CN107679524A - A kind of detection method of the safety cap wear condition based on video - Google Patents

A kind of detection method of the safety cap wear condition based on video Download PDF

Info

Publication number
CN107679524A
CN107679524A CN201711048272.9A CN201711048272A CN107679524A CN 107679524 A CN107679524 A CN 107679524A CN 201711048272 A CN201711048272 A CN 201711048272A CN 107679524 A CN107679524 A CN 107679524A
Authority
CN
China
Prior art keywords
mrow
mtd
mtr
region
head
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
Application number
CN201711048272.9A
Other languages
Chinese (zh)
Inventor
王国峰
刘琰
王思俊
毕磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Tiandi Weiye Information System Integration Co Ltd
Original Assignee
Tianjin Tiandi Weiye Information System Integration Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Tiandi Weiye Information System Integration Co Ltd filed Critical Tianjin Tiandi Weiye Information System Integration Co Ltd
Priority to CN201711048272.9A priority Critical patent/CN107679524A/en
Publication of CN107679524A publication Critical patent/CN107679524A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20104—Interactive definition of region of interest [ROI]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a kind of detection method of the safety cap wear condition based on video.This method obtains video image first, calculates two frame gray scale difference values and finds out moving region；Candidate region is found out using mass detection method；Then deformable component model system detectio is carried out for candidate region, finds clear and definite target head and shoulder region；Cascade system detection is carried out for head and shoulder region, finds out target cranial region；Hsv color space conversion is carried out for the head zone of video image；Under hsv color space, carry out classification for head zone image with neutral net and judge, determine target whether safe wearing cap；By hsv color space, safety cap color is judged；The testing result that last out-feed head region and safety cap are worn.Testing result of the present invention is accurate, reduces detection difficulty, improves detection efficiency.

