CN111985321A - Target object detection method, electronic device, and storage medium - Google Patents
Target object detection method, electronic device, and storage medium Download PDFInfo
- Publication number
- CN111985321A CN111985321A CN202010673888.0A CN202010673888A CN111985321A CN 111985321 A CN111985321 A CN 111985321A CN 202010673888 A CN202010673888 A CN 202010673888A CN 111985321 A CN111985321 A CN 111985321A
- Authority
- CN
- China
- Prior art keywords
- target object
- target
- feature
- identifying
- contour
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000010586 diagram Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 13
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 210000001202 rhombencephalon Anatomy 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001094 effect on targets Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a target object detection method, an electronic device and a storage medium, wherein the target object detection method comprises the following steps: acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images; identifying a target object in the sequence of images based on the target contour; tracking a target object and judging whether the motion direction of the target object is a backward motion; if yes, judging whether the target object has the target characteristics; and if so, identifying the target object as a valid target object. The target object which does not move back to back can be identified as the effective target object by identifying the target object based on the target contour and judging the moving direction of the target object, and compared with the target object identified based on the target contour and the target characteristics, the identification speed is high, and the omission factor is low. In addition, the target characteristics of the target object moving backwards are further identified so as to eliminate invalid target objects without the target characteristics, improve the accuracy of detecting the target object and reduce the false detection rate.
Description
Technical Field
The application belongs to the technical field of target tracking, and particularly relates to a target object detection method, electronic equipment and a storage medium.
Background
With the acceleration of the urbanization process, the public safety requirements of the society are increasing day by day, a plurality of important public places cover a wide camera network, and the automatic monitoring by using a computer vision technology becomes a focus of attention.
The target detection is the direction of the most intense research in the current detection field, wherein the face detection in the target detection is to give any picture, find out whether one or more faces exist in the picture, and return the position and range of each face in the picture. And the human face is used as the unique identification characteristic of the human body, and has wide application prospects in the fields of security monitoring, authentication comparison, human-computer interaction, public safety and the like. The quality of the face detection directly affects the performance of subsequent face recognition, so how to reduce the missing detection rate and the false detection rate of the target detection system and improve the detection accuracy is a problem to be solved.
Disclosure of Invention
The application provides a target object detection method, electronic equipment and a storage medium, which are used for solving the problems of high missing detection rate and false detection rate and low detection accuracy of a target detection system.
In order to solve the technical problem, the application adopts a technical scheme that: a target object detection method, comprising: acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images; identifying a target object in the sequence of images based on a target contour; tracking the target object, and judging whether the motion direction of the target object is a backward motion; if the movement direction of the target object is the backward movement, judging whether the target object has target characteristics; and if the target object has the target characteristics, identifying the target object as a valid target object.
According to an embodiment of the present application, if the moving direction of the target object is not a backward movement, the target object is identified as a valid target object.
According to an embodiment of the present application, the identifying a target object in the image sequence based on a target contour includes: and inputting the image sequence into a target contour recognition model to obtain a target object characteristic diagram, and obtaining a target object detection frame based on the target object characteristic diagram.
According to an embodiment of the present application, the target contour recognition model includes a YOLOv3 model.
According to an embodiment of the present application, determining whether the target object has a target feature includes: and inputting the target object feature map into a target feature recognition model, and recognizing whether the target object feature map comprises target features.
According to an embodiment of the present application, the target feature recognition model comprises an MTCNN model.
According to an embodiment of the application, the target feature recognition model comprises three cascaded sub-feature recognition modules, wherein the three cascaded sub-feature recognition modules are respectively a first feature recognition module, a second feature recognition module and a third feature recognition module; the inputting the target object feature map into a target feature recognition model comprises: inputting the target feature map into a first feature recognition module, and recognizing to obtain a first feature point and a first feature map containing the first feature point; inputting the first feature map into a second feature recognition module, and recognizing to obtain second feature points and a second feature map containing the second feature points; comparing the first characteristic points with the second characteristic points, and removing the characteristic points with the repetition degree larger than a preset value to obtain preliminary characteristic points and a preliminary characteristic graph containing the preliminary characteristic points; inputting the preliminary feature map into a third feature recognition model, and recognizing to obtain a third feature point and a third feature map containing the third feature point; and comparing the third characteristic point with the preliminary characteristic point, and removing the characteristic points with the repetition degree larger than a preset value to obtain the target characteristic.
