CN110866473B - Target object tracking detection method and device, storage medium and electronic device - Google Patents
Target object tracking detection method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN110866473B CN110866473B CN201911067409.4A CN201911067409A CN110866473B CN 110866473 B CN110866473 B CN 110866473B CN 201911067409 A CN201911067409 A CN 201911067409A CN 110866473 B CN110866473 B CN 110866473B
- Authority
- CN
- China
- Prior art keywords
- target object
- target
- image
- area
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention provides a tracking detection method and device of a target object, a storage medium and an electronic device, wherein the method comprises the following steps: detecting a target area; under the condition that a target object exists in a shielding area of the target area, detecting whether the target object in the shielding area is a living body or not to obtain a detection result; whether the target object in the shielding region is tracked and detected is determined according to the detection result, and by adopting the technical scheme, the problems that in the related technology, in the target detection process, a false target object cannot be completely identified, so that the target detection method is inaccurate and the like are solved.
Description
Technical Field
The invention relates to the field of computers, in particular to a tracking detection method and device of a target object, a storage medium and an electronic device.
Background
With the development of information-based education, modern tools and technologies based on multimedia, big data, artificial intelligence and the like are increasingly applied to the modern teaching process. Education resource sharing is one of the main features of informatization and intelligent education, recording and broadcasting of teaching activities are increasingly popular as a common way of resource sharing, and how to make recording and broadcasting more intelligent is still a problem to be solved.
The target detection methods based on deep learning are all data-driven methods, and the quality of the detection effect depends on the quality of training data to a great extent. Meanwhile, under the influence of certain specific factors such as mirror reflection, poster picture albums, electronic images and the like, false targets on the media can be detected out as real targets by the model, the existing target detection methods cannot realize 100% accurate detection, and false detection and missed detection can occur to a certain degree. Aiming at the problems that in the related art, in the target detection process, a false target object cannot be completely identified, so that the target detection method is inaccurate and the like, an effective technical scheme is not provided.
Disclosure of Invention
The embodiment of the invention provides a target object tracking detection method and device, a storage medium and an electronic device, and at least solves the problems that in the target detection process in the related art, a false target object cannot be completely identified, so that the target detection method is inaccurate and the like.
According to an embodiment of the present invention, there is provided a tracking detection method for a target object, including: detecting a target area; under the condition that a target object exists in a shielding area of the target area, detecting whether the target object in the shielding area is a living body or not to obtain a detection result; and determining whether to track and detect the target object in the shielding area according to the detection result.
In the embodiment of the present invention, detecting a target area includes: acquiring an image obtained by video recording of a target area; a target object in the image is identified.
In an embodiment of the present invention, identifying a target object in the image comprises: identifying the image through a deep-learning network model, wherein the structure of the deep-learning network model sequentially comprises: a residual error cascade module, an inclusion-Resnet module and a YOLO detection layer; and determining the target object in the image according to the recognition result.
In an embodiment of the present invention, after obtaining an image obtained by video recording of a target area, the method further includes: setting a mark for a shielding region in the image, wherein the shielding region is determined to be present in the image when the mark is present in the image, and the shielding region is determined not to be present in the image when the mark is absent in the image.
In this embodiment of the present invention, after detecting the target area, the method further includes: and under the condition that a target object exists in a non-shielding area of the target area, outputting a result that the target object is identified by the non-shielding area.
According to another embodiment of the present invention, there is also provided a tracking detection apparatus for a target object, including: the detection module is used for detecting the target area; the processing module is used for detecting whether the target object in the shielding area is a living body or not under the condition that the target object exists in the shielding area of the target area to obtain a detection result; and the determining module is used for determining whether to track and detect the target object in the shielding area according to the detection result.
In an embodiment of the present invention, the detection module includes: an acquisition unit configured to acquire an image obtained by video recording of a target area; an identification unit for identifying a target object in the image.
In an embodiment of the present invention, the identifying unit is further configured to identify the image through a deep-learning network model, where a structure of the deep-learning network model sequentially includes: a residual error cascade module, an inclusion-Resnet module and a YOLO detection layer; and determining the target object in the image according to the recognition result.
According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, comprising a memory in which a computer program is stored and a processor configured to run the computer program to perform the steps of any of the method embodiments described above.
