field of safety precaution, but most of scene monitoring systems based on the visual sensors still stay in a semi-manual simulation monitoring stage. The weak automatic processing capability of the surveillance video is a bottleneck restricting further development of video surveillance application, the data sharing capability is limited due to the lack of efficient and accurate video retrieval means, the video surveillance system is difficult to realize resource integration and interoperation with a public security information system, a contradiction exists between data compression and detail retention of the video surveillance system, the application of video surveillance lacks uniform standards and specifications, an intelligent visual surveillance system is urgently required to be developed, and a detection and tracking algorithm of a moving target is a fundamental problem and a key difficult problem of intelligent visual surveillance.
The moving object detection algorithm is the most basic and important part in video intelligent analysis, and mainly refers to a technology for automatically detecting a continuous moving object in a video frame sequence from a background by defining a corresponding mathematical model and a segmentation algorithm, and target tracking is to process the same target track on the basis of target detection. In the prior art, the main mode for processing a video image is target detection and target tracking, wherein a target T is detected in a certain video frame F, the target T is tracked through a tracking algorithm until the target tracking is finished (a video monitoring picture is taken out), and finally, a picture of the target T is output. In recent years, target detection and tracking algorithms are developed more and more mature, indexes such as accuracy are greatly improved compared with the prior art, but the problems of target detection errors, target tracking position inaccuracy and the like still exist in a video monitoring scene, on one hand, the accuracy of the algorithm cannot reach 100%, on the other hand, various algorithms are different in different scenes, and therefore the analyzed target picture is not the best in comprehensive effect.
Disclosure of Invention
The invention provides a video image correction method, a video image correction device and a readable storage medium, wherein the target position is corrected in time in combination with target detection in the tracking process, the accuracy of tracking a moving target in a monitoring video is improved, and the problem of increased deviation between the tracking target position and the target actual position caused by the imperfection of a tracking algorithm is solved.
The technical scheme adopted for solving the technical problems is as follows:
according to an aspect herein, there is provided a video image correction method, including:
acquiring a moving target from a video image as a detection target;
tracking the detection target to acquire the position of the detection target in a tracking image frame;
acquiring the position of the detection target in a detection image frame in a frame extraction mode;
correcting the target position in the tracking image frame by the target position in the detection image frame.
Optionally, the correcting the target position in the tracking image frame by the target position in the detection image frame comprises:
judging whether a detection target in the detection image frame and a tracking target in the tracking image frame are the same target or not through image recognition;
and if so, replacing the tracking image frame with the detection image frame, and continuing tracking by taking a detection target in the detection image frame as a tracking target, otherwise, ending the tracking process.
Optionally, the determining, by image recognition, whether the detection target in the detection image frame and the tracking target in the tracking image frame are the same target specifically includes:
calculating the coverage rate of the detection image frame and the tracking image frame;
judging whether the coverage rate is greater than or equal to a preset coverage rate threshold value, if so, enabling the detection target and the tracking target to be the same target; otherwise, the detection target and the tracking target are different targets.
Optionally, the calculation formula of the coverage rate is:
o＝Area(A′∩Ak)/Area(A′∪Ak)
wherein o is the coverage, A' is the detected image frame, AkTo detect image frames, Area (A' ∩ A)k) To detect the Area of intersection of an image frame with a tracked image frame, Area (A' ∪ A)k) The area of the union of the detected image frame and the tracked image frame is determined.
Optionally, the determining, by image recognition, whether the detection target in the detection image frame and the tracking target in the tracking image frame are the same target specifically includes:
calculating a similarity value of the detection image frame and the tracking image frame;
judging whether the similarity value is greater than or equal to a preset similarity threshold value, if so, enabling the detection target and the tracking target to be the same target; otherwise, the detection target and the tracking target are different targets.
Optionally, the similarity value is calculated by the following formula:
d＝∑B′Bk/sqrt(∑B′+∑Bk)
wherein d is the cosine distance between the detected image frame and the tracking image frame, B' is the detected image frame, BkTo detect image frames.