According to an embodiment of the present application, the determining whether the moving direction of the target object is a backward movement includes: and judging whether the size of the target object in the next image is smaller than that of the target object in the current image, if so, judging that the movement direction of the target object is a backward movement.
In order to solve the above technical problem, another technical solution adopted by the present application is: an electronic device comprising a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the steps of: acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images; identifying a target object in the sequence of images based on a target contour; tracking the target object, and judging whether the motion direction of the target object is a backward motion; if the movement direction of the target object is the backward movement, judging whether the target object has target characteristics; and if the target object has the target characteristics, identifying the target object as a valid target object.
In order to solve the above technical problem, the present application adopts another technical solution: a computer-readable storage medium having stored thereon program data which, when executed by a processor, performs the steps of: acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images; identifying a target object in the sequence of images based on a target contour; tracking the target object, and judging whether the motion direction of the target object is a backward motion; if the movement direction of the target object is the backward movement, judging whether the target object has target characteristics; and if the target object has the target characteristics, identifying the target object as a valid target object.
The beneficial effect of this application is: the target object which does not move back to back can be identified as the effective target object by identifying the target object based on the target contour and judging the moving direction of the target object, and compared with the target object identified based on the target contour and the target characteristics, the identification speed is high, and the omission factor is low. In addition, the target characteristics of the target object moving backwards are further identified so as to eliminate invalid target objects without the target characteristics, improve the accuracy of detecting the target object and reduce the false detection rate.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a target object detection method of the present application;
FIG. 2 is a schematic flow chart illustrating the identification of a target feature of a target object according to an embodiment of the target object detection method of the present application;
FIG. 3 is a schematic structural diagram of an embodiment of an electronic device of the present application;
FIG. 4 is a schematic structural diagram of an embodiment of a target object detection apparatus of the present application;
FIG. 5 is a schematic structural diagram of an embodiment of a computer-readable storage medium of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of a target object detection method according to the present application; fig. 2 is a schematic flowchart illustrating a process of identifying a target feature of a target object according to an embodiment of the target object detection method of the present application.
An embodiment of the present application provides a target object detection method, including the following steps:
s11: an image sequence is acquired, the image sequence comprising a plurality of images in succession.
An image sequence is acquired, the image sequence comprising a plurality of successive images, typically a plurality of successive images extracted from a video image.
S12: a target object in the sequence of images is identified based on the target contour.
Identifying a target object in a sequence of images based on an image profile includes: and inputting the image sequence into a target contour recognition model to obtain a target object characteristic diagram, and obtaining a target detection frame based on the target object characteristic diagram.
In one embodiment, the target contour recognition model is a YOLOv3 model, and the YOLOv3 model has good performance in detection accuracy and speed. Specifically, a graphic sequence is input into a YOLOv3 model, an image is continuously convoluted, extracted and down-sampled to feature maps with different resolutions, then the image is divided into S × S grids based on different feature maps, each grid is responsible for detecting the object type appearing in the grid, the S × S grids are reflected on the feature map generated finally by the model, and the scale of the finally obtained feature map is S × (B × 5+ C), wherein B represents the number of detection frames of a target object to be predicted in one grid, C represents the number of object types to be predicted, and a coordinate frame, a foreground score and a target type score of a detection target are directly regressed. The above is a general flow of the YOLOv3 model, and how the YOLOv3 model specifically recognizes images is not described herein again. The YOLOv3 model has good detection effect on target objects with different sizes, high detection speed and low omission ratio.
S13: and tracking the target object and judging whether the moving direction of the target object is a backward movement.
In step S12, the target object has been identified in the image sequence, the target object is tracked, and whether the movement direction of the target object is a backward movement is determined.
In one embodiment, tracking the target object, and determining whether the moving direction of the target object is a backward movement includes:
and tracking the target object, and judging whether the size of the target object in the next image is smaller than that of the target object in the current image, wherein if yes, the moving direction of the target object is a backward movement, namely the target object is far away from the shooting equipment. If the target object is a person, the person is moving back to the shooting device, i.e., moving back to back. Or, the target detection frame may be tracked to determine whether the target detection frame is far away from the shooting device, and if the target detection frame is far away from the shooting device, the moving direction of the target object moves backwards.
S14: and if the moving direction of the target object is the backward movement, judging whether the target object has the target characteristics.
If the moving direction of the target object is a backward movement, the target object may be a human hindbrain without the characteristics of human five sense organs, and the target object is an invalid target object, so that the target object needs to be removed, the false detection rate is reduced, and the accuracy is improved. Therefore, if the moving direction of the target object is the backward movement, whether the target object has the target characteristics is judged.
Determining whether the target object has the target feature comprises: and inputting the target object feature map into a target feature recognition model, and recognizing whether the target object feature map comprises target features.
In an embodiment, the target feature recognition model comprises an MTCNN model.
The target feature recognition model comprises three cascaded sub-feature recognition modules, wherein the three cascaded sub-feature recognition modules are respectively a first feature recognition module, a second feature recognition module and a third feature recognition module. Inputting the target object feature map into the target feature recognition model comprises:
s141: and inputting the target feature map output by the target contour recognition model into a first feature recognition module, and recognizing to obtain first feature points and a first feature map comprising the first feature points.
The target feature map output by the target contour recognition model is input into the first feature recognition module, so that a plurality of first feature points and a first feature map comprising the first feature points can be obtained. The first characteristic identification module is a P-Net network, and the P-Net network comprises three convolutional layers.
S142: and inputting the first feature map into a second feature recognition module, and recognizing to obtain second feature points and a second feature map containing the second feature points.
And inputting the first feature map containing the first feature points into a second feature recognition module, and recognizing to obtain second feature points and a second feature map containing the second feature points. The second characteristic identification module is an R-Net network, and the R-Net network comprises three convolutional layers. The resolution of the first feature map is greater than that of the target feature map, and the accuracy of the second feature points is higher than that of the first feature points.
S143: and comparing the first characteristic points with the second characteristic points, and removing the characteristic points with the repetition degree larger than a preset value to obtain preliminary characteristic points and a preliminary characteristic graph containing the preliminary characteristic points.
And comparing the first characteristic points with the second characteristic points, and removing the characteristic points with larger repetition degree to obtain more accurate preliminary characteristic points and a preliminary characteristic graph containing the preliminary characteristic points.
S144: and inputting the preliminary feature map into a third feature recognition model, and recognizing to obtain a third feature point and a third feature map containing the third feature point.
And inputting the preliminary feature map containing the preliminary feature points into a third feature recognition model, and recognizing to obtain third feature points and a third feature map containing the third feature points. The third feature recognition module is an O-Net network, and the third feature points obtained by the third feature recognition module are more accurate than the second feature points.
S145: and comparing the third characteristic points with the preliminary characteristic points, and removing the characteristic points with the repetition degree larger than a preset value to obtain the target characteristic.
And comparing the third characteristic points with the preliminary characteristic points, and removing the characteristic points with larger repetition degree to obtain the target characteristic. Through the continuous refined detection and identification processes of the three feature identification modules, the loss of the target features is calculated, the accuracy is high, the detection and positioning speed of the target features is high, and the performance is good.
S15: and if the target object has the target characteristics, identifying the target object as a valid target object.
And if the target object has the target characteristics, identifying the target object as a valid target object.
S16: and if the target object does not have the target characteristics, identifying the target object as an invalid target object.
If the target object does not have the target feature, the target object is useless, for example, the target object is a human face, and the human face without the human face feature may be a hindbrain, which is an invalid target object.
S17: and if the moving direction of the target object is not the backward movement, identifying the target object as a valid target object.
If the moving direction of the target object is not the backward movement, the target object is the forward or lateral movement, and the like, and generally has the target characteristics, and the target object can be judged to be the effective target object without further judging whether the target characteristics exist.
