CN109635697A - Electric operating personnel safety dressing detection method based on YOLOv3 target detection - Google Patents
Electric operating personnel safety dressing detection method based on YOLOv3 target detection Download PDFInfo
- Publication number
- CN109635697A CN109635697A CN201811475125.4A CN201811475125A CN109635697A CN 109635697 A CN109635697 A CN 109635697A CN 201811475125 A CN201811475125 A CN 201811475125A CN 109635697 A CN109635697 A CN 109635697A
- Authority
- CN
- China
- Prior art keywords
- electric operating
- yolov3
- dressing
- operating personnel
- network model
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Abstract
The electric operating personnel safety dressing detection method based on YOLOv3 target detection that the invention discloses a kind of.The technical solution adopted by the present invention are as follows: firstly, collecting the dressing picture of electric operating personnel, make training sample set；Secondly, building YOLOv3 network model, and network model is trained using training sample set, obtain the YOLOv3 network model of training completion；Again, the input data for YOLOv3 network model electric operating on-site supervision video completed as training detects the security wear situation of the electric operating personnel in video.Compared with the conventional method of artificial design features, this method automatically extracts feature and realizes detection, strong applicability, generalization height, and the safety cap wearing and work clothes dressing situation of electric operating personnel in video can be detected simultaneously, it can be applied to the video monitoring system at electric operating scene.
Description
Technical field
The invention belongs to field of intelligent video surveillance, are related to a kind of electric operating personnel peace based on YOLOv3 target detection
Full dressing detection method, can be applied to the video monitoring system at electric operating scene.
Background technique
There is many operation fields in daily power generation, associate power safety work order enters work to related personnel
The safety requirements that industry scene should abide by is made that stringent regulation, wherein for correct safe wearing cap and wear work clothes have it is bright
Really require.Security wear is most important for the personal safety for ensureing operating personnel, therefore, to the operation people for entering operation field
Member carries out video monitoring, can effectively ensure that and supervise the security wear of related operating personnel, the safety for reducing operating personnel is hidden
Suffer from.
In order to reduce the workload for manually checking video monitoring, constantly there is the security wear for video monitoring to detect automatically
Method is suggested, wherein focusing mostly in the detection of safety cap wearing, the detection method for work clothes is simultaneously few, can be right simultaneously
Safety cap is worn and work clothes wears method that situation is detected with regard to less.It in the conventional method, is to use manually to set mostly
Count and extract feature, then the traditional mode identified by mode identification method.There is only engineer spies for this mode
The complexity problem of sign, there is also robustness and generalization difference problem.
YOLOv3 (You Only Look Once Version 3) is a kind of state-of-the-art technology currently used for target detection,
Accuracy height and strong real-time, can be used in the real-time analysis of monitor video.
Summary of the invention
The electric operating personnel safety dressing detection based on YOLOv3 target detection that the purpose of the present invention is to provide a kind of
Method goes out the security wear situation of operating personnel in operation field by the real-time analysis detection to monitor video, can be right
The personnel of dressing are not alerted in time as required, ensure the personal safety of operating personnel.
To achieve the above object, the technical solution adopted by the present invention are as follows: the electric operating people based on YOLOv3 target detection
Member's security wear detection method comprising:
Step 1, the dressing picture of electric operating personnel is collected, training sample set is made；
Step 2, YOLOv3 network model is constructed, and network model is trained using training sample set, is trained
The YOLOv3 network model of completion；
Step 3, the input data for YOLOv3 network model electric operating on-site supervision video completed as training, inspection
Survey the security wear situation of the electric operating personnel in video.
As the supplement of the above method, the step 1 includes:
Step 11, the different dressing pictures for collecting different personnel, there is a following two approach: first, from different electric operatings
Interception saves the picture comprising operating personnel frame by frame in the history monitor video at scene；Second, allow different personnel to wear electric power work
Industry work clothes and safe wearing cap, the correct and wrong dressing situation of simulation simultaneously make different gestures, shoot and protect from different perspectives
File a document piece；
Step 12, it is modified using image processing method to the picture being collected into, by original picture and derives picture together
As the material maked sample, increase sample size by this method；
Step 13, the classification for dividing dressing situation, determines class label；
Step 14, the security wear situation in each picture is stamped into corresponding label, made for training YOLOv3
The training sample set of network.
