CN112329611A - Target detection method and device, electronic equipment and storage medium - Google Patents
Target detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112329611A CN112329611A CN202011211283.6A CN202011211283A CN112329611A CN 112329611 A CN112329611 A CN 112329611A CN 202011211283 A CN202011211283 A CN 202011211283A CN 112329611 A CN112329611 A CN 112329611A
- Authority
- CN
- China
- Prior art keywords
- target object
- target
- image
- model
- monitoring
- 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 72
- 238000012544 monitoring process Methods 0.000 claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000013136 deep learning model Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 description 19
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000012806 monitoring device Methods 0.000 description 5
- 210000000746 body region Anatomy 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a target detection method, a target detection device, target detection equipment and a target detection medium. The method comprises the following steps: acquiring a monitoring image; detecting the monitoring image; under the condition that the monitored image comprises the target object, carrying out element identification on the target object in the monitored image based on an element identification model; the element recognition model is obtained by training a deep learning model based on a target sample and a similar sample of the target sample. So as to realize high-precision identification of the elements of the target object.
Description
Technical Field
The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a target detection method, a target detection device, electronic equipment and a storage medium.
Background
With the development of computer vision technology, new requirements are made for identifying elements (such as dresses) of a target object (such as a person). For example, in an electric power material detection center, detection personnel need to strictly comply with dressing regulations to ensure operation safety.
The dress of current electric power material measurement personnel need rely on the artifical judgement of monitoring personnel, only stops at the ability level of "remote monitoring", can't carry out intelligent analysis and judge. And electric power material detection center has area big, the less characteristics of staff, if monitor through the manual work, then need more monitoring personnel to come to carry out the operation control to a small amount of personnel, cause a large amount of personnel extravagantly. At present, some dressing detection researches based on images are available, but the dressing detection researches can be realized under ideal conditions and still have a certain distance from practical application.
Disclosure of Invention
The embodiment of the invention provides a target detection method, a target detection device, electronic equipment and a storage medium, and aims to realize high-precision identification of elements of a target object.
In a first aspect, an embodiment of the present invention provides a target detection method, including:
acquiring a monitoring image;
detecting the monitoring image;
under the condition that the monitored image comprises the target object, carrying out element identification on the target object in the monitored image based on an element identification model; the element recognition model is obtained by training a deep learning model based on a target sample and a similar sample of the target sample.
In a second aspect, an embodiment of the present invention provides an object detection apparatus, including:
the image acquisition module is used for acquiring a monitoring image;
the image detection module is used for detecting the monitoring image;
the element identification module is used for carrying out element identification on the target object in the monitored image based on an element identification model under the condition that the monitored image comprises the target object; the element recognition model is obtained by training a deep learning model based on a target sample and a similar sample of the target sample.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of object detection as in any embodiment of the invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements an object detection method according to any embodiment of the present invention.
According to the technical scheme provided by the embodiment of the invention, the element recognition model obtained by training similar samples based on the target sample and the target sample is introduced, and the element recognition is carried out on the target object in the monitored image based on the element recognition model under the condition that the monitored image obtained in real time includes the target object. Compared with the existing dressing detection method based on images, if object features are extracted through image edge detection, the hidden features of deeper layers of objects in the images can be extracted based on deep learning, and meanwhile, similar samples of target samples are introduced to train the model, so that more accurate detection results can be realized.
Drawings
Fig. 1 is a flowchart of a target detection method according to an embodiment of the present invention;
fig. 2 is a flowchart of a target detection method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a target detection method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an object detection apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the embodiments of the invention and that no limitation of the invention is intended. It should be further noted that, for convenience of description, only some structures, not all structures, relating to the embodiments of the present invention are shown in the drawings.
Example one
Fig. 1 is a flowchart of a target detection method according to an embodiment of the present invention, where this embodiment is applicable to a situation of detecting an element of a target object, and this embodiment and subsequent embodiments will be described by taking, as an example, a target object as an electric power material detector and an element as an electric power material detector, but are not limited to this. The method may be performed by the object detection apparatus provided in the embodiment of the present invention, and the apparatus may be implemented in a hardware and/or software manner, and may be integrated in an electronic device carrying an object detection function, such as a server device.
The target detection method as shown in fig. 1 includes:
and S110, acquiring a monitoring image.