Optionally, the moving object comprises: a target face, a target figure, and a target vehicle.
According to another aspect of the present disclosure, there is provided a video image correction apparatus including:
the target detection module is used for acquiring a moving target from the video image as a detection target; the system is also used for acquiring the position of the detection target in a detection image frame in a frame extraction mode;
the target tracking module is used for tracking the detection target and acquiring the position of the detection target in a tracking image frame;
and the identification correction module is used for correcting the target position in the tracking image frame through the target position in the detection image frame.
According to yet another aspect herein, there is provided an electronic device comprising a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application configured to perform the video image correction method described above.
According to still another aspect herein, there is provided a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the video image correction method described above.
The invention discloses a video image correction method, a device, equipment and a readable storage medium, wherein the method comprises the following steps: acquiring a moving target from a video image as a detection target; tracking the detection target to acquire the position of the detection target in a tracking image frame; acquiring the position of the detection target in a detection image frame in a frame extraction mode; correcting the target position in the tracking image frame by the target position in the detection image frame; the target position is corrected in time in combination with target detection in the tracking process, the accuracy of tracking the moving target in the monitoring video is improved, and the problem of increased deviation between the tracking target position and the target actual position caused by the imperfection of a tracking algorithm is solved.
Drawings
Fig. 1 is a flowchart of a video image correction method according to an embodiment of the present invention;
FIG. 2 is a flowchart of the method of step S40 in FIG. 1;
FIG. 3 is a schematic diagram of a video image frame according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method of step S41 of FIG. 2;
FIG. 5 is a flowchart of another method of step S41 of FIG. 2;
fig. 6 is a block diagram illustrating an exemplary structure of a video image correction apparatus according to a fourth embodiment of the present invention.
The objects, features, and advantages described herein will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer and more obvious, the present invention is further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not restrictive.
Example one
As shown in fig. 1, in the present embodiment, a video image correction method includes:
s10, acquiring a moving target from the video image as a detection target;
s20, tracking the detection target, and acquiring the position of the detection target in a tracking image frame;
s30, acquiring the position of the detection target in the detection image frame in a frame extraction mode;
s40, correcting the target position in the tracking image frame through the target position in the detection image frame;
and S50, outputting a tracking image after the tracking is finished.
In the embodiment, the target position is corrected in time in combination with target detection in the tracking process, so that the accuracy of tracking the moving target in the monitoring video is improved, and the problem of increased deviation between the tracking target position and the target actual position caused by the imperfection of a tracking algorithm is solved.
In this embodiment, the video image may be a real-time image acquired by a monitoring camera, a camera video stream is uploaded to a video analysis platform for decoding, a decoded video frame is transmitted to a target detection module for detection, and a moving target is acquired from the decoded video frame and used as a detection target; the moving object includes: a target face, a target figure, and a target vehicle.
As shown in fig. 2, in the present embodiment, the step S40 includes:
s41, judging whether the detection target in the detection image frame and the tracking target in the tracking image frame are the same target or not through image recognition;
if so, S42, replacing the tracking image frame with the detection image frame, and continuing tracking by taking the detection target in the detection image frame as a tracking target, otherwise, S43, ending the tracking process.
Specifically, the step S40 may be described as: performing target detection on the video frame image Fm, detecting a target A, and recording a target frame A, wherein the target frame is a tracking image frame which is represented in a video in a form of a target frame, as shown in FIG. 3; tracking the target A in the video frame Fm +1 to obtain a tracking target frame A1; tracking the target A1 in the video frame Fm +2 to obtain a tracking target frame A2; tracking a target A2 in the video frame Fn to obtain a tracking target frame An; simultaneously detecting a target A' at Fn; judging An and A' as the same target through a target identification module; if An and A 'are the same target, replacing the tracking frame An with the detection frame A', and correcting the position information of the tracking frame; otherwise, the tracking is finished.