As the supplement of the above method, in the step 11, the wrong dressing situation is specifically included: not wearing completely
Safety cap；Do not wear work clothes completely；There is safety cap but does not wear；There is work clothes but does not wear；Roll any bottom of s trouser leg；It rolls any
One hand sleeve；Work clothes button is not detained and exposes internal clothes or skin.
As the supplement of the above method, in the step 12, the picture amending method is specifically included: being turned over left and right
Turn；Different angle rotation；Add different degrees of noise；Change contrast；Change brightness.
As the supplement of the above method, in the step 13, the dressing situation classification is specifically included: safety cap is worn
Wear specification；Safety cap is worn lack of standardization；Work clothes dress specification；Work clothes dress is lack of standardization.
As the supplement of the above method, the step 2 includes:
Step 21, YOLOv3 network model is constructed；
Step 22, object is carried out to the darknet-53 module in YOLOv3 network model using ImageNet image data set
Body classification based training obtains the YOLOv3 network model that part training is completed；
Step 23, on the basis of step 22 result, using Pascal VOC Data data set to complete YOLOv3 into
The training of row target detection, obtains the YOLOv3 network model that can be used in target detection；
Step 24, on the basis of step 23 result, using the training sample set made in step 1 to YOLOv3 network mould
Type carries out security wear detection training, obtains the YOLOv3 network model of security wear detection.
As the supplement of the above method, the step 3 includes:
Step 31, electric operating on-site supervision video is obtained, is input in the YOLOv3 network model of security wear detection；
Step 32, the calculating of the YOLOv3 network model by security wear detection, obtains all electric operatings in video
The security wear situation of personnel, rectangle frame information and safety cap wear condition label, personnel's body part including person head
Rectangle frame information and work clothes wear situation label；
Step 33, the video after output detection.
As the supplement of the above method, in the step 33, if using rectangle frame there are electric operating personnel in video
Head and the body part of personnel are framed respectively, and shows corresponding security wear label, and dressing situation lack of standardization is alerted；
If personnel are not present in video, original video is shown.
As the supplement of the above method, the step 14 includes:
Step 141, the head that everyone is framed in picture with rectangle frame, calculates and the central point for recording the rectangle frame is sat
Mark, width, height, while corresponding label is stamped to the personnel safety cap wear condition in the rectangle frame；
Step 142, the body part that everyone is framed in picture with rectangle frame, calculates and records the central point of the rectangle frame
Coordinate, width, height, while wearing situation to person works' clothes in the rectangle frame and stamping corresponding label；
Step 143: by picture together with subsidiary all rectangle frame information and corresponding forming label in picture at symbol
Close a training sample of YOLOv3 input format.
The present invention provides a kind of electric operating personnel safety dressing detection method based on YOLOv3 target detection, can apply
In video monitoring apparatus or system.For video acquired in video acquisition device or video monitoring system, image data, utilize
YOLOv3 target detection network model after specific set of data training carries out the security wear situation of electric operating personnel
Detection.The difficulty of security wear feature and the problem of conventional custom method generalization difference, detection are extracted the present invention overcomes artificial
Efficiency and accuracy rate are higher.
Detailed description of the invention
Fig. 1 is the electric operating personnel safety dressing detection method provided by the present invention based on YOLOv3 target detection
Flow chart；
Fig. 2 is the flow chart that electric operating personnel dressing sample set is made described in step 1 of the present invention；
Fig. 3 is the flow chart of dressing situation in marker samples picture described in step 14 of the present invention；
Fig. 4 is the flow chart of training of safety dressing detection model described in step 2 of the present invention；
Fig. 5 is the flow chart for carrying out security wear situation in detection video described in step 3 of the present invention using model.
Specific embodiment
Below in conjunction with attached drawing, elaborate to preferred embodiment.It is emphasized that following the description is only exemplary
, the range and its application being not intended to be limiting of the invention.
As shown in Figure 1, the electric operating personnel safety dressing detection side provided by the invention based on YOLOv3 target detection
Method, specific implementation step are as follows.
Step 1: collecting the dressing picture of electric operating personnel, make training sample set.As shown in Fig. 2, production is for instructing
The electric operating personnel's dressing training sample set for practicing network model is specifically implemented according to the following steps:
Step 11: collecting the different dressing pictures of different personnel.There is a following two approach, first, from different electric operatings
Interception saves the picture comprising operating personnel frame by frame in the history monitor video at scene；Second, it allows 20 (wherein men and women is fifty-fifty)
The personnel that age is not equal, height figure is different wear electric operating work clothes and safe wearing cap (different colours), and simulation is correct
With wrong dressing situation and make different gestures, shot from front, the back side, left side, four, right side different angle and save photo.
Wherein, mistake dressing situation specifically includes: not wearing a safety helmet completely；Do not wear work clothes completely；There is safety cap but not
It wears；There is work clothes but does not wear；Roll any bottom of s trouser leg；Roll any hand sleeve；Work clothes button is not detained and exposes inside
Clothes or skin.
Step 12: being modified using image processing method to the picture being collected into, by original picture and derive picture together
As the material maked sample, increase sample size by this method.
Wherein, picture amending method specifically includes: left and right overturning；Rotate clockwise 10 degree, counterclockwise 10 degree of rotation；Addition
Gaussian noise, salt-pepper noise；Increase and decrease contrast 10%；Increase and decrease brightness 10%.
Step 13: dividing the classification of dressing situation, determine class label.
Wherein, dressing situation classification specifically includes: safety cap wears specification；Safety cap is worn lack of standardization；Work clothes dress
Specification；Work clothes dress is lack of standardization.Corresponding class label is identified as helmet_ok；helmet_error；suit_ok；
suit_error。
Step 14: the security wear situation in each picture being stamped into corresponding mark using marking tool Yolo_mark
Label, make the sample set for training YOLOv3 network.As shown in figure 3, the implementation steps for marking and labelling to a picture
It is as follows:
Step 141: living in picture everyone head with solid-line rectangle circle, calculate and record the central point of the rectangle frame
Coordinate, width, height, while corresponding label, i.e. helmet_ok are stamped to the personnel safety cap wear condition in the rectangle frame
Or helmet_error.
Step 142: living in picture everyone body part with solid-line rectangle circle, calculate and record in the rectangle frame
Heart point coordinate, width, height, while wearing situation to person works' clothes in the rectangle frame and stamping corresponding label, i.e. suit_
ok；suit_error.
Step 143: by picture together with subsidiary all rectangle frame information and corresponding forming label in picture at symbol
Close a sample of YOLOv3 input format.
Step 2: building YOLOv3 network model, and network model is carried out using the dressing sample set of electric operating personnel
Training.As shown in figure 4, the training of YOLOv3 network model is specifically implemented according to the following steps:
Step 21: building YOLOv3 network model.
Step 22: object is carried out to the darknet-53 module in the YOLOv3 network using ImageNet image data set
Classification based training obtains the YOLOv3 network model that part training is completed.
Step 23: on the basis of step 22 result, using Pascal VOC Data data set to the complete YOLOv3 net
Network model carries out target detection training, obtains the YOLOv3 network model that can be used in target detection.
Step 24: on the basis of step 23 result, using the electric operating personnel's dressing training sample set made in step 1
Security wear detection training is carried out to the YOLOv3 network model, obtaining, which can be used in, detects electric operating personnel safety dressing feelings
The YOLOv3 network model of condition.
Step 3: utilizing the personnel safety in the YOLOv3 network model detection electric operating on-site supervision video trained
Dressing situation.As shown in figure 5, using electric operating personnel safety dressing situation in YOLOv3 network model detection monitor video
Specific step is as follows:
Step 31: obtaining electric operating on-site supervision video, be input in the YOLOv3 network model of security wear detection.
Step 32: calculating is made inferences to input video using the YOLOv3 network model that security wear detects, depending on
The security wear situation of all electric operating personnel in frequency, i.e. the rectangle frame information of person head and safety cap wear condition mark
Label, the rectangle frame information of personnel's body part and work clothes wear situation label.
Step 33: exporting and show the video after detection.If being distinguished there are electric operating personnel with rectangle frame in video
Head and the body part of personnel are framed, and shows corresponding security wear label, dressing situation lack of standardization is alerted；If depending on
Personnel are not present in frequency, then show original video.
The present invention is passing through a large amount of public image data set pre-training using current newest YOLOv3 target detection model
It, can after the further training of electric operating personnel safety dressing training sample set in network models afterwards
Situation is worn to the safety cap wear condition and work clothes of electric operating personnel simultaneously to be measured in real time, strong applicability, promote
Property it is high.
Technical solution of the present invention has been done by above preferred embodiment and has further been discussed in detail, but should be strong
It adjusts, specific embodiment described above is not considered as limitation of the present invention.It is read in those skilled in the art
After above content, under the premise of not departing from the thought of technical solution of the present invention, for a variety of modifications of the invention made, replace
It changes, retouch and all will be apparent, be regarded as protection scope of the present invention.Therefore, protection scope of the present invention should be by institute
Attached claim limits.
Claims (9)
1. the electric operating personnel safety dressing detection method based on YOLOv3 target detection characterized by comprising
Step 1, the dressing picture of electric operating personnel is collected, training sample set is made；
Step 2, YOLOv3 network model is constructed, and network model is trained using training sample set, obtains training completion
YOLOv3 network model；
Step 3, the input data for YOLOv3 network model electric operating on-site supervision video completed as training, detection view
The security wear situation of electric operating personnel in frequency.
2. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as described in claim 1, special
Sign is that the step 1 includes:
Step 11, the different dressing pictures for collecting different personnel, there is a following two approach: first, from different electric operatings scenes
History monitor video in frame by frame interception save include operating personnel picture；Second, allow different personnel to wear electric operating work
Make clothes and safe wearing cap, the correct and wrong dressing situation of simulation simultaneously makes different gestures, shoots from different perspectives and save photograph
Piece；
Step 12, it is modified using image processing method to the picture being collected into, by original picture and derivative picture conduct together
The material that makes sample increases sample size by this method；
Step 13, the classification for dividing dressing situation, determines class label；
Step 14, the security wear situation in each picture is stamped into corresponding label, made for training YOLOv3 network
Training sample set.
3. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as claimed in claim 2, special
Sign is, in the step 11,
The wrong dressing situation specifically includes: not wearing a safety helmet completely；Do not wear work clothes completely；There is safety cap but does not wear；
There is work clothes but does not wear；Roll any bottom of s trouser leg；Roll any hand sleeve；Work clothes button is not detained and exposes internal clothes
Or skin.
4. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as claimed in claim 2, special
Sign is, in the step 12,
The picture amending method specifically includes: left and right overturning；Different angle rotation；Add different degrees of noise；Change pair
Degree of ratio；Change brightness.
5. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as claimed in claim 2, special
Sign is, in the step 13,
The dressing situation classification specifically includes: safety cap wears specification；Safety cap is worn lack of standardization；Work clothes dress rule
Model；Work clothes dress is lack of standardization.
6. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as described in claim 1, special
Sign is that the step 2 includes:
Step 21, YOLOv3 network model is constructed；
Step 22, object point is carried out to the darknet-53 module in YOLOv3 network model using ImageNet image data set
Class training obtains the YOLOv3 network model that part training is completed；
Step 23, on the basis of step 22 result, mesh is carried out to complete YOLOv3 using Pascal VOC Data data set
Mark detection training, obtains the YOLOv3 network model that can be used in target detection；
Step 24, on the basis of step 23 result, using the training sample set made in step 1 to YOLOv3 network model into
The detection training of row security wear, obtains the YOLOv3 network model of security wear detection.
7. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as described in claim 1, special
Sign is that the step 3 includes:
Step 31, electric operating on-site supervision video is obtained, is input in the YOLOv3 network model of security wear detection；
Step 32, the calculating of the YOLOv3 network model by security wear detection, obtains all electric operating personnel in video
Security wear situation, the square of rectangle frame information and safety cap wear condition label, personnel's body part including person head
Shape frame information and work clothes wear situation label；
Step 33, the video after output detection.
8. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as claimed in claim 7, special
Sign is, in the step 33, if there are electric operating personnel in video, framed respectively with rectangle frame personnel head and
Body part, and show corresponding security wear label, dressing situation lack of standardization is alerted；If personnel are not present in video,
Then show original video.
