A safety helmet wearing detection method based on depth features and video object detection

A target detection and deep feature technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as multi-time, lack of robustness, inability to adapt to complex environments, etc., to achieve transmission and reuse, Avoid feature extraction, improve the effect of time spent

Inactive Publication Date: 2019-03-08
江苏德劭信息科技有限公司
View PDF4 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing helmet detection methods are mainly to first extract the head area and design different algorithms to detect whether there is a helmet in the detection area. This kind of method can reduce the influence of the background environment on the helmet detection to a certain extent, but the extraction of the human head It takes a lot of time in the area, which affects the real-time detection; judging whether to wear a helmet based on the color of the helmet lacks robustness and cannot adapt to complex environments

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A safety helmet wearing detection method based on depth features and video object detection
  • A safety helmet wearing detection method based on depth features and video object detection
  • A safety helmet wearing detection method based on depth features and video object detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Taking the safety helmet wearing inspection on a real construction site as an example, the specific implementation method is as follows:

[0040] hardware equipment:

[0041] A. Camera (Brand: EZVIZ Model: CS-C3WN)

[0042] B. Processing Platform

[0043] The processing platform is AMAX's PSC-HB1X deep learning workstation, the processor is Inter(R)E5-2600v3, the main frequency is 2.1GHZ, the memory is 128GB, the hard disk size is 1TB, and the graphics card model is GeForce GTX Titan X. The operating environment is: Ubuntu 16.0.4, Python 2.7. or another computer with comparable performance.

[0044] Step1 video data acquisition

[0045] This method is implemented based on the video data in MP4 format collected by the camera on the construction site. The distance between the camera and the ground is about 3 meters, and the angle between the camera lens and the horizontal plane is about 45 degrees. Intercept and obtain the part of the video that includes construction...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a safety helmet wearing detection method based on depth features and video object detection, which comprises the following steps of video data acquisition; data marking of manual marking for the data collected by Step 1; data set preparation, wherein the data set consists of divided training set, test set and verification set, and each set contains pictures corresponding tothe original video, and the special training set and verification set also contain annotation data corresponding to each picture; the network construction and training of extracting features of key frames from input video and transferring them to different neighboring frames; transferring and multiplexing the key frame features to the features of the current frame by optical flow; the target classification and location frame prediction; network training, wherein the loss function of each ROI is the sum of cross entropy loss and boundary box regression loss.

Description

technical field [0001] The invention relates to a safety helmet wearing detection method based on depth features and video target detection, in particular to a safety helmet wearing detection method in a construction scene. Background technique [0002] In the actual construction scene, safety accidents occur frequently, causing a large number of personnel and property losses. Safety helmets can effectively protect the heads of construction workers, especially to reduce the degree of injury caused by possible falling objects. Whether construction personnel have safety helmets and follow-up tracking and alarming are of great significance to safe production. In construction site monitoring, it mainly relies on manpower to observe the monitoring screen or arrange regular inspections to detect the wearing of helmets. Large-scale construction sites require a considerable number of monitoring personnel to realize all the monitoring screens or inspect large construction areas. The...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/241G06F18/253
Inventor 邓杨敏李亨吕继团
Owner 江苏德劭信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap