Pedestrian detection method based on deep learning multi-network soft fusion

Abstract

The invention discloses a pedestrian detection method based on deep learning multi-network soft fusion, and relates to the technical field of image processing, target detection and deep learning. Themethod comprises the following steps: S1, inputting a to-be-processed image; S2, inputting the to-be-processed image into a YOLO v3 pedestrian candidate region generator taking Darknet-53 as a basic network, and generating a pedestrian candidate region; S3, inputting the to-be-processed image into a front-end prediction module, and outputting C feature maps; s4, inputting the C feature maps into asemantic segmentation system, and outputting C feature maps containing context information; s5, fusing a result of the semantic segmentation system with a pedestrian candidate result generated by a pedestrian candidate region generator; s6: outputting a detection image. According to the method, the pedestrian candidate region generator and the semantic segmentation system are subjected to parallel soft fusion, pedestrians in various challenge scenes are efficiently detected, and meanwhile, the small target detection capability is improved.

Description

technical field [0001] The invention relates to the technical fields of image processing, target detection and deep learning, in particular to a pedestrian detection method based on deep learning multi-network soft fusion. Background technique [0002] Object detection is an important problem in computer vision, which requires detecting the location of objects in video or digital images. Object detection is widely used in image detection, object recognition, video surveillance and other fields. Pedestrian detection, as a branch of object detection problems, involves detecting specific human categories, and it has a wide range of applications in areas such as autonomous driving, person recognition, and robotics. [0003] The goal of pedestrian detection algorithms is to draw bounding boxes in images or videos that accurately describe the location of pedestrians in real time. However, this is difficult to achieve due to the trade-off between accuracy and speed. Because low-...

AI Technical Summary

Problems solved by technology

The regression-based target detection method is also called the first-order method. Compared with the method based on the target candidate area, the regression-based pedestrian detection method is much simpler, and it does not require candidate area extraction and subsequent resampling operations. Real-time detection can be achieved to a certain extent, but its detection performance is lower than that of the second-order method

Images