As shown in fig. 4, in this embodiment, the step S41 specifically includes:
s411, calculating the coverage rate of the detection image frame and the tracking image frame;
s412, judging whether the coverage rate is greater than or equal to a preset coverage rate threshold value, if so, S413, enabling the detection target and the tracking target to be the same target; otherwise, S414, the detection target and the tracking target are different targets.
In this embodiment, the calculation formula of the coverage rate is:
o＝Area(A′∩Ak)/Area(A′∪Ak)
wherein o is the coverage, A' is the detected image frame, AkTo detect image frames, Area (A' ∩ A)k) To detect the Area of intersection of an image frame with a tracked image frame, Area (A' ∪ A)k) The area of the union of the detected image frame and the tracked image frame is determined.
In this embodiment, taking the detection target as the target face as an example, the process of capturing the moving target face in video monitoring specifically includes: uploading the video stream of the camera to a video analysis platform for decoding; transmitting the decoded video frame to a target detection module process, detecting a face target, marking a target frame as a, as shown in fig. 3, as one frame of image frame (resolution is 1920 × 1080) after the video stream is decoded, where a rectangular frame marked in the image frame is the position of the detected face target frame; transmitting the detected target frame A to a target tracking module process, tracking a human face target A1, and tracking a subsequent video frame; the detection module performs detection once every K frames to obtain a target face frame A', and the target face frame Ak is tracked for the same video frame; calculating the coverage rate of the target frames A' and Ak, wherein the coverage rate is the ratio of the intersection area and the union area of the two target frames, and the calculation formula is as described above; when the coverage rate value is larger than a coverage rate threshold Th1 (threshold range of [0.5, 0.6]), the same target face is determined, namely the pixel coordinate position of the A 'frame is replaced by the pixel coordinate position of the Ak frame for correction, and the subsequent video frame continuously tracks the pixel coordinate position of the A' frame; and when the coverage value is smaller than the threshold Th1, the target A tracking is finished, and the image of the target A is sent to the interface to be viewed.
As shown in fig. 5, as another embodiment, the step S41 specifically includes:
s415, calculating a similarity value between the detection image frame and the tracking image frame;
s416, judging whether the similarity value is larger than or equal to a preset similarity threshold value, if so, S417, enabling the detection target and the tracking target to be the same target; otherwise, S418, the detection target and the tracking target are different targets.
In this embodiment, the calculation formula of the similarity value is:
d＝∑B′Bk/Sqrt(∑B′+∑Bk)
wherein d is the cosine distance between the detected image frame and the tracking image frame, B' is the detected image frame, BkTo detect image frames.
In this embodiment, both the coverage rate and the similarity value calculation methods shown in fig. 4 and 5 may be used to identify whether the detected target and the tracked target are the same target, and the detection is performed in the real-time tracking process, and a frame extraction manner is adopted to detect the target frame and the tracking frame at the same time every K frames, so that the tracking frame is corrected by the target frame, and the problem of increase in deviation between the position of the tracked target and the actual position of the target due to the imperfection of the tracking algorithm can be solved.
Example two
In this embodiment, taking the detected target as the target figure as an example, the process of capturing the moving target figure in video monitoring specifically includes: uploading the video stream of the camera to a video analysis platform for decoding; transmitting the decoded video frame to a target detection module process, detecting a humanoid target, and recording a target frame as B; transmitting the detected target frame B to a target tracking module process, tracking to a humanoid target B1, and tracking a subsequent video frame; the detection module performs detection once every K frames to obtain a target human face frame B', and for the same video frame, a target human face frame Bk is tracked; extracting characteristic values of B' and Bk, and calculating similarity values of the characteristic values, wherein the similarity values are not limited to be expressed by cosine distances, and the larger the cosine distance value is, the more similar the two targets are, otherwise, the more dissimilar the two targets are; the calculation formula is as described above; the similarity value is greater than a threshold Th2 (the threshold range is given according to specific conditions), the same target human shape is confirmed, namely Bk is replaced by B 'for correction, and the subsequent video frames continue to track B'; and the similarity value is smaller than the threshold Th2, the target B tracking is finished, and the image of the target B is sent to the interface to be viewed.