According to the invention, under the condition that a target object exists in a shielding area of a target area, whether the target object in the shielding area is a living body is detected, and a detection result is obtained; and determining whether to perform tracking detection on the target object in the shielding region according to the detection result, namely determining whether to perform tracking detection on the target object under the condition that whether the target object in the shielding region is a living body is identified. By adopting the technical scheme, the problems that in the related art, in the target detection process, the false target object cannot be completely identified, so that the target detection method is inaccurate and the like are solved, under the condition that the possible false target object is identified, whether the identified false target object is a living body is determined, whether the target object is tracked and identified is further determined, and the accuracy of tracking and detecting the target object is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
fig. 1 is a block diagram of a hardware structure of a computer terminal of a tracking detection method for a target object according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of tracking detection of a target object according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an alternative network architecture according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of an alternative shielded region according to an embodiment of the invention;
FIG. 5 is a schematic view of an alternative shielded region according to an embodiment of the invention;
FIG. 6 is a schematic overall flow diagram in accordance with an alternative embodiment of the invention;
fig. 7 is a block diagram of a structure of a tracking detection apparatus of a target object according to an embodiment of the present invention;
fig. 8 is another block diagram of the tracking detection apparatus of a target object according to the embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method provided by the embodiment of the application can be executed in a computer terminal or a similar operation device. Taking an example of the present invention running on a computer terminal, fig. 1 is a block diagram of a hardware structure of a computer terminal of a tracking detection method for a target object according to an embodiment of the present invention. As shown in fig. 1, the computer terminal 10 may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data, and optionally may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the computer terminal. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration with equivalent functionality to that shown in FIG. 1 or more functionality than that shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program and a module of an application software, such as a computer program corresponding to the tracking detection method of the target object in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In this embodiment, a method for tracking and detecting a target object running on the computer terminal is provided, and fig. 2 is a flowchart of the method for tracking and detecting a target object according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, detecting a target area;
step S204, under the condition that a target object exists in a shielding area of the target area, detecting whether the target object in the shielding area is a living body or not to obtain a detection result;
and step S206, determining whether to track and detect the target object in the shielding area according to the detection result.
According to the technical scheme, under the condition that the target object exists in the shielding region of the target region, whether the target object in the shielding region is a living body is detected, and a detection result is obtained; and determining whether to perform tracking detection on the target object in the shielding region according to the detection result, namely determining whether to perform tracking detection on the target object under the condition that whether the target object in the shielding region is a living body is identified. By adopting the technical scheme, the problems that in the related art, in the target detection process, the false target object cannot be completely identified, so that the target detection method is inaccurate and the like are solved, under the condition that the possible false target object is identified, whether the identified false target object is a living body is determined, whether the target object is tracked and identified is further determined, and the accuracy of tracking and detecting the target object is improved.
The step S202 may be implemented in various ways, and in an alternative embodiment, the following technical solutions may be implemented: acquiring an image obtained by video recording of a target area; the target object in the image is identified, that is, the target area may be recorded first, and whether the target object exists in the image and the position where the target object exists are identified from the obtained image.
Specifically, in the embodiment of the present invention, the target object may be identified from the image through a deep-learning network model, where a structure of the deep-learning network model sequentially includes: the network model comprises a residual error cascading module, an inclusion-respet module and a YOLO detection layer, namely the structure of the network model in the embodiment of the invention mainly comprises the residual error cascading module, the inclusion-respet module and the YOLO detection layer, an original Stem module and a Reduction module in the inclusion-respet network are removed, the residual error cascading modules 1, 2 and 3 are respectively obtained by cascading 10 layers, 6 layers and 2 layers of residual error structures, and the network model mainly has the function of deepening the network and reducing the calculation amount; the Incepration-Resnet module can obtain sparse or non-sparse characteristics on the same layer, can accelerate training and improve network performance. An inclusion-respet module is connected with a YOLO layer for classification and positioning, and finally a deep learning target detection network structure based on regression is constructed; and determining the target object in the image according to the recognition result.
The method includes the steps that after an image obtained by video recording of a target area is obtained, a mark is set for the shielding area in the image, wherein the shielding area is determined to exist in the image under the condition that the mark exists in the image, and the shielding area is determined not to exist in the image under the condition that the mark does not exist in the image.
It should be noted that, when it is detected that a target object exists in a non-shielding region of the target region, a result of identifying the target object by the non-shielding region is output.
Alternatively, if 1 living target object in the target area is recognized, the recognized living target object may be defined as a target object to be tracked and detected, and the person is tracked and detected, and a tracking detection result is output, and if more than 1 living target object in the target area is recognized, it may be understood that target objects other than the target object to be tracked and detected are included in the target area, and tracking detection may be performed on all target objects in the target area, but the tracking result is not output at this time.
In the embodiment of the invention, if the detection number of the target objects of the two frames of images before and after the image acquired by video recording the target area changes suddenly, the tracking algorithm skips the detection result and directly predicts the target position and number in the next frame of image according to the target track.
The following describes a technical solution of the tracking detection method for the target object by an optional embodiment, but the technical solution of the embodiment of the present invention is not limited to the following, and the method includes the following steps:
in an optional embodiment of the present invention, taking a target object to be tracked and detected as a human body of a teacher as an example, a specific scheme is as follows:
in an optional embodiment of the present invention, the human body detection module detects whether a human body is present on the platform (corresponding to the target area in the above embodiment), and determines whether the human body is present in the shielding area. When the human body appears in the shielding area, the living body detection module is adopted to judge whether the face appearing in the area is a living body. And then, a multi-target tracking module is adopted to smooth the human body detection result, so that the error switching of the close-up function and the non-close-up function in the recording and broadcasting process caused by the human body quantity mutation caused by human body false detection or missing detection is prevented.
In the related technology, when only one teacher appears on the platform, the teacher can be closed up while recording and broadcasting; the function of exiting the feature only makes a recording when there is no person or more than one person on the platform. The method can more clearly show the teaching content, thereby improving the quality of teaching recording and broadcasting. However, in an actual teaching scene, a teacher can perform teaching activities by means of multimedia equipment, and the rich multimedia content often contains some character pictures or videos. When the existing target detection method is used only singly to detect people for teachers, false people appearing in multimedia can be detected at the same time, and in this case, close-up of teachers is not facilitated. Meanwhile, the existing target detection methods cannot realize 100% accurate detection, and both false detection and missed detection occur to a certain extent, which causes frequent false switching of recorded broadcast pictures between close-up and non-close-up and influences the recorded broadcast quality, and in order to solve the technical scheme, the optional embodiment of the invention provides the following technical scheme:
based on the main process of the above embodiment of the present invention, a detailed technical solution provided by an alternative embodiment of the present invention is as follows, as shown in fig. 6, including the following steps:
step S602, inputting the result of the previous task into the human body detection module, where the previous task may specifically refer to an image acquired by the image acquisition device through the intercom station, that is, inputting the image into the human body detection module.
The human body detection module is mainly composed of a target detection method based on deep learning. According to the proposal, the network structure of the increment-respet is pruned and modified, then a YOLO detection layer is connected to classify and position the human body, the modified network model can realize the real-time detection effect, and the network structure is shown in figure 3.
The network structure shown in fig. 3 mainly comprises a residual error cascade module, an inclusion-respet module and a YOLO detection layer, and the existing Stem module and Reduction module in the inclusion-respet network are removed. The residual error cascading modules 1, 2 and 3 are respectively obtained by cascading 10-layer, 6-layer and 2-layer residual error structures, and the main function is to deepen the network and simultaneously reduce the calculation amount. The Incep-respet module can obtain sparse or non-sparse characteristics on the same layer, can accelerate training and improve network performance. An inclusion-rest module is connected with a YOLO layer for classification and positioning, a deep learning target detection network structure based on regression is finally constructed, a neural network model is used for detecting whether a human body appears on a platform or not, and whether the human body appears in a shielding area or not is judged. When a human body appears in the shielding area, live body and non-live body classification is carried out on the human face appearing in the shielding area, and accurate detection on the real human body is achieved.
Step S604, the target position and the type output by the human body detection module are determined. If the output target position is located in the non-shielding area, directly outputting the detection result to the next-stage task; otherwise, the detection result needs to be input into the living body detection module in the third step.
It should be noted that the shielding areas of the above embodiments are mainly multimedia teaching display screens and projector projection areas appearing in images, as shown in fig. 4 and fig. 5. The shielding region is provided from the exterior of the teacher detection module, and meanwhile, a shielding region validity identifier is provided, wherein when the identifier is invalid, the platform is not provided with the shielding region; otherwise, judging that the shielding area exists.
Step S606, the detection result of the human body detection module is input into the living body detection module.
The function of the living body detection module of the embodiment of the invention is realized by a traditional detection method, for example, the multi-level LBP (Line Spectrum Pair) feature of a face image in an HSV (Hue validation) space and the LPQ (Local Phase quantification) feature of a YCbCr space can be subjected to feature fusion through histogram connection operation, and the fusion features are input into an SVM classifier to carry out two-classification of a living body and a non-living body.
And step S608, inputting the final human body detection result into the multi-target tracking module.
The multi-target tracking module adopts a multi-target tracking algorithm based on track prediction. The proposal uses a Kalman filtering method to track all human body targets appearing on the platform and predict the tracks thereof according to the human body detection result. When no human body appears, the tracking module does not output any data; when only one person appears, tracking the person and outputting a tracking result; when the number of people is more than 1, namely, when students appear on the platform, the numbers of people on the platform can be marked respectively and tracked simultaneously, and only the number of people on the platform is output but the tracking result is not output. If the human body detection number of the two frames of images is suddenly changed, the tracking algorithm skips the human body detection result, and directly predicts the target position and number in the next frame of image according to the target track, thereby playing the role of smoothing the detection result. In specific implementation, certain scenes can be compared according to the height, for example, in a low-age education scene, the detection result with the highest height (the height can be detected according to the vertical direction) is used as the teacher detection result, a multi-target tracking algorithm based on track prediction is used, the detection result of human body detection is combined, the human body on a platform is tracked and track prediction is carried out, and the error switching of the feature function is avoided.
Step S610, inputting the detection result of the teacher detection module into a next-level task, specifically, the next-level task may be a subsequent operation of recording or relaying the teacher.
According to the technical scheme of the optional embodiment of the invention, by utilizing the characteristics that image quality distortion inevitably occurs in a character picture or a video projected and projected by a multimedia device, and obvious differences occur in the characteristics of color, texture and the like, living bodies and non-living bodies are classified by performing texture characteristic analysis on human face images in different color spaces, so that the human body false detection rate is reduced, and the real human body is prevented from being filtered.
In addition, the optional embodiment of the invention tracks all human body targets appearing on the platform and predicts the tracks by adopting a multi-target tracking algorithm, and can also smooth the human body detection result when the human body detection result changes suddenly, thereby preventing the error switching of close-up function and non-close-up function in the recording and broadcasting process caused by sudden change.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method according to the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a tracking detection apparatus for a target object is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and details of which have been already described are not repeated. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 7 is a block diagram of a structure of a tracking detection apparatus of a target object according to an embodiment of the present invention, as shown in fig. 7,
a detection module 70, configured to detect a target area;
the processing module 72 is configured to, when it is detected that a target object exists in a shielded area of the target area, detect whether the target object in the shielded area is a living body, and obtain a detection result;
and the determining module 74 is configured to determine whether to perform tracking detection on the target object in the shielding region according to the detection result.
According to the technical scheme, under the condition that the target object exists in the shielding region of the target region, whether the target object in the shielding region is a living body is detected, and a detection result is obtained; the technical scheme is adopted to solve the problems that in the related technology, in the target detection process, a false target object cannot be completely identified, so that the target detection method is inaccurate, and the like, and under the condition that a possible false target object is identified, whether the identified false target object is a living body is determined, so that whether the target object is tracked and identified is determined, and the accuracy of tracking and detecting the target object is improved.
In an embodiment of the present invention, as shown in fig. 8, the detecting module 70 includes: an acquiring unit 700 configured to acquire an image obtained by recording a target area; an identification unit 702 is configured to identify a target object in the image.
In this embodiment of the present invention, the identifying unit 702 is further configured to identify the image through a deep-learning network model, where a structure of the deep-learning network model sequentially includes: a residual error cascade module, an inclusion-Resnet module and a YOLO detection layer; and determining the target object in the image according to the recognition result.
In an embodiment of the present invention, the apparatus further includes: the setting module 76 is further configured to set a mark for a shielding region in the image, where in a case that the mark exists in the image, it is determined that the shielding region exists in the image, and in a case that the mark does not exist in the image, it is determined that the shielding region does not exist in the image.
In an embodiment of the present invention, the apparatus further includes: the setting module 76 is further configured to, when it is detected that a target object exists in a non-shielding region of the target region, output a result that the target object is identified by the non-shielding region.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are located in different processors in any combination.
An embodiment of the present invention further provides a storage medium including a stored program, wherein the program executes any one of the methods described above.
Alternatively, in the present embodiment, the storage medium may be configured to store program codes for performing the following steps:
s1, detecting a target area;
s2, under the condition that a target object exists in a shielding area of the target area, detecting whether the target object in the shielding area is a living body or not to obtain a detection result;
and S3, determining whether to track and detect the target object in the shielding area according to the detection result.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Optionally, for a specific example in this embodiment, reference may be made to the examples described in the above embodiment and optional implementation, and this embodiment is not described herein again.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, detecting a target area;
s2, under the condition that a target object exists in a shielding area of the target area, detecting whether the target object in the shielding area is a living body or not to obtain a detection result;
and S3, determining whether to track and detect the target object in the shielding area according to the detection result.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A tracking detection method of a target object is characterized by comprising the following steps:
detecting a target area;
under the condition that a target object exists in a shielding area of the target area, detecting whether the target object in the shielding area is a living body or not to obtain a detection result, wherein the shielding area comprises: at least one of a display screen or a projection area;
determining whether to track and detect the target object in the shielding area according to the detection result;
wherein, detecting the target area comprises:
acquiring an image obtained by video recording of a target area;
identifying a target object in the image;
after obtaining an image obtained by video recording of the target area, the method further includes:
setting a mark for a shielding region in the image, wherein if the mark exists in the image, the shielding region is determined to exist in the image, and if the mark does not exist in the image, the shielding region is determined not to exist in the image;
wherein, after identifying the target object in the image, the method further comprises:
in a case where it is recognized that the number of target objects that are living bodies in the target region is plural, a tracking result of the plural target objects is not output.
2. The method of claim 1, wherein identifying a target object in the image comprises:
identifying the image through a deep-learning network model, wherein the structure of the deep-learning network model sequentially comprises: a residual error cascade module, an inclusion-Resnet module and a YOLO detection layer;
and determining the target object in the image according to the recognition result.
3. The method of claim 1, wherein after detecting the target region, the method further comprises:
and under the condition that a target object exists in a non-shielding area of the target area, outputting a result that the target object is identified by the non-shielding area.
4. An apparatus for tracking and detecting a target object, comprising:
the detection module is used for detecting the target area;
a processing module, configured to detect whether a target object in a shielded region of the target region is a living body when it is detected that the target object exists in the shielded region, and obtain a detection result, where the shielded region includes: at least one of a display screen or a projection area;
the determining module is used for determining whether to track and detect the target object in the shielding area according to the detection result;
wherein, the detection module includes:
an acquisition unit configured to acquire an image obtained by video recording of a target area;
an identification unit configured to identify a target object in the image;
the acquiring unit is further configured to set a mark for a mask region in the image, where if the mark exists in the image, it is determined that the mask region exists in the image, and if the mark does not exist in the image, it is determined that the mask region does not exist in the image;
wherein the identification unit is further configured not to output a tracking result of the plurality of target objects when it is identified that the number of target objects that are living bodies in the target region is plural.
5. The apparatus according to claim 4, wherein the identifying unit is further configured to identify the image through a deep-learned network model, and a structure of the deep-learned network model sequentially includes: a residual error cascade module, an inclusion-Resnet module and a YOLO detection layer; and determining the target object in the image according to the recognition result.
6. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to carry out the method of any one of claims 1 to 3 when executed.
7. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911067409.4A CN110866473B (en) | 2019-11-04 | 2019-11-04 | Target object tracking detection method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911067409.4A CN110866473B (en) | 2019-11-04 | 2019-11-04 | Target object tracking detection method and device, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110866473A CN110866473A (en) | 2020-03-06 |
| CN110866473B true CN110866473B (en) | 2022-11-18 |
Family
ID=69653441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911067409.4A Active CN110866473B (en) | 2019-11-04 | 2019-11-04 | Target object tracking detection method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866473B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860415A (en) * | 2020-07-29 | 2020-10-30 | 浙江大华技术股份有限公司 | Cough detection method, device, storage medium and electronic device |
| CN112069969B (en) * | 2020-08-31 | 2023-07-25 | 河北省交通规划设计研究院有限公司 | Expressway monitoring video cross-mirror vehicle tracking method and system |
| CN112766397B (en) * | 2021-01-27 | 2023-12-05 | 歌尔股份有限公司 | Classification network and implementation method and device thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699469A (en) * | 2009-11-09 | 2010-04-28 | 南京邮电大学 | Method for automatically identifying action of writing on blackboard of teacher in class video recording |
| CN105306861A (en) * | 2015-10-15 | 2016-02-03 | 深圳市时尚德源文化传播有限公司 | Online teaching recording and playing method and system |
| CN106231223A (en) * | 2016-09-22 | 2016-12-14 | 广州东文信息科技有限公司 | A kind of automatic body follows the tracks of recorded broadcast equipment, system and method |
| CN107452018A (en) * | 2017-08-02 | 2017-12-08 | 北京翰博尔信息技术股份有限公司 | Speaker's tracking and system |
| CN108171204A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Detection method and device |
| CN108764126A (en) * | 2018-05-25 | 2018-11-06 | 郑州目盼智能科技有限公司 | A kind of embedded living body faces tracking system |
| CN109117794A (en) * | 2018-08-16 | 2019-01-01 | 广东工业大学 | A kind of moving target behavior tracking method, apparatus, equipment and readable storage medium storing program for executing |
| CN109492551A (en) * | 2018-10-25 | 2019-03-19 | 腾讯科技（深圳）有限公司 | The related system of biopsy method, device and application biopsy method |
| CN109920076A (en) * | 2019-01-29 | 2019-06-21 | 上海阅面网络科技有限公司 | A kind of campus human face identification work-attendance checking system |
-
2019
- 2019-11-04 CN CN201911067409.4A patent/CN110866473B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699469A (en) * | 2009-11-09 | 2010-04-28 | 南京邮电大学 | Method for automatically identifying action of writing on blackboard of teacher in class video recording |
| CN105306861A (en) * | 2015-10-15 | 2016-02-03 | 深圳市时尚德源文化传播有限公司 | Online teaching recording and playing method and system |
| CN106231223A (en) * | 2016-09-22 | 2016-12-14 | 广州东文信息科技有限公司 | A kind of automatic body follows the tracks of recorded broadcast equipment, system and method |
| CN107452018A (en) * | 2017-08-02 | 2017-12-08 | 北京翰博尔信息技术股份有限公司 | Speaker's tracking and system |
| CN108171204A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Detection method and device |
| CN108764126A (en) * | 2018-05-25 | 2018-11-06 | 郑州目盼智能科技有限公司 | A kind of embedded living body faces tracking system |
| CN109117794A (en) * | 2018-08-16 | 2019-01-01 | 广东工业大学 | A kind of moving target behavior tracking method, apparatus, equipment and readable storage medium storing program for executing |
| CN109492551A (en) * | 2018-10-25 | 2019-03-19 | 腾讯科技（深圳）有限公司 | The related system of biopsy method, device and application biopsy method |
| CN109920076A (en) * | 2019-01-29 | 2019-06-21 | 上海阅面网络科技有限公司 | A kind of campus human face identification work-attendance checking system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866473A (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sajid et al. | Universal multimode background subtraction | |
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| Jung | Efficient background subtraction and shadow removal for monochromatic video sequences | |
| CN110866473B (en) | Target object tracking detection method and device, storage medium and electronic device | |
| CN109690624A (en) | Automatic scene calibration method for video analysis | |
| CN109472193A (en) | Method for detecting human face and device | |
| CN110659391A (en) | Video detection method and device | |
| CN106651797B (en) | Method and device for determining effective area of signal lamp | |
| CN111311475A (en) | Detection model training method and device, storage medium and computer equipment | |
| CN111061898A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN104145477B (en) | Adjust the method and system of color | |
| Delussu et al. | Scene-specific crowd counting using synthetic training images | |
| CN109740527B (en) | Image processing method in video frame | |
| CN112686122B (en) | Human body and shadow detection method and device, electronic equipment and storage medium | |
| CN114040094A (en) | Method and equipment for adjusting preset position based on pan-tilt camera | |
| CN111160340B (en) | Moving object detection method and device, storage medium and terminal equipment | |
| CN113255685A (en) | Image processing method and device, computer equipment and storage medium | |
| CN109919164B (en) | User interface object identification method and device | |
| CN116824641A (en) | Gesture classification method, device, equipment and computer storage medium | |
| CN116612355A (en) | Training method and device for face fake recognition model, face recognition method and device | |
| CN111988520B (en) | Picture switching method and device, electronic equipment and storage medium | |
| CN114170271A (en) | Multi-target tracking method with self-tracking consciousness, equipment and storage medium | |
| CN116546304A (en) | Parameter configuration method, device, equipment, storage medium and product | |
| CN115147818A (en) | Method and device for identifying mobile phone playing behaviors | |
| CN111027560B (en) | Text detection method and related device |
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 |