In this embodiment, the monitoring image may be obtained from a monitoring device (e.g., a monitor) in real time; furthermore, a communication connection may be established with the monitoring device through an Application Programming Interface (API), so as to obtain a monitoring video stream acquired by the monitoring device in real time from the monitoring device, and further intercept the monitoring image from the monitoring video stream. Optionally, one or more frames of images may be randomly acquired from the monitoring video stream as the monitoring image; alternatively, a frame number may be set in advance, and a video frame having the same number as the set frame number in the surveillance video stream may be used as the surveillance image.
And S120, detecting the monitoring image.
Optionally, the monitoring image may be detected by an image recognition technology to determine whether a target object exists in the monitoring image, where the target object may be a person, and specifically may be an electric power material detector. It should be noted that one monitoring image may not include the target object, and may also include the target object. Further, in a case where one monitoring image includes a target object, the number of the target objects included in the monitoring image may be one or a plurality of.
S130, under the condition that the target object is detected to be included in the monitored image, element recognition is carried out on the target object in the monitored image based on the element recognition model.
Alternatively, the elements may be different in different scenarios. For example, when the target object is an electric power material detector, the element is the dressing of the electric power material detector, and may specifically include a safety helmet, a tool, and the like. Further, in some scenarios, such as a target object tracking scenario, the element may also be a fingerprint of the target object, etc.
In this embodiment, the element recognition model is obtained by training a deep learning model based on a target sample and a similar sample of the target sample. Optionally, in a scene of identifying the wearing of the power material detection personnel, the target sample may include images of personnel wearing a safety helmet and wearing a tool, which are captured from a monitoring device history collection to a monitoring video stream, and may also include images of personnel wearing a safety helmet and wearing a tool, which are captured by a device such as a mobile phone or a camera; it should be noted that the safety helmet worn by the staff and the worn tool in the target sample are issued by the electric power material mechanism for the staff; further, the dresses of all the personnel of the electric power supply organization can be the same, or all the personnel of the electric power supply organization can be classified into different grades, the dresses of the personnel of different grades are different, and the target sample can relate to the dresses of the personnel of all the grades. In addition, the personnel in the target sample are a safety helmet and a tool which are worn according to the dressing requirements of the personnel of the electric power material mechanism.
The similar samples of the target sample may include images of persons wearing safety helmets similar to safety helmets issued by the electric power material mechanism for employees and/or wearing tools similar to tools issued by the electric power material mechanism for employees. In the embodiment, a training sample set is formed by the target sample and the similar sample of the target sample, and the deep learning model is trained to obtain the element recognition model. Optionally, the deep learning model in this embodiment may be a Single Shot Multi Box Detector (SSD) model.
Illustratively, in the case that the target object is detected to be included in the monitored image, whether the target object in the monitored image is worn by a safety helmet or worn by a tool is identified by using the element identification model. Further, in the case that it is detected that the target object is not included in the monitored image, the monitored image may be acquired from the monitored video stream again, and S120 and S130 in this embodiment are executed; alternatively, the undetected related information may be directly output.
Optionally, the target samples and the similar samples in this embodiment may be labeled, and for the target samples, the label in each target sample may include a "standard hat" and a "standard tool"; for similar samples, the label in each similar sample may include a "similar hat" and/or a "similar tool". Further, when the target object is detected to be included in the monitored image, the monitored image may be input into an element recognition model, and the element recognition model may output a tag result, which may be, for example, one of "standard hat", "standard tool", "standard hat" and "standard tool", "similar hat", "similar tool", and "similar hat" and "similar tool"; and determining the conditions of wearing the safety helmet and wearing the tool by the target object in the monitoring image according to the label result.
According to the technical scheme provided by the embodiment of the invention, the element recognition model obtained by training similar samples based on the target sample and the target sample is introduced, and the element recognition is carried out on the target object in the monitored image based on the element recognition model under the condition that the monitored image obtained in real time includes the target object. Compared with the existing dressing detection method based on images, if object features are extracted through image edge detection, the hidden features of deeper layers of objects in the images can be extracted based on deep learning, and meanwhile, similar samples of target samples are introduced to train the model, so that more accurate detection results can be realized.
Example two
Fig. 2 is a flowchart of a target detection method according to a second embodiment of the present invention, which is optimized based on the second embodiment.
Further, the operation of "detecting the monitoring image" is embodied as "detecting the monitoring image based on the object detection model" to improve the detection speed and precision. Performing element recognition on the target object in the monitored image based on the element recognition model when the operation that the target object is detected to be included in the monitored image is performed, specifically intercepting a target area including the target object from the monitored image when the operation that the target object is included in the monitored image is detected; wherein the target area is smaller than the area of the monitoring image; and performing element recognition on the target object in the target area based on the element recognition model to improve the recognition speed and accuracy.