Description

A kind of detection method of the safety cap wear condition based on video
Technical field
The invention belongs to detection technique field, more particularly, to a kind of detection side of the safety cap wear condition based on video Method.
Background technology
In being monitored in building site, by the human eye picture of viewing monitoring for a long time, or personnel's regular visit construction site is arranged, Observation workmen safety cap wearing situation is cumbersome and time consuming, it is necessary to enough monitoring personnel ability in extensive Centralized Monitoring All monitoring pictures can be monitored simultaneously or make an inspection tour the construction site of large area, are so not only caused manpower to waste, are monitored Personnel as fatigue and leave abnormal picture；Meanwhile personnel's discrepancy that construction area is extra, it can equally increase generation Unexpected risk.
The content of the invention
In view of this, the present invention is directed to propose a kind of detection method of the safety cap wear condition based on video, for examining The safety cap for surveying site ingress/egress points and construction area wears situation, by alarm or reports Surveillance center's mode to be assisted, The personnel of non-safe wearing cap or safe wearing cap color mistake are prevented, into construction area.
To reach above-mentioned purpose, the technical proposal of the invention is realized in this way：
A kind of detection method of the safety cap wear condition based on video, specifically comprises the following steps：
(1) video image is obtained, moving region is obtained using two field pictures gray scale difference value, in the moving region of acquisition Candidate region is obtained using mass detection method；
(2) for acquisition candidate region by deformable component model system detectio, obtain clear and definite target head and shoulder Region；
(3) for obtained target head and shoulder region, carry out cascade system detection to obtain target cranial region, then for Target cranial region carries out hsv color space conversion；
(4) for the head zone under obtained hsv color space, divided with neutral net for head zone image Class judge, determine target whether safe wearing cap, then by hsv color space, judge safety cap color；
(5) out-feed head region and safety cap wear testing result.
Further, the step (1) specifically includes carries out difference meter using the gray value of each pixel of two field pictures Calculate, the absolute value of difference is foreground pixel more than threshold marker, otherwise labeled as background pixel, for foreground image progress agglomerate Detection, adjacent foreground point is carried out subject fusion, obtains candidate region.
Further, in the step (2), the detection of deformable component model system includes training and identification, training When, deformable component model system is trained by input sample, during identification, the head and shoulder position by the system for moving target Put and be identified.
Further, in the step (3), the detection of cascade system includes training and identification, during training, by inputting sample This training cascade system, during identification, it is identified by head position of the system for head and shoulder region.
Further, in the step (3), hsv color space conversion method specifically includes
For original YUV color spaces, RGB color is converted to first：
R (x, y)=Y (x, y)+1.042* (V (x, y) -128)
G (x, y)=Y (x, y) -0.3441* (U (x, y) -128) -0.7141* (V (x, y) -128)
B (x, y)=Y (x, y)+1.772* (U (x, y) -128)
Then for RGB face space, hsv color space is converted to：
V (x, y)=max (R (x, y), G (x, y), B (x, y))
H (x, y)=H (x, y)+360, if H (x, y) ＜ 0.
Further, in the step (4), the process of neutral net includes training and identification, during training, by inputting sample This training nerve network system, during identification, it is identified by the system for the head position safe wearing cap in the case of.
Further, in the step (4), according to the threshold value of tri- components of HSV of detection head image, for the region Individual element is marked, and according to the difference of mark, mass detection is carried out for region, by area coinciding threshold value and close to head Color representated by the agglomerate of region top edge, depending on makeing safety cap color.
Relative to prior art, a kind of detection method of the safety cap wear condition based on video of the present invention has Following advantage：The invention provides the detection method of the safety cap wear condition based on monitor video, is come in and gone out for detecting building site The safety cap of mouth and construction area wears situation, by alarm or reports Surveillance center's mode to be assisted, prevents from not wearing The personnel of safety cap or safe wearing cap color mistake, into construction area；Judged based on moving object detection and feature Method, reduce the probability of happening of false alarm；It using color space conversion, can help preferably to extract feature, reduce inspection Survey difficulty；Trickle image information is not needed, the requirement to image definition is reduced, expands use range.
Brief description of the drawings
The accompanying drawing for forming the part of the present invention is used for providing a further understanding of the present invention, schematic reality of the invention Apply example and its illustrate to be used to explain the present invention, do not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of the deformable component model systematic training and identification process described in the embodiment of the present invention；
Fig. 2 is the flow chart of the cascade system training and identification process described in the embodiment of the present invention；
Fig. 3 for the embodiment of the present invention neural metwork training and identification process flow chart.
Embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the present invention can phase Mutually combination.
Describe the present invention in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
The present invention provides a kind of detection method of the safety cap wear condition based on video, specifically includes
(1) mathematic interpolation is carried out first with the gray value of each pixel of two field pictures, the absolute value of difference is more than threshold Value is labeled as foreground pixel；
|pt(x,y)-pt-1(x, y) | then (x, y) belongs to prospect to ＞ threshold, is otherwise background.
Wherein, pt(x, y) be t time (x, y) coordinate pixel value, pt-1(x, y) is t-1 time (x, y) coordinate pixel Value, threshold is judgment threshold；
Mass detection is carried out to foreground image, connected foreground point is carried out subject fusion, obtains the candidate region of target.
(2) for acquisition candidate region by deformable component model system detectio, obtain clear and definite target head and shoulder Region；
The training of deformable component model (DPM) system is as shown in Figure 1 with identification.Wherein, train prediction process can be with It is divided into training stage and cognitive phase two parts：
During training, deformable component model (DPM) system is trained by input sample；
During identification, it is identified by head and shoulder position of the system for moving target.
(3) for obtained target head and shoulder region, cascade system detection is carried out to obtain target cranial region, it is then right Hsv color space conversion is carried out in target cranial region；
The training of cascade system is as shown in Figure 2 with identification.Wherein, training prediction process can be divided into training stage and identification Stage two parts：
During training, cascade system is trained by input sample
During identification, it is identified by head position of the system for head and shoulder region.
Hsv color space conversion is carried out for the head position image of determination, conversion method is as follows
For original YUV color spaces, RGB color is converted to first：
R (x, y)=Y (x, y)+1.402* (V (x, y) -128)
G (x, y)=Y (x, y) -0.3441* (U (x, y) -128) -0.7141
* (V (x, y) -128)
B (x, y)=Y (x, y)+1.772* (U (x, y) -128)
Then for RGB face space, hsv color space is converted to：
V (x, y)=max (R (x, y), G (x, y), B (x, y))
H (x, y)=H (x, y)+360, if H (x, y) ＜ 0.
(4) for the head zone under obtained hsv color space, carried out with neutral net for head zone image Classification judge, determine target whether safe wearing cap, then by hsv color space, judge safety cap color；
The training of neutral net is as shown in Figure 3 with identification.Wherein, training prediction process can be divided into training stage and identification Stage two parts：
During training, nerve network system is trained by input sample.
During identification, it is identified by the system for the head position safe wearing cap in the case of.
According to the threshold value of tri- components of HSV of detection head image, it is marked for the region individual element, 0 represents Black, 1 represents red, and 2 represent blueness, and 3 represent white, and 4 represent yellow, and 255 represent other colors.According to the difference of mark, Mass detection is carried out for region, by the color representated by area coinciding threshold value and agglomerate close to head zone top edge, depending on Make safety cap color.
(5) out-feed head region and safety cap wear testing result.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention God any modification, equivalent substitution and improvements made etc., should be included in the scope of the protection with principle.