The target object which does not move back to back can be identified as the effective target object by identifying the target object based on the target contour and judging the moving direction of the target object, and compared with the target object identified based on the target contour and the target characteristics, the identification speed is high, and the omission factor is low. In addition, the target characteristics of the target object moving backwards are further identified so as to eliminate invalid target objects without the target characteristics, improve the accuracy of detecting the target object and reduce the false detection rate.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an embodiment of an electronic device according to the present application.
Yet another embodiment of the present application provides an electronic device 20, which includes a memory 21 and a processor 22 coupled to each other, wherein the processor 22 is configured to execute program instructions stored in the memory 21. In one particular implementation scenario, electronic device 20 may include, but is not limited to: a microcomputer, a server, and the electronic device 20 may also include a mobile device such as a notebook computer, a tablet computer, and the like, which is not limited herein.
In particular, the processor 22 is configured to control itself and the memory 21 to implement the following steps: acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images; identifying a target object in the sequence of images based on the target contour; tracking a target object and judging whether the motion direction of the target object is a backward motion; if the moving direction of the target object is the backward movement, judging whether the target object has target characteristics; and if the target object has the target characteristics, identifying the target object as a valid target object.
Further, the electronic device 20 may also implement the target object detection method of any of the above embodiments.
The processor 22 may also be referred to as a CPU (Central Processing Unit). The processor 22 may be an integrated circuit chip having signal processing capabilities. The Processor 22 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 22 may be commonly implemented by an integrated circuit chip. The target object which does not move back to back can be identified as the effective target object by identifying the target object based on the target contour and judging the moving direction of the target object, and compared with the target object identified based on the target contour and the target characteristics, the identification speed is high, and the omission factor is low. In addition, the target characteristics of the target object moving backwards are further identified so as to eliminate invalid target objects without the target characteristics, improve the accuracy of detecting the target object and reduce the false detection rate.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of a target object detection apparatus according to the present application.
The present application further provides a target object detection apparatus 30, which includes an image acquisition module 31, a target contour recognition module 32, a tracking module 33, a determination module 34, and a target feature recognition module 35. Wherein the image acquisition module 31 acquires an image sequence, the image sequence comprising a plurality of continuous images; the target contour identification module 32 identifies a target object in the sequence of images based on the target contour; the tracking module 33 tracks the target object, and the judging module 34 judges whether the moving direction of the target object is a backward movement; if the moving direction of the target object is a backward movement, the target feature recognition module 35 recognizes the target feature of the target object, and the determination module 34 determines whether the target object has the target feature; if the target object has the target feature, the determination module 34 identifies the target object as a valid target object. The target object which does not move back to back can be identified as the effective target object by identifying the target object based on the target contour and judging the moving direction of the target object, and compared with the target object identified based on the target contour and the target characteristics, the identification speed is high, and the omission factor is low. In addition, the target characteristics of the target object moving backwards are further identified so as to eliminate invalid target objects without the target characteristics, improve the accuracy of detecting the target object and reduce the false detection rate.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of a computer-readable storage medium according to the present application.
Yet another embodiment of the application provides a computer readable storage medium 40 having program data 41 stored thereon, the program data 41 when executed by a processor implementing the steps of: acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images; identifying a target object in the sequence of images based on the target contour; tracking a target object and judging whether the motion direction of the target object is a backward motion; if the moving direction of the target object is the backward movement, judging whether the target object has target characteristics; and if the target object has the target characteristics, identifying the target object as a valid target object. Further, the program data 41, when executed by the processor, implements the target object detection method of any of the above embodiments. Through the scheme, the target object is identified based on the target contour, the moving direction of the target object is judged in a combined manner, the target object which does not move back to back can be identified as the effective target object, and compared with the target object identified based on the target contour and the target characteristics, the target object identification speed is high, and the omission factor is low. In addition, the target characteristics of the target object moving backwards are further identified so as to eliminate invalid target objects without the target characteristics, improve the accuracy of detecting the target object and reduce the false detection rate.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely one type of logical division, and an actual implementation may have another division, for example, a unit or a component may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on network elements. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium 40. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium 40 and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium 40 includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (10)
1. A target object detection method, comprising:
acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images;
identifying a target object in the sequence of images based on a target contour;
tracking the target object, and judging whether the motion direction of the target object is a backward motion;
if the movement direction of the target object is the backward movement, judging whether the target object has target characteristics;
and if the target object has the target characteristics, identifying the target object as a valid target object.
