Pedestrian detection method based on multi-layer convolution feature fusion

Abstract

The invention discloses a pedestrian detection method based on multi-layer convolution feature fusion, and the method comprises the steps: constructing a new feature extraction network Darknet-61 through the reconstruction of a residual network, enabling the feature extraction network Darknet-61 to have the capability of six times of down-sampling, and increasing the output of a YOLO output layerof a YOLOv3 algorithm from 3 layers to 5 layers through the new feature extraction network Darknet-61; subsequently, obtaining a target candidate box on the basis of a YOLOv3 algorithm with five-layeroutput through a k-mean algorithm, and carrying out subsequent processing on the current optimal candidate box in the target candidate box through an NMS method. According to the method, the Darknet-53 feature extraction network is improved, four residual networks and convolution layers are introduced, the down-sampling frequency is increased, a 7 * 7 feature map is output, the characterization capability of low-layer features is enhanced, and the precision of large-scale pedestrian detection is improved.

Description

technical field [0001] The invention relates to the field of pedestrian detection, in particular to a pedestrian detection method for multi-layer convolution feature fusion. Background technique [0002] Pedestrian detection, as a core technology of smart devices, enables machines and devices to obtain surrounding video or image information, and uses the powerful analysis capabilities of computers to visually process the acquired information, so that they can observe and understand complex things like humans. ability to analyze. Help people complete various recognition and detection tasks. [0003] Pedestrian detection is an important research direction in the field of computer vision. The computer recognizes whether there are pedestrians from images or video clips. If there are pedestrians, it further detects the specific location of pedestrians, so as to accurately calibrate their position coordinates. Among them It is widely used in manufacturing, military, medical and ...

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a pedestrian detection method of multi-layer convolution feature fusion to solve the problem of missed detection in pedestrian detection of different scales in the prior art

Images