Claims (7)

  1. A kind of 1. detection method of the safety cap wear condition based on video, it is characterised in that：Specifically comprise the following steps：
    (1) video image is obtained, moving region is obtained using two field pictures gray scale difference value, for being used in the moving region of acquisition Mass detection method obtains candidate region；
    (2) for acquisition candidate region by deformable component model system detectio, obtain clear and definite target head and shoulder region；
    (3) for obtained target head and shoulder region, cascade system detection is carried out to obtain target cranial region, then for target Head zone carries out hsv color space conversion；
    (4) for the head zone under obtained hsv color space, carry out classification for head zone image with neutral net and sentence It is disconnected, determine target whether safe wearing cap, then by hsv color space, judge safety cap color；
    (5) out-feed head region and safety cap wear testing result.
  2. A kind of 2. detection method of safety cap wear condition based on video according to claim 1, it is characterised in that：Institute State step (1) and specifically include and carry out mathematic interpolation using the gray value of each pixel of two field pictures, the absolute value of difference is more than Threshold marker is foreground pixel, otherwise labeled as background pixel, mass detection is carried out for foreground image, adjacent foreground point Subject fusion is carried out, obtains candidate region.
  3. A kind of 3. detection method of safety cap wear condition based on video according to claim 1, it is characterised in that：Institute State in step (2), the detection of deformable component model system includes training and identification, during training, is trained by input sample Deformable component model system, during identification, it is identified by head and shoulder position of the system for moving target.
  4. A kind of 4. detection method of safety cap wear condition based on video according to claim 1, it is characterised in that：Institute State in step (3), the detection of cascade system includes training and identification, during training, passes through input sample and trains cascade system, identification When, it is identified by head position of the system for head and shoulder region.
  5. A kind of 5. detection method of safety cap wear condition based on video according to claim 1, it is characterised in that：Institute State in step (3), hsv color space conversion method specifically includes
    For original YUV color spaces, RGB color is converted to first：
    R (x, y)=Y (x, y)+1.042* (V (x, y) -128)
    G (x, y)=Y (x, y) -0.3441* (U (x, y) -128) -0.7141* (V (x, y) -128)
    B (x, y)=Y (x, y)+1.772* (U (x, y) -128)
    Then for RGB face space, hsv color space is converted to：
    V (x, y)=max (R (x, y), G (x, y), B (x, y))
    <mrow> <mi>S</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mfrac> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>min</mi> <mrow> <mo>(</mo> <mi>R</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>G</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>B</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> </mfrac> </mtd> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>i</mi> <mi>f</mi> </mrow> </mtd> <mtd> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>&amp;NotEqual;</mo> <mn>0</mn> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mrow> <mi>o</mi> <mi>t</mi> <mi>h</mi> <mi>e</mi> <mi>r</mi> <mi>w</mi> <mi>i</mi> <mi>s</mi> <mi>e</mi> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
    <mfenced open = "" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>H</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mfrac> <mrow> <mn>60</mn> <mo>*</mo> <mrow> <mo>(</mo> <mi>G</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>B</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>min</mi> <mrow> <mo>(</mo> <mi>R</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>G</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>B</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> </mfrac> </mtd> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>i</mi> <mi>f</mi> </mrow> </mtd> <mtd> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>=</mo> <mi>R</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> <mtr> <mtd> <mfrac> <mrow> <mn>120</mn> <mo>+</mo> <mn>60</mn> <mo>*</mo> <mrow> <mo>(</mo> <mi>B</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>R</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>min</mi> <mrow> <mo>(</mo> <mi>R</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>G</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>B</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> </mfrac> </mtd> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>i</mi> <mi>f</mi> </mrow> </mtd> <mtd> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>=</mo> <mi>G</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> <mtr> <mtd> <mfrac> <mrow> <mn>240</mn> <mo>+</mo> <mn>60</mn> <mo>*</mo> <mrow> <mo>(</mo> <mi>R</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>G</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mi>min</mi> <mrow> <mo>(</mo> <mi>R</mi> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>G</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>B</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>)</mo> </mrow> </mfrac> </mtd> <mtd> <mtable> <mtr> <mtd> <mrow> <mi>i</mi> <mi>f</mi> </mrow> </mtd> <mtd> <mrow> <mi>V</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> <mo>=</mo> <mi>B</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mtd> </mtr> </mtable> </mfenced> </mrow> </mtd> </mtr> </mtable> </mfenced>
    H (x, y)=H (x, y)+360, if H (x, y) ＜ 0.
  6. A kind of 6. detection method of safety cap wear condition based on video according to claim 1, it is characterised in that：Institute To state in step (4), the process of neutral net includes training and identification, and during training, nerve network system is trained by input sample, During identification, it is identified by the system for the head position safe wearing cap in the case of.
  7. A kind of 7. detection method of safety cap wear condition based on video according to claim 1, it is characterised in that：Institute State in step (4), according to the threshold value of tri- components of HSV of detection head image, be marked for the region individual element, root According to the difference of mark, mass detection is carried out for region, by area coinciding threshold value and close to the agglomerate institute of head zone top edge The color of representative, depending on makeing safety cap color.
CN201711048272.9A 2017-10-31 2017-10-31 A kind of detection method of the safety cap wear condition based on video Pending CN107679524A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711048272.9A CN107679524A (en) 2017-10-31 2017-10-31 A kind of detection method of the safety cap wear condition based on video

