Improved pedestrian target detection algorithm in Faster R-CNN tunnel environment

Abstract

The invention discloses an improved pedestrian target detection algorithm in a Faster R-CNN tunnel environment, and the algorithm comprises the following steps: building a pedestrian target data set in a highway tunnel environment, and randomly dividing the pedestrian target data set into a training set and a test set; optimizing Anchor in the Faster R-CNN network by adopting an unsupervised learning algorithm on the basis of the training set obtained in the above steps to obtain anchor setting; establishing a cavity convolution pyramid structure; designing an attention mechanism for processing the feature information and enhancing the expression ability of the features; and establishing a pedestrian detection framework in an expressway tunnel environment. According to the method, the pedestrian target feature extraction capability under the conditions of dark images, small target relative scale, vehicle lamp influence and the like is improved, and the pedestrian target detection ratein a tunnel environment is improved.

Description

technical field [0001] The invention relates to the technical field of pedestrian detection in computer vision, in particular to an improved Faster R-CNN tunnel environment pedestrian target detection algorithm. Background technique [0002] In the relevant laws and regulations, pedestrians are prohibited from appearing on the expressway, but some people pass on the expressway with a fluke mentality, which has caused a huge safety hazard to the safe operation of the expressway. Automatic detection technology has important practical significance to the safe operation of expressways. Through the analysis of the surveillance video in the highway tunnel environment, it is found that the pictures are generally dark and the pedestrian targets are relatively small, and there is interference from the headlights, which makes the pedestrian feature extraction difficult, resulting in the pedestrian target detection effect in the tunnel environment is not very good. Therefore, it has i...

AI Technical Summary

Problems solved by technology

[0002] In the relevant laws and regulations, pedestrians are prohibited from appearing on the expressway, but some people pass on the expressway with a fluke mentality, which has caused a huge safety hazard to the safe operation of the expressway. Automatic detection technology has important practical significance to the safe operation of expressway

Through the analysis of the surveillance video in the highway tunnel environment, it is found that the pictures are generally dark and the pedestrian targets are relatively small. At the same time, there is interference from car lights, which makes it difficult to extract pedestrian features, resulting in poor detection of pedestrian targets in the tunnel environment.

Images