The target detection method as shown in fig. 2 includes:
and S210, acquiring a monitoring image.
And S220, detecting the monitoring image based on the object detection model.
Wherein the object detection model is a CenterNet model.
Illustratively, the object detection model in the present embodiment is determined by: firstly, carrying out standardization processing on a series of training image samples, and marking human body regions in the images; and inputting the marked images into an initial CenterNet model, continuously adjusting parameters of the model by the model through characteristic learning of the calibration region, and finally realizing effective identification of the human body region in any image, wherein the trained CenterNet model, namely the object detection model, can be obtained.
The marking of the human body region in the image can be realized by marking the coordinates of the region block diagram where the human body is located in a coordinate form, associating the coordinates with the image, and inputting the coordinates and the image into the initial CenterNet model. Optionally, the block diagram of the area where the human body is located may be a triangle or a rectangle, and if the triangle is located, the coordinates of three vertices of the triangle are recorded, and if the rectangle is located, the coordinates of four vertices of the rectangle are recorded.
It can be understood that the speed and accuracy of detecting the target object can be improved by using the centrnet model to detect the monitoring image.
And S230, under the condition that the target object is detected to be included in the monitored image, intercepting a target area including the target object from the monitored image.
Illustratively, when it is detected that the monitored image includes the target object, the monitored image is intercepted according to the area where the target object is located in the monitored image, and the target area can be obtained. The method has the advantages that the scale of the image in the element identification link of the subsequent target object can be reduced through interception, so that the calculation amount is reduced, and the calculation processing speed is increased.
And S240, carrying out element recognition on the target object in the target area based on the element recognition model.
For example, after a target region including a target object is cut out from a monitoring image, the target region may be subjected to a normalization process; the normalization process is to resize the target area image to a size necessary for the element recognition model input. And inputting the standardized target area into an element recognition model for element recognition, wherein the output of the model can be a label result, namely the recognition result, namely the situation of wearing a safety helmet and a tool.
According to the technical scheme provided by the embodiment of the invention, the object detection model is introduced to detect the monitored image, the part of the monitored image including the target object is intercepted, and the scale of the image in the subsequent detection link can be reduced through interception, so that the calculation amount is reduced; then, the element identification of the target object is carried out based on the element identification model, and under the scene of identifying the dressing of the electric power material detection personnel, the detection precision of whether the personnel wear safety helmets or not and whether the personnel wear tools or not can be improved, so that the working pressure of monitoring personnel is reduced, and the comprehensive real-time intelligent safety monitoring of the electric power material detection work is realized.
EXAMPLE III
Fig. 3 is a flowchart of a target detection method provided by a third embodiment of the present invention, and optimization is performed based on the above embodiments.
Further, after the target object in the monitoring picture is subjected to element identification, operation is added, and whether the elements of the target object meet the set judgment standard or not is determined according to the identification result; if not, alarm information is output to judge the detection result and give an alarm.
The target detection method as shown in fig. 3 includes:
and S310, acquiring a monitoring image.
And S320, detecting the monitoring image based on the object detection model.
S330, under the condition that the target object is detected to be included in the monitored image, element recognition is carried out on the target object in the monitored image based on the element recognition model.
And S340, determining whether the elements of the target object meet the set judgment standard or not according to the recognition result.
In this embodiment, in a scene of identifying dresses of electric power material detection personnel, the evaluation criterion refers to a basic requirement that a worker who is set by an electric power material mechanism wears a safety helmet and wears a tool when entering a work place.
Optionally, after the target object is identified, and according to the identification result, whether an element of the target object meets a set criterion is determined. If the fact that the person wears the safety helmet and wears the tool is detected, the area where the person is located can be framed and displayed in a green frame.
Optionally, the monitoring images acquired in real time are at least two frames, and if the at least two frames of monitoring images include the same target object, the driving direction of the target object is determined according to the at least two frames of monitoring images; correspondingly, according to the recognition result, determining whether the element of the target object meets the set judgment standard comprises the following steps: and determining whether the elements of the target object meet the set judgment standard or not according to the driving direction and the recognition result.
For example, if the detected at least two frames of monitored images include the same target object, the driving direction of the target object is determined. If the driving direction of the target object enters the working site, and the safety helmet and the tool are worn, and/or the driving direction of the target object leaves the working site, and the safety helmet is not worn and the tool is not worn, the judgment standard is met; and if the target object enters the working site in the driving direction, and the safety helmet is not worn or the tool is not worn, the judgment standard is not met.