As another embodiment, the target human shape may also be obtained by identifying whether the detected target and the tracked target are the same target by a coverage method, where the two methods are identifying in a real-time tracking process, and a frame extraction method is adopted to detect the target frame and the tracking frame at intervals of K frames, so that the tracking frame is corrected by the target frame, and the problem of increased deviation between the position of the tracked target and the actual position of the target due to the imperfection of the tracking algorithm can be solved.
EXAMPLE III
In this embodiment, taking a vehicle passing through a gate as an example of a detection target, a process of capturing a moving target vehicle in video monitoring specifically includes: uploading the video stream of the camera to a video analysis platform for decoding; transmitting the decoded video frame to a target detection module process, detecting a vehicle target, and recording a target frame as C; transmitting the detected target frame C to a target tracking module process, tracking to a humanoid target C1, and tracking a subsequent video frame; the detection module performs detection once every K frames to obtain a target vehicle frame C', and the same video frame is tracked to the target vehicle frame Ck; calculating the coverage rate of the target frame C 'and the Ck, wherein the coverage rate value is greater than a threshold Th3, the target frame C' and the Ck are confirmed to be the same target vehicle, namely the Ck is replaced by the C 'for correction, and the subsequent video frame C' continues to track; and when the coverage value is smaller than the threshold Th3, the target C tracking is finished, and the image of the target C is sent to the interface to be viewed.
As another embodiment, the similarity value may also be used to identify whether the detected target and the tracked target are the same target, the specific calculation methods of the two methods refer to the calculation formulas in the first and second embodiments, both the methods are identified in the real-time tracking process, and a frame extraction method is adopted to simultaneously detect the target frame and the tracking frame every K frames, so that the tracking frame is corrected by the target frame, and the problem of increased deviation between the position of the tracked target and the actual position of the target due to the imperfection of the tracking algorithm can be solved.
Example four
As shown in fig. 6, in the present embodiment, a video image correction apparatus includes:
the target detection module 10 is used for acquiring a moving target from a video image as a detection target; the system is also used for acquiring the position of the detection target in a detection image frame in a frame extraction mode;
a target tracking module 20, configured to track the detection target and obtain a position of the detection target in a tracking image frame;
and the identification correction module 30 is used for correcting the target position in the tracking image frame through the target position in the detection image frame.
In the embodiment, the target position is corrected in time in combination with target detection in the tracking process, so that the accuracy of tracking the moving target in the monitoring video is improved, and the problem of increased deviation between the tracking target position and the target actual position caused by the imperfection of a tracking algorithm is solved.
In this embodiment, the video image may be a real-time image acquired by a monitoring camera, a camera video stream is uploaded to a video analysis platform for decoding, a decoded video frame is transmitted to a target detection module for detection, and a moving target is acquired from the decoded video frame and used as a detection target; the moving object includes: a target face, a target figure, and a target vehicle.
EXAMPLE five
In this embodiment, an electronic device includes a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application configured to perform the video image correction method of embodiments one through three.
EXAMPLE six
Embodiments of the present invention provide a readable storage medium, on which a computer program is stored, which when executed by a processor implements the method embodiments as described in any of the above video image correction method embodiments.
It should be noted that the above device, apparatus, and readable storage medium embodiments and method embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments, and technical features in the method embodiments are correspondingly applicable in the device embodiments, which are not described herein again.
