CN110084123A - Human body behavioral value method and system, computer readable storage medium - Google Patents
Human body behavioral value method and system, computer readable storage medium Download PDFInfo
- Publication number
- CN110084123A CN110084123A CN201910242524.4A CN201910242524A CN110084123A CN 110084123 A CN110084123 A CN 110084123A CN 201910242524 A CN201910242524 A CN 201910242524A CN 110084123 A CN110084123 A CN 110084123A
- Authority
- CN
- China
- Prior art keywords
- behavioral value
- image
- human body
- detected
- result
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
A kind of human body behavioral value method and system, computer readable storage medium, the human body behavioral value method, comprising: obtain image to be detected；Human body behavioral value is carried out to described image to be detected, behavioral value is obtained as a result, the behavioral value result comprises at least one of the following: probability that default behavior occurs, occur default behavior in described image to be detected time location, there is default behavior spatial position locating in described image to be detected, behavior type；Store the behavioral value result.Using the above scheme, it can be improved the validity that intelligent terminal utilizes image and video data.
Description
Technical field
The present embodiments relate to behavioral value technical field more particularly to a kind of human body behavioral value method and system,
Computer readable storage medium.
Background technique
Currently, occurring various being integrated with the intelligent terminal of camera, such as mobile phone, automatic teller machine, automatic vending in the market
Machine etc..Except with it is most basic take pictures and camera function in addition to, some intelligent terminals can also carry out Face datection, pedestrian detection
Deng.
However, intelligent terminal is lower to the utilization validity of institute's acquired image or video data.
Summary of the invention
The technical issues of embodiment of the present invention solves is that the validity that intelligent terminal utilizes image and video data is lower.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of human body behavioral value method, comprising: obtain to be checked
Altimetric image；Human body behavioral value is carried out to described image to be detected, obtains behavioral value as a result, the behavioral value result includes
Following at least one: there is the time location preset behavior in described image to be detected, occurs in the probability of default behavior appearance
Default behavior spatial position locating in described image to be detected, behavior type；Store the behavioral value result.
Optionally, the first behavior detection unit is suitable for carrying out described image to be detected following at least two types
Human body behavioral value, obtain the corresponding behavioral value result of human body behavioral value of at least two type: to it is described to
Detection image carries out feature extraction, obtains the characteristics of image of described image to be detected, described image feature includes following at least one
Kind: edge feature or corner feature；Characteristics of image based on described image to be detected carries out behavioral value, obtains feature extraction pair
The behavioral value result answered；Target detection is carried out to described image to be detected, positions and identifies target object；Based on what is identified
Target object carries out behavioral value, obtains the corresponding behavioral value result of target detection；Posture is carried out to described image to be detected
Detection, obtains the key point information of target object；Key point information based on the target object carries out behavioral value, obtains appearance
State identifies corresponding behavioral value result, wherein the key point comprises at least one of the following: wrist, palm, elbow, eyes,
Ankle；Human body positioning and identification are carried out to described image to be detected；According to the human body positioning and recognition result into
Row behavioral value obtains human body and detects corresponding behavioral value result.
Optionally, the first behavior detection unit, suitable for the corresponding row of behavioral value to following at least two type
It is merged for testing result, obtains the behavioral value result: the corresponding behavioral value result of feature extraction, target detection pair
The corresponding behavioral value result of behavioral value result, the gesture recognition answered, human body detect corresponding behavioral value result.
Optionally, the first behavior detection unit is suitable for using following at least one amalgamation mode to described at least two
The corresponding behavioral value result of the behavioral value of seed type is merged: ballot mode, mode of averaging, weighting scheme and selection
Property amalgamation mode.
Optionally, the intelligent terminal, further includes: the first image pre-processing unit, be suitable for described image to be detected into
Row image preprocessing obtains pretreated image, wherein described image pretreatment comprises at least one of the following: compression of images,
Image encryption, image enhancement, image restoration, image transformation.
Optionally, first storage unit is further adapted for storing pretreated image.
Optionally, first storage unit is further adapted for storing described image to be detected.
Optionally, the human body behavioral value system further include: the first receiving unit is suitable for receiving pre-association terminal and sends
Solicited message, the solicited message is for behavioral value result described in request.
Optionally, the human body behavioral value system further include: the first output unit is suitable for receiving in the receiving unit
To after the solicited message, the behavioral value result is exported to the pre-association terminal.
The embodiment of the present invention also provides another human body behavioral value system, comprising: intelligent terminal and server, wherein
The intelligent terminal, comprising: second acquisition unit, suitable for obtaining image to be detected and being sent to the server；The service
Device, comprising: the second behavioral value unit and the second storage unit, the second behavioral value unit are suitable for described to be detected
Image carries out human body behavioral value, obtains behavioral value as a result, the behavioral value result comprises at least one of the following: default row
It is the probability of appearance, time location of the default behavior in described image to be detected occurs, default behavior occur described to be checked
Locating spatial position, behavior type in altimetric image；Second storage unit is suitable for storing obtained behavioral value result.
Optionally, the second behavioral value unit is suitable for carrying out described image to be detected following at least two types
Human body behavioral value, obtain the corresponding behavioral value result of human body behavioral value of at least two type: to it is described to
Detection image carries out feature extraction, obtains the characteristics of image of described image to be detected, described image feature includes following at least one
Kind: edge feature or corner feature；Characteristics of image based on described image to be detected carries out behavioral value, obtains feature extraction pair
The behavioral value result answered；Target detection is carried out to described image to be detected, positions and identifies target object；Based on what is identified
Target object carries out behavioral value, obtains the corresponding behavioral value result of target detection；Posture is carried out to described image to be detected
Detection, obtains the key point information of target object；Key point information based on the target object carries out behavioral value, obtains appearance
State identifies corresponding behavioral value result, wherein the key point comprises at least one of the following: wrist, palm, elbow, eyes,
Ankle；Human body positioning and identification are carried out to described image to be detected；According to the human body positioning and recognition result into
Row behavioral value obtains human body and detects corresponding behavioral value result.
Optionally, the second behavioral value unit, suitable for the corresponding row of behavioral value to following at least two type
It is merged for testing result, obtains the behavioral value result: the corresponding behavioral value result of feature extraction, target detection pair
The corresponding behavioral value result of behavioral value result, the gesture recognition answered, human body detect corresponding behavioral value result.
Optionally, the second behavioral value unit is suitable for using following at least one amalgamation mode to described at least two
The corresponding behavioral value result of the behavioral value of seed type is merged: ballot mode, mode of averaging, weighting scheme and selection
Property amalgamation mode.
Optionally, the intelligent terminal further include: the second image pre-processing unit is suitable for carrying out described image to be detected
Image preprocessing obtains pretreated image, wherein described image pretreatment comprises at least one of the following: compression of images, figure
As encryption, image enhancement, image restoration, image transformation.
Optionally, the intelligent terminal further include: the second image pre-processing unit is suitable for carrying out described image to be detected
Image preprocessing obtains pretreated image, wherein described image pretreatment comprises at least one of the following: compression of images, figure
As encryption, image enhancement, image restoration, image transformation.
Optionally, the third storage unit is further adapted for storing described image to be detected.
Optionally, the intelligent terminal further include: transmission unit, it is described pre- suitable for storing the third storage unit
Treated image or described image to be detected are sent to the server.
Optionally, the server further include: third image pre-processing unit, suitable for carrying out figure to described image to be detected
As pretreatment, pretreated image is obtained, wherein described image pretreatment comprises at least one of the following: compression of images, image
Encryption, image enhancement, image restoration, image transformation.
Optionally, second storage unit is further adapted for storing the pretreated figure of third image pre-processing unit
Picture.
The embodiment of the present invention also provides a kind of human body behavioral value method, comprising: obtains image to be detected；To described to be checked
Altimetric image carries out human body behavioral value, obtains behavioral value as a result, the behavioral value result comprises at least one of the following: default
Probability that behavior occurs, occur time location of the default behavior in described image to be detected, occur default behavior it is described to
Locating spatial position, behavior type in detection image；Store the behavioral value result.
Optionally, described that human body behavioral value is carried out to described image to be detected, comprising: described image to be detected is carried out
The human body behavioral value of at least two types below obtains the corresponding behavior inspection of human body behavioral value of at least two type
Survey result: described that human body behavioral value is carried out to described image to be detected, comprising: carry out below at least to described image to be detected
Two kinds of human body behavioral value obtains the corresponding behavioral value result of human body behavioral value of at least two type:
Target detection is carried out to described image to be detected, positions and identifies target object；Behavior is carried out based on the target object identified
Detection, obtains the corresponding behavioral value result of target detection；Attitude detection is carried out to described image to be detected, obtains target object
Key point information；Key point information based on the target object carries out behavioral value, obtains the corresponding behavior of gesture recognition
Testing result, wherein the key point comprises at least one of the following: wrist, palm, elbow, eyes, ankle；To described to be detected
Image carries out human body positioning and identification；Behavioral value is carried out according to human body positioning and recognition result, obtains people
Body region detects corresponding behavioral value result.
Optionally, described that human body behavioral value is carried out to described image to be detected, comprising: to following at least two type
The corresponding behavioral value result of behavioral value is merged, and the behavioral value result: the corresponding behavior inspection of feature extraction is obtained
Survey result, the corresponding behavioral value result of target detection, the corresponding behavioral value result of gesture recognition, human body detection correspondence
Behavioral value result.
Optionally, described that the corresponding behavioral value result of the behavioral value of following at least two type is merged, packet
It includes: the corresponding behavioral value result of the behavioral value of at least two type being carried out using following at least one amalgamation mode
Fusion: ballot mode, mode of averaging, weighting scheme and selective amalgamation mode.
Optionally, after obtaining image to be detected, further includes: carry out image preprocessing to described image to be detected, obtain
To pretreated image, wherein described image pretreatment comprises at least one of the following: compression of images, image encryption, image increase
By force, image restoration, image transformation.
Optionally, after carrying out image preprocessing to described image to be detected, further includes: store pretreated figure
Picture.
Optionally, after obtaining image to be detected, further includes: store described image to be detected.
Optionally, after obtaining the behavioral value result, further includes: receive the request letter that pre-association terminal is sent
Breath, the solicited message is for behavioral value result described in request；The solicited message is received in the receiving unit
Afterwards, the behavioral value result is exported to the pre-association terminal.
The embodiment of the present invention also provides a kind of human body behavioral value system, including memory and processor, the memory
On be stored with the computer instruction that can be run on the processor, the processor executes sheet when running the computer instruction
The step of inventing any of the above-described kind of human body behavioral value method.
The embodiment of the present invention also provides a kind of computer readable storage medium, and computer readable storage medium is non-volatile
Storage medium or non-transitory storage media, are stored thereon with computer instruction, and the computer instruction executes the present invention when running
The step of any of the above-described kind of human body behavioral value method.
Compared with prior art, the technical solution of the embodiment of the present invention has the advantages that
After carrying out behavioral value to the image to be detected got, behavior testing result is stored, for multiple pre-associations
Terminal uses, so as to improve the validity that intelligent terminal utilizes image and video data.
Further, the behavioral value that at least two types are carried out to image to be detected, obtains behavioral value as a result, can mention
The accuracy of high obtained behavioral value result.
Further, before carrying out human body behavioral value to image to be processed, image preprocessing is carried out to image to be detected,
The accuracy that obtained behavioral value result can be improved, is conducive to image procossing.
Detailed description of the invention
Fig. 1 is the flow chart of one of embodiment of the present invention human body behavioral value method；
Fig. 2 is the structural schematic diagram of one of embodiment of the present invention human body behavioral value system；
Fig. 3 is the structural schematic diagram of another human body behavioral value system in the embodiment of the present invention.
Specific embodiment
As described above, intelligent terminal is lower to the utilization validity of institute's acquired image or video data.
In the embodiment of the present invention, after carrying out behavioral value to the image to be detected got, behavior testing result is stored,
For the use of multiple pre-association terminals, so as to improve the validity that intelligent terminal utilizes image and video data.
It is understandable to enable the above-mentioned purpose, feature and beneficial effect of the embodiment of the present invention to become apparent, below with reference to attached
Figure is described in detail specific embodiments of the present invention.
Referring to Fig.1, give the flow chart of one of embodiment of the present invention human body behavioral value method, may include with
Lower step.
Step 11, image to be detected is obtained.
In specific implementation, the images such as camera have been generally integrated on the intelligent terminals such as mobile phone, automatic teller machine, automatic vending machine
Acquisition device.Intelligent terminal can by image acquisition devices images such as cameras integrated thereon, can also by with
Other associated image acquisition device images.In embodiments of the present invention, can using institute's acquired image as to
Detection image.Image to be detected can be still image, or video flowing can also be dynamic image etc..
In embodiments of the present invention, after getting image to be detected, it can store image to be detected.It is to be checked storing
When altimetric image, image to be detected can be stored in intelligent terminal, image to be detected can also be stored in and be closed with intelligent terminal
The server of connection.
Step 12, human body behavioral value is carried out to described image to be detected, obtains behavioral value result.
In specific implementation, after getting image to be detected, human body behavioral value can be carried out to image to be detected.
In an embodiment of the present invention, human body behavioral value is carried out to described image to be detected by intelligent terminal.It is another in the present invention
In embodiment, accessed image to be detected is sent to server by intelligent terminal, and server is to the mapping to be checked received
As carrying out human body behavioral value, behavioral value result is obtained.
Behavioral value result may include following at least one: there is default behavior in institute in the probability of default behavior appearance
It states the time location in image to be detected, default behavior spatial position and behavior locating in described image to be detected occur
Type.For example, in carrying out driving caller's body behavioral value, to the behavioral value result of image to be detected are as follows: beat electricity
Talking about probability is 0.7, and in the 00:13:53 of video flowing, behavior type is in violation of rules and regulations.
In practical applications, default behavior and default behavior type can be set according to practical application scene, when locating
Application scenarios difference when, set default behavior and behavior type are different.
In specific implementation, the behavioral value of following at least two types can be carried out to image to be detected, and obtain two
The corresponding behavioral value result of the behavioral value of seed type: behavioral value is carried out, using target detection mode using feature extraction
Carry out behavioral value, use attitude detection mode carry out behavioral value, use human body detection mode carry out behavioral value with
And behavioral value is carried out based on described image to be detected.
In embodiments of the present invention, behavioral value is carried out using feature extraction, it is specific as follows: image to be detected to be carried out special
Sign is extracted, and the characteristics of image of image to be detected is obtained.Obtained characteristics of image may include edge feature or corner feature
At least one of.Based on the accessed corresponding characteristics of image of image to be detected, behavioral value is carried out, to be used
The corresponding behavioral value result of feature extraction mode.
In specific implementation, feature extraction can be carried out using any mode in HOG, SIFI, Haar etc..
In embodiments of the present invention, behavioral value is carried out using target detection mode, it is specific as follows: to image to be detected into
Row target detection positions and identifies target object.The target object can for the human body occurred in image to be detected or its
His object.Behavioral value is carried out based on the target object identified, obtains the corresponding behavioral value result of target object.
In embodiments of the present invention, behavioral value is carried out using attitude detection mode, it is specific as follows: to the mapping to be checked
As carrying out attitude detection, the key point information of target object is obtained；Key point information based on the target object carries out behavior
Detection, obtains the corresponding behavioral value result of gesture recognition, wherein the key point comprises at least one of the following: wrist, hand
The palm, elbow, eyes, ankle.It is understood that the key point may be other positions of target object.
In embodiments of the present invention, behavioral value is carried out using human body detection mode, it is specific as follows: to figure to be detected
As carrying out human body positioning and identification；Behavioral value is carried out according to human body positioning and recognition result, obtains human body
The corresponding behavioral value result of location detection.Each position of human body can be positioned and be identified by human body detection,
The movement that current human can be determined by the positioning of human body and recognition result, may thereby determine that corresponding behavioral value
As a result.
In specific implementation, in order to improve the accuracy of obtained behavioral value result, can by it is obtained at least
The corresponding behavioral value result of two kinds of behavioral value is merged, and the final behavioral value result is obtained.
It in specific implementation, can be using various ways to the corresponding behavioral value knot of the behavioral value of at least two types
Fruit is merged.
In an embodiment of the present invention, using ballot mode to the corresponding behavioral value of the behavioral value of at least two types
As a result it is merged.For example, using following 5 channels: feature extraction channel, target detection channel, attitude detection channel, human body
Location detection channel and image channel to be processed, each channel be corresponding with behavioral value as a result, corresponding behavior probability not
Together, using the corresponding behavioral value result in the highest channel of behavior probability as behavioral value result.
In an alternative embodiment of the invention, corresponding using behavioral value of the mode of averaging at least two type
Behavioral value result merged, obtain behavioral value result.
In still another embodiment of the process, using weighting scheme to the corresponding row of behavioral value of at least two type
It is merged for testing result.For example, can for different types of behavioral value result set weight, according to the weight of setting with
Obtained behavior probability is calculated, and determines final behavior type and behavior probability, to obtain behavioral value result.
In yet another embodiment of the invention, according to preset alternative condition, the behavioral value of respective type is selected as a result, simultaneously
Selected behavioral value result is merged.In specific implementation, different types of image to be detected, using different rows
May be different for the accuracy of the obtained behavioral value result of detection mode, respective class is selectively selected according to actual needs
The behavioural information of type carries out behavioral value, and the accuracy of obtained behavioral value result can be improved.To selected row
When being merged for information, the behavioral value result of selection can be merged using ballot mode, can also use and ask flat
Mean value mode merges selected behavioral value result, can also be using weighting scheme to selected behavioral value knot
Fruit is merged, and in practical applications, can select amalgamation mode according to specific application scenarios and demand.
It is understood that various types of behavioral value results can also be merged using other amalgamation modes,
Details are not described herein again.
In specific implementation, above-mentioned human body behavioral value can be carried out on intelligent terminal, can also on the server into
The above-mentioned human body behavioral value of row.
Step 13, the behavioral value result is stored.
In specific implementation, after obtaining the behavioral value result, the behavioral value can be detected and is stored,
So that pre-association terminal uses in follow-up process.Behavioral value result can be stored in intelligent terminal, behavior can also be examined
It surveys result and is stored in server.
By above scheme it is found that after carrying out behavioral value to the image to be detected got, behavior testing result is stored,
For the use of multiple pre-association terminals, so as to improve the validity that intelligent terminal utilizes image and video data.
Using behavioral value method provided in an embodiment of the present invention, it is based on image to be detected, to occurring in image to be detected
Human body behavior positioned, identified.It is real compared to the Face datection and target detection, the present invention only carried out to image in more existing
Deeper information can be excavated by carrying out human body behavioral value to image to be detected from image to be detected by applying example, be added
The deep understanding to image to be detected, further increases the degree of intelligence of smart machine or server.Obtained behavioral value knot
Fruit can use for downstream application, and richer information is provided for downstream application, as downstream application can be based on obtained row
Behavior prediction, behavior monitoring, group behavior analysis or security protection etc. are carried out for testing result, so as to further promote downstream
The performance and effect of application.
In specific implementation, it in order to further increase the accuracy of behavioral value result, is got in step 11 to be detected
After image, image preprocessing can also be carried out to image to be detected, obtain pretreated image, and based on pretreated
Image carries out human body behavioral value.
In embodiments of the present invention, at least one image preprocessing below being carried out to image to be detected: compression of images,
Image encryption, image enhancement, image restoration and image transformation.
In specific implementation, compression of images is carried out to image to be detected, adjustable image to be detected is deposited to occupied
Store up space or occupied processing memory.
In specific implementation, image encryption is carried out to image to be detected, data safety can be improved.
In specific implementation, image enhancement is carried out to image to be detected, picture quality can be improved.In the embodiment of the present invention
In, detection image can be treated using following at least one image procossing mode and carry out image enhancement: image to be detected is carried out
Denoising；Processing is sharpened to image to be detected；Image to be detected degree of comparing adjustment is handled, to enhance or subtract
The contrast of weak image to be detected.It is understood that detection image progress can also be treated using other image procossing modes
Enhancing processing, is not repeated herein.
In specific implementation, image transformation is carried out to image to be detected, may include image standardization or image spreading.
Image standardization is carried out to image to be detected, adjustable image data distribution facilitates subsequent image to be detected
Using.In embodiments of the present invention, detection image can be treated using following at least one image procossing mode and carries out image mark
Standardization: whitening processing is carried out to image to be detected；Image to be detected is normalized, to obtain meeting pre-set dimension
Image to be detected；Image to be detected is standardized, so that the key point in figure to be detected may be at presetting
Position.It is understood that can also treat detection image according to actual needs using other image procossing modes and carry out image
Standardization, is not repeated herein.
Image spreading is carried out to image to be detected, the image for assisting detection can be generated.In embodiments of the present invention,
Image spreading can be carried out using following at least one mode: translation, rotation, distortion, Fuzzy Processing and pyramidization processing
Deng.It is understood that can also treat detection image according to actual needs using other image procossing modes and carry out image expansion
Exhibition, is not repeated herein.
It is understood that according to practical application request other processing can also be carried out to image, details are not described herein again.
Image preprocessing is carried out to image to be detected, it, can also will be pretreated after obtaining pretreated image
Image is stored.
In specific implementation, the solicited message of pre-association terminal transmission can also be received, the solicited message is for requesting
Obtain behavioral value result.After receiving the solicited message, request results can be exported to pre-association terminal.
In embodiments of the present invention, solicited message can be sent to intelligent terminal by pre-association terminal, and intelligent terminal receives
After to the solicited message behavioral value can be obtained in the data of itself storage as a result, and the behavioral value result that will acquire
It exports to pre-association terminal.Intelligent terminal can also get behavioral value from server as a result, and the behavior that will acquire
Testing result output valve is to pre-association terminal.
In embodiments of the present invention, solicited message can also be sent to server by pre-association terminal, and server receives
After solicited message, behavioral value can be obtained in the data that server is stored as a result, and by acquired behavioral value knot
Fruit exports to pre-association terminal.
For the embodiment of the present invention is better understood and realized convenient for those skilled in the art.The embodiment of the present invention also provides one
Kind human body behavioral value system.
Referring to Fig. 2, a kind of structural schematic diagram of human body behavioral value system in the embodiment of the present invention is given.The human body
Behavioral value system may include intelligent terminal 20.The intelligent terminal 20 may include: first acquisition unit 21, the first behavior
Detection unit 22 and the first storage unit 23, in which:
First acquisition unit 21 is suitable for obtaining image to be detected；
First behavior detection unit 22 is suitable for carrying out human body behavioral value to described image to be detected, obtains behavioral value
As a result, the behavioral value result comprises at least one of the following: probability that default behavior occurs, occur default behavior it is described to
Time location, appearance in detection image preset behavior spatial position locating in described image to be detected and behavior class
Type；
First storage unit 23 is suitable for storing obtained behavioral value result.
In specific implementation, the first behavior detection unit 22, suitable for following at least to the progress of described image to be detected
Two kinds of human body behavioral value: feature extraction is carried out to described image to be detected, obtains the image of described image to be detected
Feature, described image feature comprise at least one of the following: edge feature or corner feature；Image based on described image to be detected
Feature carries out behavioral value, obtains the corresponding behavioral value result of feature extraction；Target detection is carried out to described image to be detected,
It positions and identifies target object；Behavioral value is carried out based on the target object identified, obtains the corresponding behavior inspection of target detection
Survey result；Attitude detection is carried out to described image to be detected, obtains the key point information of target object；Based on the target object
Key point information carry out behavioral value, obtain the corresponding behavioral value result of gesture recognition, wherein the key point include with
Lower at least one: wrist, palm, elbow, eyes, ankle；Human body positioning and identification are carried out to described image to be detected；Root
Behavioral value is carried out according to human body positioning and recognition result, human body is obtained and detects corresponding behavioral value result.
In specific implementation, the first behavior detection unit 22, suitable for the behavioral value to following at least two type
Corresponding behavioral value result is merged, and the behavioral value result: the corresponding behavioral value result of feature extraction, mesh is obtained
Mark detects corresponding behavioral value result, the corresponding behavioral value result of gesture recognition, human body and detects corresponding behavior inspection
Survey result.
In specific implementation, the first behavior detection unit 22 is suitable for using following at least one amalgamation mode to institute
The corresponding behavioral value result of behavioral value for stating at least two types is merged: ballot mode, average mode, weighting side
Formula and selective amalgamation mode.
In specific implementation, the intelligent terminal 20 can also include: the first image pre-processing unit 24, be suitable for described
Image to be detected carries out image preprocessing, obtains pretreated image, wherein described image pretreatment includes following at least one
Kind: compression of images, image encryption, image enhancement, image restoration, image transformation.
In specific implementation, first storage unit 23 is further adapted for storing pretreated image.
In specific implementation, first storage unit 23 is further adapted for storing described image to be detected.
In specific implementation, the intelligent terminal 20 can also include: the first receiving unit (Fig. 2 is not shown), suitable for connecing
The solicited message that pre-association terminal is sent is received, the solicited message is for behavioral value result described in request.
In specific implementation, the intelligent terminal 20 can also include: the first output unit (Fig. 2 is not shown), be suitable for
After the receiving unit receives the solicited message, the behavioral value result is exported to the pre-association terminal.
In specific implementation, the human body behavioral value system can also include server 10.The intelligent terminal 20 can
Behavioral value result is sent to the server 10.The server 10 can store the behavioral value result.
In embodiments of the present invention, the behavioral value result being stored on server 10 or intelligent terminal 20 can be for downstream
Using.
The behavioral value system that our inventive embodiments provide, is deployed in intelligent terminal 20 for the first behavior detection unit 22
On, suitable for the storage of intelligent terminal 30 and computing capability compared with strong and by a relatively simple algorithm and model situation, precision it is high and
Time delay is smaller.
In specific implementation, the working principle of the behavioral value system and workflow can be with reference to the above-mentioned realities of the present invention
The description in example is applied, details are not described herein again.
Referring to Fig. 3, the structural schematic diagram of another behavioral value system in the embodiment of the present invention is given.Behavioral value system
System may include intelligent terminal 30 and server 40.Intelligent terminal 30 includes: second acquisition unit 31, is suitable for obtaining mapping to be checked
Picture is simultaneously sent to the server 40.Server 40 includes: the second behavioral value unit 41 and the second storage unit 42, wherein
The second behavioral value unit 41, be suitable for described image to be detected carry out human body behavioral value, obtain behavioral value as a result,
The behavioral value result comprises at least one of the following: there is default behavior described to be detected in the probability of default behavior appearance
Time location, appearance in image preset behavior spatial position locating in described image to be detected, behavior type；Second deposits
Storage unit 42 is suitable for storing obtained behavioral value result.
In specific implementation, the second behavioral value unit 41, suitable for following at least to the progress of described image to be detected
Two kinds of human body behavioral value: feature extraction is carried out to described image to be detected, obtains the image of described image to be detected
Feature, described image feature comprise at least one of the following: edge feature or corner feature；Image based on described image to be detected
Feature carries out behavioral value, obtains the corresponding behavioral value result of feature extraction；Target detection is carried out to described image to be detected,
It positions and identifies target object；Behavioral value is carried out based on the target object identified, obtains the corresponding behavior inspection of target detection
Survey result；Attitude detection is carried out to described image to be detected, obtains the key point information of target object；Based on the target object
Key point information carry out behavioral value, obtain the corresponding behavioral value result of gesture recognition, wherein the key point include with
Lower at least one: wrist, palm, elbow, eyes, ankle；Human body positioning and identification are carried out to described image to be detected；Root
Behavioral value is carried out according to human body positioning and recognition result, human body is obtained and detects corresponding behavioral value result.
In specific implementation, the second behavioral value unit 41, suitable for the behavioral value to following at least two type
Corresponding behavioral value result is merged, and the behavioral value result: the corresponding behavioral value result of feature extraction, mesh is obtained
Mark detects corresponding behavioral value result, the corresponding behavioral value result of gesture recognition, human body and detects corresponding behavior inspection
Survey result.
In specific implementation, the second behavioral value unit 41 is suitable for using following at least one amalgamation mode to institute
The corresponding behavioral value result of behavioral value for stating at least two types is merged: ballot mode, average mode, weighting side
Formula and selective amalgamation mode.
In specific implementation, the intelligent terminal 30 can also include the second image pre-processing unit 32, be suitable for described
Image to be detected carries out image preprocessing, obtains pretreated image, wherein described image pretreatment includes following at least one
Kind: compression of images, image encryption, image enhancement, image restoration, image transformation.
In specific implementation, the intelligent terminal 30 can also include: third storage unit 33, be suitable for storage described second
The pretreated image of image pre-processing unit 32.
In specific implementation, the third storage unit 33 is further adapted for storing described image to be detected.
In specific implementation, the intelligent terminal 30 can also include: transmission unit (Fig. 3 is not shown), and being suitable for will be described
The pretreated image or described image to be detected that third storage unit 33 stores are sent to the server 40.
In specific implementation, the server 40 can also include: third image pre-processing unit 43, be suitable for it is described to
Detection image carries out image preprocessing, obtains pretreated image, wherein described image pretreatment includes following at least one
Kind: compression of images, image encryption, image enhancement, image restoration, image transformation.
Second storage unit 42 is further adapted for storing the pretreated image of the third image pre-processing unit 43.
The human body behavioral value system provided using the above embodiment of the present invention, intelligent terminal 30 will acquire to be detected
Image or the second image pre-processing unit 32 carry out the pretreated image obtained after image preprocessing, are sent to clothes
Business device 40 carries out human body behavioral value, obtains behavioral value result.Using above-mentioned deployment way, using server 40 to human body row
To be detected, it can reduce the requirement to the computing capability and storage capacity of intelligent terminal 30, be suitable for requirement of real-time
Not high application scenarios.
In specific implementation, the workflow of the human body behavioral value system and working principle can be with reference in the present invention
The description in the behavioral value method provided in embodiment is stated, details are not described herein again.
The embodiment of the present invention also provides a kind of human body behavioral value system, including memory and processor, the memory
On be stored with the computer instruction that can be run on the processor, the processor executes sheet when running the computer instruction
The step of inventing the human body behavioral value method that any of the above-described embodiment provides.
The embodiment of the present invention also provides a kind of computer readable storage medium, and computer readable storage medium is non-volatile
Storage medium or non-transitory storage media, are stored thereon with computer instruction, and the computer instruction executes the present invention when running
The step of human body behavioral value method that any of the above-described embodiment provides.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with indicating relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: ROM, RAM, disk or CD etc..
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (29)
1. a kind of human body behavioral value system characterized by comprising intelligent terminal, wherein the intelligent terminal, comprising:
First acquisition unit is suitable for obtaining image to be detected；
First behavior detection unit is suitable for carrying out human body behavioral value to described image to be detected, obtains behavioral value as a result, institute
State behavioral value result to comprise at least one of the following: there is default behavior in the mapping to be checked in the probability of default behavior appearance
Time location, appearance as in preset behavior spatial position locating in described image to be detected and behavior type；
First storage unit is suitable for storing obtained behavioral value result.
2. human body behavioral value system according to claim 1, which is characterized in that the first behavior detection unit is fitted
In the human body behavioral value for carrying out following at least two types to described image to be detected, the people of at least two type is obtained
The corresponding behavioral value result of body behavioral value:
Feature extraction is carried out to described image to be detected, obtains the characteristics of image of described image to be detected, described image feature packet
Include following at least one: edge feature or corner feature；Characteristics of image based on described image to be detected carries out behavioral value, obtains
To the corresponding behavioral value result of feature extraction；
Target detection is carried out to described image to be detected, positions and identifies target object；It is carried out based on the target object identified
Behavioral value obtains the corresponding behavioral value result of target detection；
Attitude detection is carried out to described image to be detected, obtains the key point information of target object；Based on the target object
Key point information carries out behavioral value, obtains the corresponding behavioral value result of gesture recognition, wherein the key point includes following
It is at least one: wrist, palm, elbow, eyes, ankle；
Human body positioning and identification are carried out to described image to be detected；It is carried out according to human body positioning and recognition result
Behavioral value obtains human body and detects corresponding behavioral value result.
3. human body behavioral value system according to claim 2, which is characterized in that the first behavior detection unit is fitted
It is merged in the corresponding behavioral value result of behavioral value to following at least two type, obtains the behavioral value knot
Fruit: the corresponding behavior inspection of the corresponding behavioral value result of feature extraction, the corresponding behavioral value result of target detection, gesture recognition
Survey result, human body detects corresponding behavioral value result.
4. human body behavioral value system according to claim 3, which is characterized in that the first behavior detection unit is fitted
The corresponding behavioral value result of the behavioral value of at least two type is carried out in the following at least one amalgamation mode of use
Fusion: ballot mode, mode of averaging, weighting scheme and selective amalgamation mode.
5. human body behavioral value system according to any one of claims 1 to 4, which is characterized in that the intelligent terminal, also
Include: the first image pre-processing unit, is suitable for carrying out image preprocessing to described image to be detected, obtains pretreated figure
Picture, wherein described image pretreatment comprises at least one of the following: compression of images, image encryption, image enhancement, image restoration, figure
As transformation.
6. human body behavioral value system according to claim 5, which is characterized in that first storage unit is further adapted for
Store pretreated image.
7. human body behavioral value system according to claim 6, which is characterized in that first storage unit is further adapted for
Store described image to be detected.
8. human body behavioral value system according to any one of claims 1 to 4, which is characterized in that further include: first receives
Unit, the solicited message sent suitable for receiving pre-association terminal, the solicited message is for behavioral value knot described in request
Fruit.
9. human body behavioral value system according to claim 8, which is characterized in that further include: the first output unit is suitable for
After the receiving unit receives the solicited message, the behavioral value result is exported to the pre-association terminal.
10. a kind of human body behavioral value system characterized by comprising intelligent terminal and server, wherein the intelligence is eventually
End, comprising: second acquisition unit, suitable for obtaining image to be detected and being sent to the server；
The server, comprising: the second behavioral value unit and the second storage unit, the second behavioral value unit are suitable for
To described image to be detected carry out human body behavioral value, obtain behavioral value as a result, the behavioral value result include with down toward
It is few a kind of: time location, appearance default row of the probability, the default behavior of appearance that default behavior occurs in described image to be detected
For locating spatial position in described image to be detected, behavior type；
Second storage unit is suitable for storing obtained behavioral value result.
11. human body behavioral value system according to claim 10, which is characterized in that the second behavioral value unit,
Suitable for carrying out the human body behavioral value of following at least two types to described image to be detected, at least two type is obtained
The corresponding behavioral value result of human body behavioral value:
Feature extraction is carried out to described image to be detected, obtains the characteristics of image of described image to be detected, described image feature packet
Include following at least one: edge feature or corner feature；Characteristics of image based on described image to be detected carries out behavioral value, obtains
To the corresponding behavioral value result of feature extraction；
Target detection is carried out to described image to be detected, positions and identifies target object；It is carried out based on the target object identified
Behavioral value obtains the corresponding behavioral value result of target detection；
Attitude detection is carried out to described image to be detected, obtains the key point information of target object；Based on the target object
Key point information carries out behavioral value, obtains the corresponding behavioral value result of gesture recognition, wherein the key point includes following
It is at least one: wrist, palm, elbow, eyes, ankle；
Human body positioning and identification are carried out to described image to be detected；It is carried out according to human body positioning and recognition result
Behavioral value obtains human body and detects corresponding behavioral value result.
12. human body behavioral value system according to claim 11, which is characterized in that the second behavioral value unit,
It is merged suitable for the corresponding behavioral value result of behavioral value to following at least two type, obtains the behavioral value knot
Fruit: the corresponding behavior inspection of the corresponding behavioral value result of feature extraction, the corresponding behavioral value result of target detection, gesture recognition
Survey result, human body detects corresponding behavioral value result.
13. human body behavioral value system according to claim 12, which is characterized in that the second behavioral value unit,
Suitable for using following at least one amalgamation mode to the corresponding behavioral value result of the behavioral value of at least two type into
Row fusion: ballot mode, mode of averaging, weighting scheme and selective amalgamation mode.
14. human body behavioral value system according to any one of claims 10 to 13, which is characterized in that the intelligent terminal
Further include: the second image pre-processing unit is suitable for carrying out image preprocessing to described image to be detected, obtains pretreated figure
Picture, wherein described image pretreatment comprises at least one of the following: compression of images, image encryption, image enhancement, image restoration, figure
As transformation.
15. human body behavioral value system according to claim 14, which is characterized in that the intelligent terminal further include: the
Three storage units are suitable for storing the pretreated image of the second image pre-processing unit.
16. human body behavioral value system according to claim 15, which is characterized in that the third storage unit, it is also suitable
In the described image to be detected of storage.
17. human body behavioral value system according to claim 16, which is characterized in that the intelligent terminal further include: hair
Unit is sent, the pretreated image or described image to be detected suitable for storing the third storage unit are sent to
The server.
18. human body behavioral value system according to any one of claims 10 to 13, which is characterized in that the server is also
Include: third image pre-processing unit, is suitable for carrying out image preprocessing to described image to be detected, obtains pretreated figure
Picture, wherein described image pretreatment comprises at least one of the following: compression of images, image encryption, image enhancement, image restoration, figure
As transformation.
19. human body behavioral value system according to claim 18, which is characterized in that second storage unit, it is also suitable
In the storage pretreated image of third image pre-processing unit.
20. a kind of human body behavioral value method characterized by comprising
Obtain image to be detected；
To described image to be detected carry out human body behavioral value, obtain behavioral value as a result, the behavioral value result include with
Lower at least one: the probability of behavior appearance is preset, the time location preset behavior in described image to be detected occurs, occurs in advance
If behavior spatial position locating in described image to be detected, behavior type；
Store the behavioral value result.
21. human body behavioral value method according to claim 20, which is characterized in that it is described to described image to be detected into
Pedestrian's body behavioral value, comprising: the human body behavioral value that following at least two types are carried out to described image to be detected obtains institute
State the corresponding behavioral value result of human body behavioral value of at least two types:
Feature extraction is carried out to described image to be detected, obtains the characteristics of image of described image to be detected, described image feature packet
Include following at least one: edge feature or corner feature；Characteristics of image based on described image to be detected carries out behavioral value, obtains
To the corresponding behavioral value result of feature extraction；
Target detection is carried out to described image to be detected, positions and identifies target object；It is carried out based on the target object identified
Behavioral value obtains the corresponding behavioral value result of target detection；
Attitude detection is carried out to described image to be detected, obtains the key point information of target object；Based on the target object
Key point information carries out behavioral value, obtains the corresponding behavioral value of gesture recognition as a result, wherein the key point includes following
It is at least one: wrist, palm, elbow, eyes, ankle；
Human body positioning and identification are carried out to described image to be detected；It is carried out according to human body positioning and recognition result
Behavioral value obtains human body and detects corresponding behavioral value result.
22. human body behavioral value method according to claim 21, which is characterized in that it is described to described image to be detected into
Pedestrian's body behavioral value, comprising:
The corresponding behavioral value result of the behavioral value of following at least two type is merged, the behavioral value knot is obtained
Fruit: the corresponding behavior inspection of the corresponding behavioral value result of feature extraction, the corresponding behavioral value result of target detection, gesture recognition
Survey result, human body detects corresponding behavioral value result.
23. human body behavioral value method according to claim 22, which is characterized in that described to following at least two type
The corresponding behavioral value result of behavioral value merged, comprising:
Using the corresponding behavioral value result of behavioral value of the following at least one amalgamation mode at least two type into
Row fusion: ballot mode, mode of averaging, weighting scheme and selective amalgamation mode.
24. human body behavioral value method according to claim 20, which is characterized in that after obtaining image to be detected,
Further include:
Image preprocessing is carried out to described image to be detected, obtains pretreated image, wherein described image, which pre-processes, includes
Following at least one:
Compression of images, image encryption, image enhancement, image restoration, image transformation.
25. human body behavioral value method according to claim 24, which is characterized in that carried out to described image to be detected
After image preprocessing, further includes: store pretreated image.
26. human body behavioral value method according to claim 20, which is characterized in that after obtaining image to be detected,
Further include: store described image to be detected.
27. human body behavioral value method according to claim 20, which is characterized in that obtaining the behavioral value result
Later, further includes: receive the solicited message that pre-association terminal is sent, the solicited message is for behavioral value described in request
As a result；After the receiving unit receives the solicited message, the behavioral value result is exported to the pre-association terminal.
28. a kind of human body behavioral value system, including memory and processor, being stored on the memory can be in the processing
The computer instruction run on device, which is characterized in that perform claim requires 20 when the processor runs the computer instruction
The step of to 27 described in any item human body behavioral value methods.