And S350, if the condition is not met, outputting alarm information.
For example, if it is determined that the element of the target object does not meet the set judgment standard, that is, it is detected that the person does not wear a safety helmet or a tool, the region where the person is located is framed and displayed in a red frame, and an alarm message is issued to remind the manager. The alarm information can be an alarm in the form of continuous flashing of the indicator light, an alarm in the form of alarm sound, an alarm in the form of flashing of the indicator light and alarm sound at the same time, and the like.
According to the technical scheme provided by the embodiment of the invention, under the scene of identifying the dressing of the electric power material detection personnel, the alarm can be timely sent to the monitoring personnel according to whether the identification result meets the set judgment standard, so that the function of timely reminding is achieved, meanwhile, the situation that the personnel who do not wear the safety helmet and wear the tool enter the working site can be effectively avoided, and the occurrence of safety accidents is reduced.
Example four
The structure schematic diagram of the target detection device provided by the fourth embodiment of the present invention is applicable to a situation of detecting an element of a target object (for example, detecting the wearing of an electric power material detector), and the device can be implemented in a hardware and/or software manner and can be integrated into an electronic device bearing a target detection function, for example, a server device.
The object detection apparatus shown in fig. 4 comprises an image acquisition module 410, an image detection module 420 and a target object element identification module 430, wherein,
an image acquisition module 410, configured to acquire a monitoring image;
an image detection module 420, configured to detect a monitoring image;
the element identification module 430 is configured to, in a case that it is detected that the target object is included in the monitored image, perform element identification on the target object in the monitored image based on the element identification model; the element recognition model is obtained by training a deep learning model based on the target sample and the similar sample of the target sample.
According to the technical scheme provided by the embodiment of the invention, the element recognition model obtained by training similar samples based on the target sample and the target sample is introduced, and the element recognition is carried out on the target object in the monitored image based on the element recognition model under the condition that the monitored image obtained in real time includes the target object. Compared with the existing dressing detection method based on images, if object features are extracted through image edge detection, the hidden features of deeper layers of objects in the images can be extracted based on deep learning, and meanwhile, similar samples of target samples are introduced to train the model, so that more accurate detection results can be realized.
Further, the element recognition module 430 includes a target region intercepting unit and an element recognition unit, wherein,
a target area intercepting unit for intercepting a target area including a target object from the monitored image, in a case where it is detected that the target object is included in the monitored image; wherein the target area is smaller than the area of the monitoring image;
and the element identification unit is used for carrying out element identification on the target object in the target area based on the element identification model.
Further, the image detection module 420 is specifically configured to detect the monitored image based on the object detection model; wherein the object detection model is a CenterNet model.
Further, the apparatus further includes an identification result determination module, where the identification result determination module is configured to:
determining whether the elements of the target object meet the set judgment standard or not according to the recognition result;
if not, alarm information is output.
Further, the device also comprises
The driving direction determining module is used for determining the driving direction of the target object according to the at least two frames of monitoring images if the at least two frames of monitoring images comprise the same target object;
correspondingly, the identification result judging module is further used for determining whether the elements of the target object meet the set judgment standard according to the driving direction and the identification result.
The object detection device can execute the object detection method provided by any embodiment of the application, and has corresponding functional modules and beneficial effects for executing the object detection method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, and fig. 5 shows a block diagram of an exemplary device suitable for implementing the embodiment of the present invention. The device shown in fig. 5 is only an example and should not bring any limitation to the function and the scope of use of the embodiments of the present invention. The device may be a user device, a computer, a server device, etc.
As shown in FIG. 5, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of embodiments described herein.
Device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with device 12, and/or with any devices (e.g., network card, modem, etc.) that enable device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with the other modules of the device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing, for example, implementing an object detection method provided by an embodiment of the present invention, by executing a program stored in the system memory 28.
EXAMPLE six
The sixth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program (or referred to as computer-executable instructions) is stored, where the computer program is used for executing the object detection method provided by the embodiment of the present invention when executed by a processor, and the computer-readable storage medium includes:
acquiring a monitoring image;
detecting the monitoring image;
under the condition that the target object is detected to be included in the monitored image, element recognition is carried out on the target object in the monitored image based on an element recognition model; the element recognition model is obtained by training a deep learning model based on the target sample and the similar sample of the target sample.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the embodiments of the present invention have been described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and many other equivalent embodiments may be included without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (8)
1. A method of object detection, comprising:
acquiring a monitoring image;
detecting the monitoring image;
under the condition that the monitored image comprises the target object, carrying out element identification on the target object in the monitored image based on an element identification model; the element recognition model is obtained by training a deep learning model based on a target sample and a similar sample of the target sample.