The invention discloses a video image correction method, a device, equipment and a readable storage medium, wherein the system comprises the following steps: acquiring a moving target from a video image as a detection target; tracking the detection target to acquire the position of the detection target in a tracking image frame; acquiring the position of the detection target in a detection image frame in a frame extraction mode; correcting the target position in the tracking image frame by the target position in the detection image frame; the target position is corrected in time in combination with target detection in the tracking process, the accuracy of tracking the moving target in the monitoring video is improved, and the problem of increased deviation between the tracking target position and the target actual position caused by the imperfection of a tracking algorithm is solved.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and are not to be construed as limiting the scope of the invention. Any modifications, equivalents and improvements which may occur to those skilled in the art without departing from the scope and spirit of the present invention are intended to be within the scope of the claims.
Claims (10)
1. A method for correcting a video image, comprising:
acquiring a moving target from a video image as a detection target;
tracking the detection target to acquire the position of the detection target in a tracking image frame;
acquiring the position of the detection target in a detection image frame in a frame extraction mode;
correcting the target position in the tracking image frame by the target position in the detection image frame.
2. The method according to claim 1, wherein said correcting the position of the target in the tracking image frame by the position of the target in the detection image frame comprises:
judging whether a detection target in the detection image frame and a tracking target in the tracking image frame are the same target or not through image recognition;
and if so, replacing the tracking image frame with the detection image frame, and continuing tracking by taking a detection target in the detection image frame as a tracking target, otherwise, ending the tracking process.
3. The method according to claim 2, wherein said determining whether the detected object in the detected image frame and the tracked object in the tracked image frame are the same object by image recognition specifically comprises:
calculating the coverage rate of the detection image frame and the tracking image frame;
judging whether the coverage rate is greater than or equal to a preset coverage rate threshold value, if so, enabling the detection target and the tracking target to be the same target; otherwise, the detection target and the tracking target are different targets.
4. A method as claimed in claim 3, wherein the coverage rate is calculated by the following formula:
o＝Area(A′∩Ak)/Area(A′∪Ak)
wherein o is the coverage, A' is the detected image frame, AkTo detect image frames, Area (A' ∩ A)k) To detect the Area of intersection of an image frame with a tracked image frame, Area (A' ∪ A)k) The area of the union of the detected image frame and the tracked image frame is determined.
5. The method according to claim 2, wherein said determining whether the detected object in the detected image frame and the tracked object in the tracked image frame are the same object by image recognition specifically comprises:
calculating a similarity value of the detection image frame and the tracking image frame;
judging whether the similarity value is greater than or equal to a preset similarity threshold value, if so, enabling the detection target and the tracking target to be the same target; otherwise, the detection target and the tracking target are different targets.
6. The method of claim 5, wherein the similarity value is calculated by the following formula:
d＝∑B′Bk/sqrt(∑B′+∑Bk)
wherein d is the cosine distance between the detected image frame and the tracking image frame, B' is the detected image frame, BkTo detect image frames.
7. The method according to claim 1, wherein the moving object comprises: a target face, a target figure, and a target vehicle.
8. A video image correction apparatus, comprising:
the target detection module is used for acquiring a moving target from the video image as a detection target; the system is also used for acquiring the position of the detection target in a detection image frame in a frame extraction mode;
the target tracking module is used for tracking the detection target and acquiring the position of the detection target in a tracking image frame;
and the identification correction module is used for correcting the target position in the tracking image frame through the target position in the detection image frame.
9. An electronic device comprising a memory, a processor and at least one application program stored in the memory and configured to be executed by the processor, wherein the application program is configured to perform the video image correction method of any of claims 1-7.
