Safety helmet wearing detection method, device and equipment and storage medium

A safety helmet and detection result technology, applied in neural learning methods, instruments, data processing applications, etc., can solve the problems of low recognition accuracy and efficiency, missed detection and false detection, etc., to improve detection accuracy and detection efficiency, and avoid leakage. The effect of detection and false detection

CN113177513AActive Publication Date: 2021-07-27STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST +2
1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2021-07-27

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a safety helmet wearing detection method, device and equipment and a computer readable storage medium, and the method comprises the steps: inputting a to-be-detected image into a target safety helmet detection neural network model, and extracting a human body target feature map through a target detection SSD network; inputting the human body target feature map into a key area attention mechanism network to determine a head key area; segmenting and extracting a head region feature map from the human body target feature map by using a key region feature map segmentation network according to the position of the head key region; and inputting the head region feature map into a safety helmet detection dynamic model, judging the confidence output by the branch network, and outputting a detection result of which the confidence is greater than or equal to a threshold value as a safety helmet wearing detection result. According to the method, the device, the equipment and the computer readable storage provided by the invention, the precision and the efficiency of the detection result of the wearing condition of the safety helmet are improved, and the phenomena of missing detection and false detection caused by a complex background of a substation scene are effectively avoided.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of deep learning and artificial intelligence, in particular to a safety helmet wearing detection method, device, equipment and computer-readable storage medium. Background technique

[0002] Substation is an important facility in the national grid. Wearing safety helmets is an important measure to ensure the safety of workers. Therefore, it is of great significance to provide a method that can monitor the wearing of safety helmets by workers in real time. The existing safety helmet wearing detection algorithm has the following problems: a. The data set about the worker's safety helmet is relatively scarce, and the proportion of valid data is relatively low; The proportion is low, the feature information is not clear, and there will inevitably be missed detection problems; c. The environment of the substation is relatively complex, and it is prone to false detections caused by complex images. The abo...

Examples

Embodiment Construction

[0044] The core of the present invention is to provide a safety helmet wearing detection method, device, equipment and computer-readable storage medium, which improves the accuracy and efficiency of safety helmet wearing detection, and can effectively avoid the occurrence of missed detection and false detection.

[0045] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0046] Please refer to figure 1 , figure 1 It is a flow chart of the first specific embodiment of...