2. The method of claim 1, comprising:
and if the motion direction of the target object is not the backward motion, identifying the target object as an effective target object.
3. The method of claim 1, wherein the identifying a target object in the sequence of images based on a target contour comprises:
and inputting the image sequence into a target contour recognition model to obtain a target object characteristic diagram, and obtaining a target object detection frame based on the target object characteristic diagram.
4. The method of claim 3, wherein the target contour recognition model comprises a YOLOv3 model.
5. The method of claim 3, wherein determining whether the target object has a target feature comprises:
and inputting the target object feature map into a target feature recognition model, and recognizing whether the target object feature map comprises target features.
6. The method of claim 5, wherein the target feature recognition model comprises an MTCNN model.
7. The method of claim 5, wherein the target feature recognition model comprises three cascaded sub-feature recognition modules, wherein the three cascaded sub-feature recognition modules are a first feature recognition module, a second feature recognition module and a third feature recognition module; the inputting the target object feature map into a target feature recognition model comprises:
inputting the target feature map into a first feature recognition module, and recognizing to obtain a first feature point and a first feature map containing the first feature point;
inputting the first feature map into a second feature recognition module, and recognizing to obtain second feature points and a second feature map containing the second feature points;
comparing the first characteristic points with the second characteristic points, and removing the characteristic points with the repetition degree larger than a preset value to obtain preliminary characteristic points and a preliminary characteristic graph containing the preliminary characteristic points;
inputting the preliminary feature map into a third feature recognition model, and recognizing to obtain a third feature point and a third feature map containing the third feature point;
and comparing the third characteristic point with the preliminary characteristic point, and removing the characteristic points with the repetition degree larger than a preset value to obtain the target characteristic.
8. The method according to any one of claims 1-7, wherein the determining whether the moving direction of the target object is a backward movement comprises:
and judging whether the size of the target object in the next image is smaller than that of the target object in the current image, if so, judging that the movement direction of the target object is a backward movement.
9. An electronic device comprising a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the steps of:
acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images;
identifying a target object in the sequence of images based on a target contour;
tracking the target object, and judging whether the motion direction of the target object is a backward motion;
if the movement direction of the target object is the backward movement, judging whether the target object has target characteristics;
and if the target object has the target characteristics, identifying the target object as a valid target object.
10. A computer-readable storage medium having program data stored thereon, wherein the program data when executed by a processor implements the steps of:
acquiring an image sequence, wherein the image sequence comprises a plurality of continuous images;
identifying a target object in the sequence of images based on a target contour;
tracking the target object, and judging whether the motion direction of the target object is a backward motion;
if the movement direction of the target object is the backward movement, judging whether the target object has target characteristics;
and if the target object has the target characteristics, identifying the target object as a valid target object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010673888.0A CN111985321A (en) | 2020-07-14 | 2020-07-14 | Target object detection method, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010673888.0A CN111985321A (en) | 2020-07-14 | 2020-07-14 | Target object detection method, electronic device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111985321A true CN111985321A (en) | 2020-11-24 |
Family
ID=73439173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010673888.0A Pending CN111985321A (en) | 2020-07-14 | 2020-07-14 | Target object detection method, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111985321A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400397A (en) * | 2013-07-31 | 2013-11-20 | 中安消技术有限公司 | Method, device and system for smooth target dividing based on space-time |
