Embedded safety helmet detection method and equipment

Abstract

The invention discloses an embedded safety helmet detection method and equipment. The method comprises the following steps: collecting to-be-detected image data; performing feature extraction on the to-be-detected image data by using a feature extraction network to obtain a plurality of feature maps of different dimensions; the feature extraction network is a simplified darknet-53 neural network of which the network layer number and the convolution kernel number are less than those of a traditional darknet-53 neural network; a constructed improved YOLOv3 network model is used to detect and identify the plurality of feature maps of different dimensions, and a safety helmet image region is obtained; wherein the improved YOLOv3 network model comprises four layers of YOLO detection layers. According to the invention, the network parameter quantity can be reduced, the detection speed is improved, and the precision is higher than that of the original YOLOv3.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to an embedded-based safety helmet detection method and equipment. Background technique [0002] As the most basic personal protective equipment for workers, hard hats are of great significance to the life safety of workers. However, some operators lack safety awareness, and behaviors of not wearing safety helmets often occur. In order to ensure the personal safety of workers, real-time detection of helmets is very necessary. [0003] With the rapid development of computer vision and convolutional neural networks, object detection technology has set off a new research boom, providing a new research perspective for helmet detection. The target detection algorithm is used to detect the helmet, and a higher accuracy rate is achieved. In the prior art, the accuracy rate of more than 90% is obtained for the detection of the helmet. Although a high accuracy rate has been achie...

AI Technical Summary

Problems solved by technology

Although a high accuracy rate has been achieved, there are also certain limitations. The current target detection algorithm based on convolutional neural network has huge parameters and consumes a lot of computing resources. The existing detection mode needs to transmit video files to the server. , and rely on a large-scale GPU computing platform for calculation and optimization, it is difficult to transplant to an embedded platform, and cannot meet the real-time and convenient detection needs

Images