2. The method according to claim 1, wherein in a case that it is detected that a target object is included in the monitored image, performing element recognition on the target object in the monitored image based on an element recognition model includes:
intercepting a target area including a target object from the monitoring image under the condition that the target object is detected to be included in the monitoring image; wherein the target area is smaller than the area of the monitoring image;
and carrying out element recognition on the target object in the target area based on an element recognition model.
3. The method of claim 1, wherein detecting the monitoring image comprises:
detecting the monitoring image based on an object detection model; wherein the object detection model is a centret model.
4. The method of claim 1, wherein after performing element recognition on the target object in the monitored image, further comprising:
determining whether the elements of the target object meet set judgment criteria or not according to the recognition result;
if not, alarm information is output.
5. The method of claim 1, wherein if the monitored image has at least two frames, after detecting the monitored image, further comprising:
if the at least two frames of monitoring images comprise the same target object, determining the driving direction of the target object according to the at least two frames of monitoring images;
correspondingly, according to the recognition result, determining whether the element of the target object meets the set judgment standard includes:
and determining whether the elements of the target object meet set judgment criteria or not according to the driving direction and the recognition result.
6. An object detection device, comprising:
the image acquisition module is used for acquiring a monitoring image;
the image detection module is used for detecting the monitoring image;
the element identification module is used for carrying out element identification on the target object in the monitored image based on an element identification model under the condition that the monitored image comprises the target object; the element recognition model is obtained by training a deep learning model based on a target sample and a similar sample of the target sample.
7. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the object detection method of any of claims 1-5.
8. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the object detection method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011211283.6A CN112329611A (en) | 2020-11-03 | 2020-11-03 | Target detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011211283.6A CN112329611A (en) | 2020-11-03 | 2020-11-03 | Target detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112329611A true CN112329611A (en) | 2021-02-05 |
Family
ID=74323434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011211283.6A Pending CN112329611A (en) | 2020-11-03 | 2020-11-03 | Target detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329611A (en) |
-
2020
- 2020-11-03 CN CN202011211283.6A patent/CN112329611A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| 郝存明等: ""基于深度学习的安全帽检测方法研究"", 《河北省科学院学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807429A (en) | Construction safety detection method and system based on tiny-YOLOv3 | |
| CN111598040B (en) | Construction worker identity recognition and safety helmet wearing detection method and system | |
| CN109887234B (en) | Method and device for preventing children from getting lost, electronic equipment and storage medium | |
| CN206672041U (en) | A kind of mining equipment intelligent patrol detection based on augmented reality and safeguard accessory system | |
| CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
| CN107948585A (en) | Video recording labeling method, device and computer-readable recording medium | |
| CN110889339A (en) | Head and shoulder detection-based dangerous area grading early warning method and system | |
| RU2713876C1 (en) | Method and system for detecting alarm events when interacting with self-service device | |
| CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
| CN113269142A (en) | Method for identifying sleeping behaviors of person on duty in field of inspection | |
| CN113011280A (en) | Method and device for detecting person contact distance, computer equipment and storage medium | |
| CN113255516A (en) | Living body detection method and device and electronic equipment | |
| CN112949457A (en) | Maintenance method, device and system based on augmented reality technology | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN111091104A (en) | Target object protection detection method, device, equipment and storage medium | |
| CN115759868A (en) | Forest inspection personnel management method, intelligent terminal and storage medium | |
| Jeelani et al. | Improving safety performance in construction using eye-tracking, visual data analytics, and virtual reality | |
| CN113314230A (en) | Intelligent epidemic prevention method, device, equipment and storage medium based on big data | |
| Rivera et al. | Work safety assessment through contextual analysis with computer vision | |
| CN112329611A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN114067283A (en) | Violation identification method and device, electronic equipment and storage medium | |
| CN112434560A (en) | Safety equipment real-time detection method and device based on deep learning | |
| CN113570622A (en) | Obstacle determination method and device, electronic equipment and storage medium | |
| CN112418140A (en) | Electric shock prevention alarm method and system for power distribution construction site | |
| CN111126771A (en) | Safety inspector image recognition quality supervision and guarantee system and method based on regional attention prediction |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210205 |
|
| RJ01 | Rejection of invention patent application after publication |