10. A readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the video image correction method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811605189.1A CN111369586A (en) | 2018-12-26 | 2018-12-26 | Video image correction method, device, equipment and readable storage medium |
| PCT/CN2019/123186 WO2020134935A1 (en) | 2018-12-26 | 2019-12-05 | Video image correction method, apparatus and device, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811605189.1A CN111369586A (en) | 2018-12-26 | 2018-12-26 | Video image correction method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111369586A true CN111369586A (en) | 2020-07-03 |
Family
ID=71126901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811605189.1A Pending CN111369586A (en) | 2018-12-26 | 2018-12-26 | Video image correction method, device, equipment and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111369586A (en) |
| WO (1) | WO2020134935A1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130322684A1 (en) * | 2012-06-04 | 2013-12-05 | International Business Machines Corporation | Surveillance including a modified video data stream |
| CN105654512A (en) * | 2015-12-29 | 2016-06-08 | 深圳羚羊微服机器人科技有限公司 | Target tracking method and device |
| CN108062763A (en) * | 2017-12-29 | 2018-05-22 | 纳恩博（北京）科技有限公司 | Method for tracking target and device, storage medium |
| CN108985204A (en) * | 2018-07-04 | 2018-12-11 | 北京师范大学珠海分校 | Pedestrian detection tracking and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101098461B (en) * | 2007-07-05 | 2010-11-17 | 复旦大学 | Full shelter processing method of video target tracking |
| CN102339391B (en) * | 2010-07-27 | 2013-12-04 | 株式会社理光 | Multiobject identification method and device |
| CN102880864A (en) * | 2012-04-28 | 2013-01-16 | 王浩 | Method for snap-shooting human face from streaming media file |
| US9070020B2 (en) * | 2012-08-21 | 2015-06-30 | International Business Machines Corporation | Determination of train presence and motion state in railway environments |
-
2018
- 2018-12-26 CN CN201811605189.1A patent/CN111369586A/en active Pending
-
2019
- 2019-12-05 WO PCT/CN2019/123186 patent/WO2020134935A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130322684A1 (en) * | 2012-06-04 | 2013-12-05 | International Business Machines Corporation | Surveillance including a modified video data stream |
| CN105654512A (en) * | 2015-12-29 | 2016-06-08 | 深圳羚羊微服机器人科技有限公司 | Target tracking method and device |
| CN108062763A (en) * | 2017-12-29 | 2018-05-22 | 纳恩博（北京）科技有限公司 | Method for tracking target and device, storage medium |
| CN108985204A (en) * | 2018-07-04 | 2018-12-11 | 北京师范大学珠海分校 | Pedestrian detection tracking and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020134935A1 (en) | 2020-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10223595B2 (en) | Methods, devices and computer programs for tracking targets using independent tracking modules associated with cameras | |
| US9953225B2 (en) | Image processing apparatus and image processing method | |
| TWI425454B (en) | Method, system and computer program product for reconstructing moving path of vehicle | |
| US9105101B2 (en) | Image tracking device and image tracking method thereof | |
| CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| US20180047271A1 (en) | Fire detection method, fire detection apparatus and electronic equipment | |
| WO2018058530A1 (en) | Target detection method and device, and image processing apparatus | |
| Satzoda et al. | On performance evaluation metrics for lane estimation | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN105608209A (en) | Video labeling method and video labeling device | |
| CN110298302B (en) | Human body target detection method and related equipment | |
| JP2017076394A (en) | Moving object counter and method | |
| EP3432575A1 (en) | Method for performing multi-camera automatic patrol control with aid of statistics data in a surveillance system, and associated apparatus | |
| CN110688873A (en) | Multi-target tracking method and face recognition method | |
| CN111489380A (en) | Target object track analysis method | |
| CN104112281B (en) | Method Of Tracking Objects Using Hyperspectral Imagery | |
| TWI517100B (en) | Method for tracking moving object and electronic apparatus using the same | |
| US10916016B2 (en) | Image processing apparatus and method and monitoring system | |
| CN109815861B (en) | User behavior information statistical method based on face recognition | |
| US20220375202A1 (en) | Hierarchical sampling for object identification | |
| CN111369586A (en) | Video image correction method, device, equipment and readable storage medium | |
| CN105830437A (en) | Method and system for identifying background in monitoring system | |
| CN112906495B (en) | Target detection method and device, electronic equipment and storage medium | |
| CN109740518B (en) | Method and device for determining object in video | |
| CN109859234B (en) | Video human body trajectory tracking method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |