Random ferns multi-feature fusion-based safety helmet detection method

Abstract

The invention discloses a random ferns multi-feature fusion-based safety helmet detection method. The method comprises the steps of extracting an HSI color histogram feature, an HOG feature and an HOFfeature of a sample; then performing training for a random ferns classifier of each type and each histogram feature; according to YOLOv2 of deep learning, obtaining a human body target to serve as the to-be-detected sample; and based on fusion of random ferns classifiers of multiple features, establishing a safety helmet detection framework. According to the method, a human body target region isquickly and accurately detected based on deep learning, so that the accuracy and speed of safety helmet position locating are improved; and according to a random ferns classifier algorithm, multiple feature training classifiers are fused, so that the classification accuracy is improved. The method is simple and effective, is good in timeliness, and has very good application prospects.

Description

technical field [0001] The invention belongs to the technical fields of computer vision, machine learning, etc., and more specifically relates to a safety helmet detection method based on random multi-feature fusion. Background technique [0002] With the development of computer information technology, image recognition technology has been widely used, such as medical diagnosis, fingerprint recognition, traffic navigation and video surveillance. This is very important for industrial production and safe production. [0003] In some high-risk sites, it is a necessary safety measure for staff to wear safety helmets. Nowadays, many industrial production sites have monitoring systems to monitor whether workers are wearing safety helmets. The monitoring is mainly carried out in two ways: manual on-duty and video monitoring. Since manual on-duty monitoring is prone to omissions and the monitoring range is limited and consumes manpower and material resources, it is now more inclin...

AI Technical Summary

Problems solved by technology

The disadvantage of these methods is that only a single feature is used, and the feature representation ability of the helmet target is insufficient. When encountering effects such as strong light, complex monitoring environment, low-resolution and blurred images, etc., the helmet cannot be accurately identified.

Images