9. the electric operating personnel safety dressing detection method based on YOLOv3 target detection as claimed in claim 7, special
Sign is that the step 14 includes:
Step 141, the head that everyone is framed in picture with rectangle frame, calculates and records the center point coordinate of the rectangle frame, width
Degree, height, while corresponding label is stamped to the personnel safety cap wear condition in the rectangle frame；
Step 142, the body part that everyone is framed in picture with rectangle frame, calculates and the central point for recording the rectangle frame is sat
Mark, width, height, while wearing situation to person works' clothes in the rectangle frame and stamping corresponding label；
Step 143: by picture together with subsidiary all rectangle frame information in picture and corresponding forming label at meeting
One training sample of YOLOv3 input format.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811475125.4A CN109635697A (en) | 2018-12-04 | 2018-12-04 | Electric operating personnel safety dressing detection method based on YOLOv3 target detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811475125.4A CN109635697A (en) | 2018-12-04 | 2018-12-04 | Electric operating personnel safety dressing detection method based on YOLOv3 target detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635697A true CN109635697A (en) | 2019-04-16 |
Family
ID=66071071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811475125.4A Pending CN109635697A (en) | 2018-12-04 | 2018-12-04 | Electric operating personnel safety dressing detection method based on YOLOv3 target detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635697A (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046605A (en) * | 2019-04-25 | 2019-07-23 | 大连海事大学 | The multidimensional information of view-based access control model tracking proofreads mechanical processing site management system |
| CN110111016A (en) * | 2019-05-14 | 2019-08-09 | 深圳供电局有限公司 | Precarious position monitoring method, device and the computer equipment of operating personnel |
| CN110399905A (en) * | 2019-07-03 | 2019-11-01 | 常州大学 | The detection and description method of safety cap wear condition in scene of constructing |
| CN110502965A (en) * | 2019-06-26 | 2019-11-26 | 哈尔滨工业大学 | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude |
| CN110543986A (en) * | 2019-08-27 | 2019-12-06 | 广东电网有限责任公司 | Intelligent monitoring system and monitoring method for external hidden danger of power transmission line |
| CN110599735A (en) * | 2019-07-31 | 2019-12-20 | 国网浙江省电力有限公司杭州供电公司 | Warning method based on intelligent identification of operation violation behaviors of transformer substation |
| CN110751125A (en) * | 2019-10-29 | 2020-02-04 | 秒针信息技术有限公司 | Wearing detection method and device |
| CN110807429A (en) * | 2019-10-23 | 2020-02-18 | 西安科技大学 | Construction safety detection method and system based on tiny-YOLOv3 |
| CN111080693A (en) * | 2019-11-22 | 2020-04-28 | 天津大学 | Robot autonomous classification grabbing method based on YOLOv3 |
| CN111144263A (en) * | 2019-12-20 | 2020-05-12 | 山东大学 | Construction worker high-fall accident early warning method and device |
| CN111178302A (en) * | 2019-12-31 | 2020-05-19 | 北大方正集团有限公司 | Method and device for detecting specific clothing person |
| CN111178212A (en) * | 2019-12-23 | 2020-05-19 | 深圳供电局有限公司 | Image recognition method and device, computer equipment and storage medium |
| CN111310723A (en) * | 2020-03-12 | 2020-06-19 | 智洋创新科技股份有限公司 | Deep learning technology-based wearing standard analysis method for transformer substation personnel |
| CN111401314A (en) * | 2020-04-10 | 2020-07-10 | 上海东普信息科技有限公司 | Dressing information detection method, device, equipment and storage medium |
| CN111401278A (en) * | 2020-03-20 | 2020-07-10 | 重庆紫光华山智安科技有限公司 | Helmet identification method and device, electronic equipment and storage medium |
| CN111563557A (en) * | 2020-05-12 | 2020-08-21 | 山东科华电力技术有限公司 | Method for detecting target in power cable tunnel |
| CN111652046A (en) * | 2020-04-17 | 2020-09-11 | 济南浪潮高新科技投资发展有限公司 | Safe wearing detection method, equipment and system based on deep learning |
| CN111814763A (en) * | 2020-08-26 | 2020-10-23 | 长沙鹏阳信息技术有限公司 | Noninductive attendance and uniform identification method based on tracking sequence |
| CN111860471A (en) * | 2020-09-21 | 2020-10-30 | 之江实验室 | Work clothes wearing identification method and system based on feature retrieval |
| CN112149512A (en) * | 2020-08-28 | 2020-12-29 | 成都飞机工业（集团）有限责任公司 | Helmet wearing identification method based on two-stage deep learning |
| CN112365692A (en) * | 2020-11-08 | 2021-02-12 | 华能通辽风力发电有限公司 | System and method for detecting whether safety helmet is worn by operation and maintenance personnel in wind power plant |
| CN112528855A (en) * | 2020-12-11 | 2021-03-19 | 南方电网电力科技股份有限公司 | Electric power operation dressing standard identification method and device |
| CN112580739A (en) * | 2020-12-28 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Method and device for determining training sample set |
| CN112634233A (en) * | 2020-12-24 | 2021-04-09 | 四川电器集团中低压智能配电有限公司 | Application method in power distribution equipment based on image detection and analysis technology |
| CN112861576A (en) * | 2019-11-27 | 2021-05-28 | 顺丰科技有限公司 | Employee image detection method and device, computer equipment and storage medium |
| CN112966618A (en) * | 2021-03-11 | 2021-06-15 | 京东数科海益信息科技有限公司 | Dressing identification method, device, equipment and computer readable medium |
| CN113179386A (en) * | 2021-03-19 | 2021-07-27 | 江西铜业股份有限公司 | Mining area safety intelligent monitoring broadcasting system and intelligent broadcasting method thereof |
| CN113256934A (en) * | 2021-05-18 | 2021-08-13 | 哈尔滨理工大学 | Safety detection system for aerial work personnel |
| CN113297913A (en) * | 2021-04-26 | 2021-08-24 | 云南电网有限责任公司信息中心 | Method for identifying dressing specification of distribution network field operating personnel |
| CN113313186A (en) * | 2021-06-09 | 2021-08-27 | 广东电网有限责任公司 | Method and system for identifying non-standard wearing work clothes |
| CN113553979A (en) * | 2021-07-30 | 2021-10-26 | 国电汉川发电有限公司 | Safety clothing detection method and system based on improved YOLO V5 |
| CN113657165A (en) * | 2020-08-10 | 2021-11-16 | 广东电网有限责任公司 | Dangerous climbing behavior recognition algorithm in electric power field operation |
| CN113673335A (en) * | 2020-08-10 | 2021-11-19 | 广东电网有限责任公司 | Dangerous boundary-crossing behavior recognition algorithm in electric power field operation |
| CN113807240A (en) * | 2021-09-15 | 2021-12-17 | 国网河北省电力有限公司衡水供电分公司 | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition |
| WO2022111271A1 (en) * | 2020-11-24 | 2022-06-02 | 华为云计算技术有限公司 | Clothing standardization detection method and apparatus |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120146792A1 (en) * | 2010-12-09 | 2012-06-14 | Nicholas De Luca | Automated monitoring and control of contamination in a production area |
| CN108052900A (en) * | 2017-12-12 | 2018-05-18 | 成都睿码科技有限责任公司 | A kind of method by monitor video automatic decision dressing specification |
| CN108319934A (en) * | 2018-03-20 | 2018-07-24 | 武汉倍特威视系统有限公司 | Safety cap wear condition detection method based on video stream data |
-
2018
- 2018-12-04 CN CN201811475125.4A patent/CN109635697A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120146792A1 (en) * | 2010-12-09 | 2012-06-14 | Nicholas De Luca | Automated monitoring and control of contamination in a production area |
| CN108052900A (en) * | 2017-12-12 | 2018-05-18 | 成都睿码科技有限责任公司 | A kind of method by monitor video automatic decision dressing specification |
| CN108319934A (en) * | 2018-03-20 | 2018-07-24 | 武汉倍特威视系统有限公司 | Safety cap wear condition detection method based on video stream data |
Non-Patent Citations (3)
| Title |
|---|
| BAIDU_38371925: "https://blog.csdn.net/baidu_38371925/article/details/78421612", 《基于DARKNET框架的IMAGENET数据分类预训练》 * |
| ZWX1995ZWX: "https://blog.csdn.net/zwx1995zwx/article/details/79874434", 《YOLOV3在PASCAL_VOC数据集上的训练（一）》 * |
| 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》 * |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046605A (en) * | 2019-04-25 | 2019-07-23 | 大连海事大学 | The multidimensional information of view-based access control model tracking proofreads mechanical processing site management system |
| CN110111016A (en) * | 2019-05-14 | 2019-08-09 | 深圳供电局有限公司 | Precarious position monitoring method, device and the computer equipment of operating personnel |
| CN110502965A (en) * | 2019-06-26 | 2019-11-26 | 哈尔滨工业大学 | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude |
| CN110502965B (en) * | 2019-06-26 | 2022-05-17 | 哈尔滨工业大学 | Construction safety helmet wearing monitoring method based on computer vision human body posture estimation |
| CN110399905A (en) * | 2019-07-03 | 2019-11-01 | 常州大学 | The detection and description method of safety cap wear condition in scene of constructing |
| CN110599735A (en) * | 2019-07-31 | 2019-12-20 | 国网浙江省电力有限公司杭州供电公司 | Warning method based on intelligent identification of operation violation behaviors of transformer substation |
| CN110543986A (en) * | 2019-08-27 | 2019-12-06 | 广东电网有限责任公司 | Intelligent monitoring system and monitoring method for external hidden danger of power transmission line |
| CN110807429B (en) * | 2019-10-23 | 2023-04-07 | 西安科技大学 | Construction safety detection method and system based on tiny-YOLOv3 |
| CN110807429A (en) * | 2019-10-23 | 2020-02-18 | 西安科技大学 | Construction safety detection method and system based on tiny-YOLOv3 |
| CN110751125A (en) * | 2019-10-29 | 2020-02-04 | 秒针信息技术有限公司 | Wearing detection method and device |
| CN111080693A (en) * | 2019-11-22 | 2020-04-28 | 天津大学 | Robot autonomous classification grabbing method based on YOLOv3 |
| CN112861576A (en) * | 2019-11-27 | 2021-05-28 | 顺丰科技有限公司 | Employee image detection method and device, computer equipment and storage medium |
| CN111144263A (en) * | 2019-12-20 | 2020-05-12 | 山东大学 | Construction worker high-fall accident early warning method and device |
| CN111144263B (en) * | 2019-12-20 | 2023-10-13 | 山东大学 | Construction worker high-falling accident early warning method and device |
| CN111178212A (en) * | 2019-12-23 | 2020-05-19 | 深圳供电局有限公司 | Image recognition method and device, computer equipment and storage medium |
| CN111178302A (en) * | 2019-12-31 | 2020-05-19 | 北大方正集团有限公司 | Method and device for detecting specific clothing person |
| CN111310723A (en) * | 2020-03-12 | 2020-06-19 | 智洋创新科技股份有限公司 | Deep learning technology-based wearing standard analysis method for transformer substation personnel |
| CN111401278A (en) * | 2020-03-20 | 2020-07-10 | 重庆紫光华山智安科技有限公司 | Helmet identification method and device, electronic equipment and storage medium |
| CN111401314B (en) * | 2020-04-10 | 2023-06-13 | 上海东普信息科技有限公司 | Dressing information detection method, device, equipment and storage medium |
| CN111401314A (en) * | 2020-04-10 | 2020-07-10 | 上海东普信息科技有限公司 | Dressing information detection method, device, equipment and storage medium |
| CN111652046A (en) * | 2020-04-17 | 2020-09-11 | 济南浪潮高新科技投资发展有限公司 | Safe wearing detection method, equipment and system based on deep learning |
| CN111563557A (en) * | 2020-05-12 | 2020-08-21 | 山东科华电力技术有限公司 | Method for detecting target in power cable tunnel |
| CN111563557B (en) * | 2020-05-12 | 2023-01-17 | 山东科华电力技术有限公司 | Method for detecting target in power cable tunnel |
| CN113673335A (en) * | 2020-08-10 | 2021-11-19 | 广东电网有限责任公司 | Dangerous boundary-crossing behavior recognition algorithm in electric power field operation |
| CN113657165A (en) * | 2020-08-10 | 2021-11-16 | 广东电网有限责任公司 | Dangerous climbing behavior recognition algorithm in electric power field operation |
| CN111814763B (en) * | 2020-08-26 | 2021-01-08 | 长沙鹏阳信息技术有限公司 | Noninductive attendance and uniform identification method based on tracking sequence |
| CN111814763A (en) * | 2020-08-26 | 2020-10-23 | 长沙鹏阳信息技术有限公司 | Noninductive attendance and uniform identification method based on tracking sequence |
| CN112149512A (en) * | 2020-08-28 | 2020-12-29 | 成都飞机工业（集团）有限责任公司 | Helmet wearing identification method based on two-stage deep learning |
| CN111860471A (en) * | 2020-09-21 | 2020-10-30 | 之江实验室 | Work clothes wearing identification method and system based on feature retrieval |
| CN112365692A (en) * | 2020-11-08 | 2021-02-12 | 华能通辽风力发电有限公司 | System and method for detecting whether safety helmet is worn by operation and maintenance personnel in wind power plant |
| WO2022111271A1 (en) * | 2020-11-24 | 2022-06-02 | 华为云计算技术有限公司 | Clothing standardization detection method and apparatus |
| CN112528855A (en) * | 2020-12-11 | 2021-03-19 | 南方电网电力科技股份有限公司 | Electric power operation dressing standard identification method and device |
| CN112634233A (en) * | 2020-12-24 | 2021-04-09 | 四川电器集团中低压智能配电有限公司 | Application method in power distribution equipment based on image detection and analysis technology |