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711048272.9A CN107679524A (en) 2017-10-31 2017-10-31 A kind of detection method of the safety cap wear condition based on video

Publications (1)

Publication Number Publication Date
CN107679524A true CN107679524A (en) 2018-02-09

Family

ID=61143378

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711048272.9A Pending CN107679524A (en) 2017-10-31 2017-10-31 A kind of detection method of the safety cap wear condition based on video

Country Status (1)

Country Link
CN (1) CN107679524A (en)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108319934A (en) * 2018-03-20 2018-07-24 武汉倍特威视***有限公司 Safety cap wear condition detection method based on video stream data
CN108416797A (en) * 2018-02-27 2018-08-17 鲁东大学 A kind of method, equipment and the storage medium of detection Behavioral change
CN108460358A (en) * 2018-03-20 2018-08-28 武汉倍特威视***有限公司 Safety cap recognition methods based on video stream data
CN108537256A (en) * 2018-03-26 2018-09-14 北京智芯原动科技有限公司 A kind of safety cap wears recognition methods and device
CN108564069A (en) * 2018-05-04 2018-09-21 中国石油大学(华东) A kind of industry safe wearing cap video detecting method
CN108647619A (en) * 2018-05-02 2018-10-12 安徽大学 The detection method and device that safety cap is worn in a kind of video based on deep learning
CN109117827A (en) * 2018-09-05 2019-01-01 武汉市蓝领英才科技有限公司 Work clothes work hat wearing state automatic identifying method and alarm system based on video
CN109542215A (en) * 2018-10-09 2019-03-29 中国矿业大学 Safety cap wears monitoring method
CN109753898A (en) * 2018-12-21 2019-05-14 中国三峡建设管理有限公司 A kind of safety cap recognition methods and device
CN110188724A (en) * 2019-06-05 2019-08-30 中冶赛迪重庆信息技术有限公司 The method and system of safety cap positioning and color identification based on deep learning
CN110210274A (en) * 2018-02-28 2019-09-06 杭州海康威视数字技术股份有限公司 Safety cap detection method, device and computer readable storage medium
CN110263609A (en) * 2019-01-27 2019-09-20 杭州品茗安控信息技术股份有限公司 A kind of automatic identifying method of safety cap wear condition
CN110287787A (en) * 2019-05-21 2019-09-27 平安国际智慧城市科技股份有限公司 Image-recognizing method, device and computer readable storage medium
CN110414342A (en) * 2019-06-24 2019-11-05 台州宏达电力建设有限公司 A kind of movement human detection recognition method based on video image processing technology
CN110688893A (en) * 2019-08-22 2020-01-14 成都通甲优博科技有限责任公司 Detection method for wearing safety helmet, model training method and related device
CN111079731A (en) * 2019-12-03 2020-04-28 中冶赛迪重庆信息技术有限公司 Configuration system, method, equipment and medium based on safety helmet identification monitoring system
CN111428641A (en) * 2020-03-24 2020-07-17 深圳供电局有限公司 Secure dressing detection method and device, computer equipment and readable storage medium
CN112232313A (en) * 2020-03-06 2021-01-15 杭州宇泛智能科技有限公司 Method and device for detecting wearing state of personal safety helmet in video and electronic equipment
CN112488031A (en) * 2020-12-11 2021-03-12 华能华家岭风力发电有限公司 Safety helmet detection method based on color segmentation