29. a kind of computer readable storage medium, computer readable storage medium is non-volatile memory medium or non-transient deposits
Storage media is stored thereon with computer instruction, which is characterized in that perform claim requires 20 to 27 when the computer instruction is run
The step of described in any item human body behavioral value methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910242524.4A CN110084123A (en) | 2019-03-28 | 2019-03-28 | Human body behavioral value method and system, computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910242524.4A CN110084123A (en) | 2019-03-28 | 2019-03-28 | Human body behavioral value method and system, computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084123A true CN110084123A (en) | 2019-08-02 |
Family
ID=67413815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910242524.4A Pending CN110084123A (en) | 2019-03-28 | 2019-03-28 | Human body behavioral value method and system, computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084123A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331687A (en) * | 2014-10-30 | 2015-02-04 | 安徽国华光电技术有限公司 | Safety belt unfastening behavior detection method based on vehicular video analysis |
| CN103268495B (en) * | 2013-05-31 | 2016-08-17 | 公安部第三研究所 | Human body behavior modeling recognition methods based on priori knowledge cluster in computer system |
| CN106778796A (en) * | 2016-10-20 | 2017-05-31 | 江苏大学 | Human motion recognition method and system based on hybrid cooperative model training |
| CN104156693B (en) * | 2014-07-15 | 2017-06-06 | 天津大学 | A kind of action identification method based on the fusion of multi-modal sequence |
| CN107895161A (en) * | 2017-12-22 | 2018-04-10 | 北京奇虎科技有限公司 | Real-time attitude recognition methods and device, computing device based on video data |
| CN108647649A (en) * | 2018-05-14 | 2018-10-12 | 中国科学技术大学 | The detection method of abnormal behaviour in a kind of video |
| CN108764100A (en) * | 2018-05-22 | 2018-11-06 | 全球能源互联网研究院有限公司 | A kind of goal behavior detection method and server |
| CN109086729A (en) * | 2018-08-13 | 2018-12-25 | 成都盯盯科技有限公司 | Communication behavior detection method, device, equipment and storage medium |
| CN109101901A (en) * | 2018-07-23 | 2018-12-28 | 北京旷视科技有限公司 | Human action identification and its neural network generation method, device and electronic equipment |
-
2019
- 2019-03-28 CN CN201910242524.4A patent/CN110084123A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268495B (en) * | 2013-05-31 | 2016-08-17 | 公安部第三研究所 | Human body behavior modeling recognition methods based on priori knowledge cluster in computer system |
| CN104156693B (en) * | 2014-07-15 | 2017-06-06 | 天津大学 | A kind of action identification method based on the fusion of multi-modal sequence |
| CN104331687A (en) * | 2014-10-30 | 2015-02-04 | 安徽国华光电技术有限公司 | Safety belt unfastening behavior detection method based on vehicular video analysis |
| CN106778796A (en) * | 2016-10-20 | 2017-05-31 | 江苏大学 | Human motion recognition method and system based on hybrid cooperative model training |
| CN107895161A (en) * | 2017-12-22 | 2018-04-10 | 北京奇虎科技有限公司 | Real-time attitude recognition methods and device, computing device based on video data |
| CN108647649A (en) * | 2018-05-14 | 2018-10-12 | 中国科学技术大学 | The detection method of abnormal behaviour in a kind of video |
| CN108764100A (en) * | 2018-05-22 | 2018-11-06 | 全球能源互联网研究院有限公司 | A kind of goal behavior detection method and server |
| CN109101901A (en) * | 2018-07-23 | 2018-12-28 | 北京旷视科技有限公司 | Human action identification and its neural network generation method, device and electronic equipment |
| CN109086729A (en) * | 2018-08-13 | 2018-12-25 | 成都盯盯科技有限公司 | Communication behavior detection method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陈庆峰，冯仕民，丁恩杰: "一种基于多特征多分类器融合的人体行为识别方法", 《河南科技大学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Davison et al. | Objective micro-facial movement detection using facs-based regions and baseline evaluation | |
| CN103116763B (en) | A kind of living body faces detection method based on hsv color Spatial Statistical Character | |
| CN109086718A (en) | Biopsy method, device, computer equipment and storage medium | |
| CN105160318A (en) | Facial expression based lie detection method and system | |
| CN109522790A (en) | Human body attribute recognition approach, device, storage medium and electronic equipment | |
| US9990555B2 (en) | Video detection method, video detection system and computer program product | |
| CN110569731A (en) | face recognition method and device and electronic equipment | |
| WO2019014813A1 (en) | Method and apparatus for quantitatively detecting skin type parameter of human face, and intelligent terminal | |
| WO2022252642A1 (en) | Behavior posture detection method and apparatus based on video image, and device and medium | |
| Kalas | Real time face detection and tracking using OpenCV | |
| US20200085296A1 (en) | Eye state detection system and method of operating the same for utilizing a deep learning model to detect an eye state | |
| CN113033519B (en) | Living body detection method, estimation network processing method, device and computer equipment | |
| CN106919891B (en) | A kind of image processing method and device | |
| CN110705353A (en) | Method and device for identifying face to be shielded based on attention mechanism | |
| CN110287848A (en) | The generation method and device of video | |
| CN107844742A (en) | Facial image glasses minimizing technology, device and storage medium | |
| CN108369644A (en) | A kind of method and intelligent terminal quantitatively detecting face wrinkles on one's forehead | |
| CN113139439A (en) | Online learning concentration evaluation method and device based on face recognition | |
| CN111340758A (en) | Novel efficient iris image quality evaluation method based on deep neural network | |
| CN110008825A (en) | Palm grain identification method, device, computer equipment and storage medium | |
| CN111611860A (en) | Micro-expression occurrence detection method and detection system | |
| CN111860057A (en) | Face image blurring and living body detection method and device, storage medium and equipment | |
| CN111563492B (en) | Fall detection method, fall detection device and storage device | |
| Bhaskar et al. | Advanced algorithm for gender prediction with image quality assessment | |
| CN116740485A (en) | Training method and device for lesion detection model, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190802 |