| CN106022278A (en) * | 2016-05-26 | 2016-10-12 | 天津艾思科尔科技有限公司 | Method and system for detecting people wearing burka in video images |
| CN108509859A (en) * | 2018-03-09 | 2018-09-07 | 南京邮电大学 | A kind of non-overlapping region pedestrian tracting method based on deep neural network |
| CN108600707A (en) * | 2018-06-19 | 2018-09-28 | 华为技术有限公司 | A kind of monitoring method, recognition methods, relevant apparatus and system |
| CN108875588A (en) * | 2018-05-25 | 2018-11-23 | 武汉大学 | Across camera pedestrian detection tracking based on deep learning |
| CN109711246A (en) * | 2018-09-30 | 2019-05-03 | 鲁东大学 | A kind of dynamic object recognition methods, computer installation and readable storage medium storing program for executing |
| CN110674748A (en) * | 2019-09-24 | 2020-01-10 | 腾讯科技（深圳）有限公司 | Image data processing method, image data processing device, computer equipment and readable storage medium |
| US20200058129A1 (en) * | 2018-08-14 | 2020-02-20 | National Chiao Tung University | Image tracking method |
-
2020
- 2020-07-14 CN CN202010673888.0A patent/CN111985321A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400397A (en) * | 2013-07-31 | 2013-11-20 | 中安消技术有限公司 | Method, device and system for smooth target dividing based on space-time |
| CN106022278A (en) * | 2016-05-26 | 2016-10-12 | 天津艾思科尔科技有限公司 | Method and system for detecting people wearing burka in video images |
| CN108509859A (en) * | 2018-03-09 | 2018-09-07 | 南京邮电大学 | A kind of non-overlapping region pedestrian tracting method based on deep neural network |
| CN108875588A (en) * | 2018-05-25 | 2018-11-23 | 武汉大学 | Across camera pedestrian detection tracking based on deep learning |
| CN108600707A (en) * | 2018-06-19 | 2018-09-28 | 华为技术有限公司 | A kind of monitoring method, recognition methods, relevant apparatus and system |
| US20200058129A1 (en) * | 2018-08-14 | 2020-02-20 | National Chiao Tung University | Image tracking method |
| CN109711246A (en) * | 2018-09-30 | 2019-05-03 | 鲁东大学 | A kind of dynamic object recognition methods, computer installation and readable storage medium storing program for executing |
| CN110674748A (en) * | 2019-09-24 | 2020-01-10 | 腾讯科技（深圳）有限公司 | Image data processing method, image data processing device, computer equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王科俊 等: "视频图像序列运动目标检测及轮廓提取", 微计算机信息, no. 30, 31 October 2008 (2008-10-31), pages 302 - 303 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358149B (en) | Human body posture detection method and device | |
| US20200294252A1 (en) | Human-tracking methods, systems, and storage media | |
| CN111104925B (en) | Image processing method, image processing apparatus, storage medium, and electronic device | |
| CN112989962B (en) | Track generation method, track generation device, electronic equipment and storage medium | |
| CN110660102B (en) | Speaker recognition method, device and system based on artificial intelligence | |
| CN111311634A (en) | Face image detection method, device and equipment | |
| US11074716B2 (en) | Image processing for object detection | |
| US20220301317A1 (en) | Method and device for constructing object motion trajectory, and computer storage medium | |
| US20210358133A1 (en) | Method and device for estimating background motion of infrared image sequences and storage medium | |
| CN111291749B (en) | Gesture recognition method and device and robot | |
| CN111382722A (en) | License plate image optimization method, image processing device and device with storage function | |
| CN112966654A (en) | Lip movement detection method and device, terminal equipment and computer readable storage medium | |
| CN113256683B (en) | Target tracking method and related equipment | |
| CN113298852A (en) | Target tracking method and device, electronic equipment and computer readable storage medium | |
| CN111382606A (en) | Tumble detection method, tumble detection device and electronic equipment | |
| CN113870322A (en) | Event camera-based multi-target tracking method and device and computer equipment | |
| CN116912517B (en) | Method and device for detecting camera view field boundary | |
| CN110799984A (en) | Tracking control method, device and computer readable storage medium | |
| CN114972492A (en) | Position and pose determination method and device based on aerial view and computer storage medium | |
| CN111768427A (en) | Multi-moving-target tracking method and device and storage medium | |
| JPWO2018179119A1 (en) | Video analysis device, video analysis method, and program | |
| CN111985321A (en) | Target object detection method, electronic device, and storage medium | |
| CN116342642A (en) | Target tracking method, device, electronic equipment and readable storage medium | |
| CN112416128B (en) | Gesture recognition method and terminal equipment | |
| CN114219938A (en) | Region-of-interest acquisition 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 |