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103745226A (en) * 2013-12-31 2014-04-23 国家电网公司 Dressing safety detection method for worker on working site of electric power facility
CN105303193A (en) * 2015-09-21 2016-02-03 重庆邮电大学 People counting system for processing single-frame image
CN105469069A (en) * 2015-12-09 2016-04-06 上海工业自动化仪表研究院 Safety helmet video detection method for production line data acquisition terminal
CN105488490A (en) * 2015-12-23 2016-04-13 天津天地伟业数码科技有限公司 Judge dressing detection method based on video
CN106295551A (en) * 2016-08-05 2017-01-04 南京理工大学 A kind of personal security cap wear condition real-time detection method based on video analysis
CN106339723A (en) * 2016-08-30 2017-01-18 天津天地伟业数码科技有限公司 Video based river illegal dredging detection method
CN106372662A (en) * 2016-08-30 2017-02-01 腾讯科技（深圳）有限公司 Helmet wearing detection method and device, camera, and server
CN106446926A (en) * 2016-07-12 2017-02-22 重庆大学 Transformer station worker helmet wear detection method based on video analysis
CN107103617A (en) * 2017-03-27 2017-08-29 国机智能科技有限公司 The recognition methods of safety cap wearing state and system based on optical flow method

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103745226A (en) * 2013-12-31 2014-04-23 国家电网公司 Dressing safety detection method for worker on working site of electric power facility
CN105303193A (en) * 2015-09-21 2016-02-03 重庆邮电大学 People counting system for processing single-frame image
CN105469069A (en) * 2015-12-09 2016-04-06 上海工业自动化仪表研究院 Safety helmet video detection method for production line data acquisition terminal
CN105488490A (en) * 2015-12-23 2016-04-13 天津天地伟业数码科技有限公司 Judge dressing detection method based on video
CN106446926A (en) * 2016-07-12 2017-02-22 重庆大学 Transformer station worker helmet wear detection method based on video analysis
CN106295551A (en) * 2016-08-05 2017-01-04 南京理工大学 A kind of personal security cap wear condition real-time detection method based on video analysis
CN106339723A (en) * 2016-08-30 2017-01-18 天津天地伟业数码科技有限公司 Video based river illegal dredging detection method
CN106372662A (en) * 2016-08-30 2017-02-01 腾讯科技（深圳）有限公司 Helmet wearing detection method and device, camera, and server
CN107103617A (en) * 2017-03-27 2017-08-29 国机智能科技有限公司 The recognition methods of safety cap wearing state and system based on optical flow method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ABU H. M. RUBAIYAT ET AL.: "Automatic Detection of Helmet Uses for Construction Safety", 《2016 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE WORKSHOPS》 *
周艳青 等: "基于 LBP 统计特征的低分辨率安全帽识别", 《计算机***应用》 *
沈沛意 等: "《DAVINCI技术剖析及实战应用开发指南》", 30 April 2012, 西安电子科技大学出版社 *