| CN112580739A (en) * | 2020-12-28 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Method and device for determining training sample set |
| CN112580739B (en) * | 2020-12-28 | 2024-02-27 | 上海明略人工智能(集团)有限公司 | Method and device for determining training sample set |
| CN112966618B (en) * | 2021-03-11 | 2024-02-09 | 京东科技信息技术有限公司 | Dressing recognition method, apparatus, device and computer readable medium |
| CN112966618A (en) * | 2021-03-11 | 2021-06-15 | 京东数科海益信息科技有限公司 | Dressing identification method, device, equipment and computer readable medium |
| CN113179386A (en) * | 2021-03-19 | 2021-07-27 | 江西铜业股份有限公司 | Mining area safety intelligent monitoring broadcasting system and intelligent broadcasting method thereof |
| CN113179386B (en) * | 2021-03-19 | 2023-04-25 | 江西铜业股份有限公司 | Mining area safety intelligent monitoring broadcasting system and intelligent broadcasting method thereof |
| CN113297913A (en) * | 2021-04-26 | 2021-08-24 | 云南电网有限责任公司信息中心 | Method for identifying dressing specification of distribution network field operating personnel |
| CN113297913B (en) * | 2021-04-26 | 2023-05-26 | 云南电网有限责任公司信息中心 | Identification method for dressing specification of distribution network field operators |
| CN113256934A (en) * | 2021-05-18 | 2021-08-13 | 哈尔滨理工大学 | Safety detection system for aerial work personnel |
| CN113313186B (en) * | 2021-06-09 | 2023-01-24 | 广东电网有限责任公司 | Method and system for identifying irregular wearing work clothes |
| CN113313186A (en) * | 2021-06-09 | 2021-08-27 | 广东电网有限责任公司 | Method and system for identifying non-standard wearing work clothes |
| CN113553979B (en) * | 2021-07-30 | 2023-08-08 | 国电汉川发电有限公司 | Safety clothing detection method and system based on improved YOLO V5 |
| CN113553979A (en) * | 2021-07-30 | 2021-10-26 | 国电汉川发电有限公司 | Safety clothing detection method and system based on improved YOLO V5 |
| CN113807240A (en) * | 2021-09-15 | 2021-12-17 | 国网河北省电力有限公司衡水供电分公司 | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635697A (en) | Electric operating personnel safety dressing detection method based on YOLOv3 target detection | |
| CN106022304B (en) | A kind of real-time body's sitting posture situation detection method based on binocular camera | |
| CN110110629A (en) | Personal information detection method and system towards indoor environmental condition control | |
| CN108596011A (en) | A kind of face character recognition methods and device based on combined depth network | |
| CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| CN107590452A (en) | A kind of personal identification method and device based on gait and face fusion | |
| CN104951773B (en) | A kind of real-time face recognition monitoring system | |
| CN108108684A (en) | A kind of attention detection method for merging line-of-sight detection | |
| CN104143086B (en) | Portrait compares the application process on mobile terminal operating system | |
| CN109657609A (en) | Face identification method and system | |
| CN107895160A (en) | Human face detection and tracing device and method | |
| CN107679503A (en) | A kind of crowd's counting algorithm based on deep learning | |
| CN104143079A (en) | Method and system for face attribute recognition | |
| CN109522853A (en) | Face datection and searching method towards monitor video | |
| CN104091173B (en) | A kind of gender identification method and device based on web camera | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| CN107480586B (en) | Face characteristic point displacement-based biometric photo counterfeit attack detection method | |
| CN105930798A (en) | Tongue image quick detection and segmentation method based on learning and oriented to handset application | |
| CN110074788A (en) | A kind of body data acquisition methods and device based on machine learning | |
| CN108960076A (en) | Ear recognition and tracking based on convolutional neural networks | |
| CN106204223A (en) | Image processing method and system | |
| CN109587394A (en) | A kind of intelligence patterning process, electronic equipment and storage medium | |
| CN108648228A (en) | A kind of binocular infrared human body dimension measurement method and system | |
| CN111912531A (en) | Dynamic human body trunk temperature analysis method based on intelligent thermal imaging video analysis |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190416 |