Cited By (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416797A (en) * 2018-02-27 2018-08-17 鲁东大学 A kind of method, equipment and the storage medium of detection Behavioral change
CN110210274A (en) * 2018-02-28 2019-09-06 杭州海康威视数字技术股份有限公司 Safety cap detection method, device and computer readable storage medium
CN108460358A (en) * 2018-03-20 2018-08-28 武汉倍特威视***有限公司 Safety cap recognition methods based on video stream data
CN108319934A (en) * 2018-03-20 2018-07-24 武汉倍特威视***有限公司 Safety cap wear condition detection method based on video stream data
CN108537256A (en) * 2018-03-26 2018-09-14 北京智芯原动科技有限公司 A kind of safety cap wears recognition methods and device
CN108537256B (en) * 2018-03-26 2021-09-17 北京智芯原动科技有限公司 Method and device for identifying wearing of safety helmet
CN108647619A (en) * 2018-05-02 2018-10-12 安徽大学 The detection method and device that safety cap is worn in a kind of video based on deep learning
CN108564069A (en) * 2018-05-04 2018-09-21 中国石油大学(华东) A kind of industry safe wearing cap video detecting method
CN108564069B (en) * 2018-05-04 2021-09-21 中国石油大学(华东) Video detection method for industrial safety helmet
CN109117827A (en) * 2018-09-05 2019-01-01 武汉市蓝领英才科技有限公司 Work clothes work hat wearing state automatic identifying method and alarm system based on video
CN109117827B (en) * 2018-09-05 2020-11-24 武汉市蓝领英才科技有限公司 Video-based method for automatically identifying wearing state of work clothes and work cap and alarm system
CN109542215B (en) * 2018-10-09 2022-03-08 中国矿业大学 Wearing monitoring method for safety helmet
CN109542215A (en) * 2018-10-09 2019-03-29 中国矿业大学 Safety cap wears monitoring method
CN109753898A (en) * 2018-12-21 2019-05-14 中国三峡建设管理有限公司 A kind of safety cap recognition methods and device
CN110263609A (en) * 2019-01-27 2019-09-20 杭州品茗安控信息技术股份有限公司 A kind of automatic identifying method of safety cap wear condition
CN110287787A (en) * 2019-05-21 2019-09-27 平安国际智慧城市科技股份有限公司 Image-recognizing method, device and computer readable storage medium
CN110287787B (en) * 2019-05-21 2022-05-06 平安国际智慧城市科技股份有限公司 Image recognition method, image recognition device and computer-readable storage medium
CN110188724A (en) * 2019-06-05 2019-08-30 中冶赛迪重庆信息技术有限公司 The method and system of safety cap positioning and color identification based on deep learning
CN110188724B (en) * 2019-06-05 2023-02-28 中冶赛迪信息技术(重庆)有限公司 Method and system for helmet positioning and color recognition based on deep learning
CN110414342A (en) * 2019-06-24 2019-11-05 台州宏达电力建设有限公司 A kind of movement human detection recognition method based on video image processing technology
CN110688893A (en) * 2019-08-22 2020-01-14 成都通甲优博科技有限责任公司 Detection method for wearing safety helmet, model training method and related device
CN111079731A (en) * 2019-12-03 2020-04-28 中冶赛迪重庆信息技术有限公司 Configuration system, method, equipment and medium based on safety helmet identification monitoring system
CN112232313A (en) * 2020-03-06 2021-01-15 杭州宇泛智能科技有限公司 Method and device for detecting wearing state of personal safety helmet in video and electronic equipment
CN111428641A (en) * 2020-03-24 2020-07-17 深圳供电局有限公司 Secure dressing detection method and device, computer equipment and readable storage medium
CN112488031A (en) * 2020-12-11 2021-03-12 华能华家岭风力发电有限公司 Safety helmet detection method based on color segmentation

Similar Documents

Publication Publication Date Title
CN107679524A (en) A kind of detection method of the safety cap wear condition based on video
CN111144263B (en) Construction worker high-falling accident early warning method and device
CN106295551B (en) A kind of personnel safety cap wear condition real-time detection method based on video analysis
CN111445524B (en) Scene understanding-based construction site worker unsafe behavior identification method
CN106503716A (en) A kind of safety cap recognition methods that is extracted based on color and contour feature and system
CN108319934A (en) Safety cap wear condition detection method based on video stream data
CN111191586B (en) Method and system for inspecting wearing condition of safety helmet of personnel in construction site
CN101563710B (en) Method and apparatus for identifying properties of an object detected by a video surveillance camera
KR101709751B1 (en) An automatic monitoring system for dangerous situation of persons in the sea
CN112396658B (en) Indoor personnel positioning method and system based on video
CN107103617A (en) The recognition methods of safety cap wearing state and system based on optical flow method
CN108460358A (en) Safety cap recognition methods based on video stream data
CN110602449A (en) Intelligent construction safety monitoring system method in large scene based on vision
CN108647619A (en) The detection method and device that safety cap is worn in a kind of video based on deep learning
CN106228150A (en) Smog detection method based on video image
CN110136172A (en) The detection method that safeguard is worn before a kind of miner goes into the well
CN105893963A (en) Method for screening out optimal easily-recognizable frame of single pedestrian target in video
CA3081967A1 (en) Method and system for connected advanced flare analytics
CN102999994A (en) Flame detection device based on video image analysis
CN115223249A (en) Quick analysis and identification method for unsafe behaviors of underground personnel based on machine vision
CN111222420A (en) FTP protocol-based low-bandwidth-requirement helmet identification method
CN106372566A (en) Digital signage-based emergency evacuation system and method
CN101521805A (en) Helmet-site detecting system on construction field and detecting method thereof
Huang et al. Skeleton-based automatic assessment and prediction of intrusion risk in construction hazardous areas
CN103020587A (en) View analyzing method based on video image 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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180209