Human body detection method in low-illumination environment based on image enhancement, electronic equipment and storage medium

Abstract

The invention discloses a human body detection method in a low-illumination environment based on image enhancement, electronic equipment and a storage medium, and the detection method comprises the steps: inputting a low-illumination image into a low-illumination image enhancement module, and obtaining an enhanced image; inputting the enhanced image into an improved human body detection module, and outputting a human body detection prediction result; performing multi-stage joint optimization on the low-illumination image enhancement module and the human body detection module through a multi-task loss function, and training to obtain an end-to-end low-illumination human body detection framework; and inputting the low-illumination image into the trained end-to-end low-illumination human body detection framework, carrying out image enhancement and human body detection, and outputting a human body detection prediction result. The end-to-end low-illumination image human body detection framework constructed by the invention realizes higher detection precision through mutual adaptation of the low-illumination image enhancement module and the human body detection module, and has stronger robustness for human body detection in different illumination environments.

Description

technical field [0001] The invention belongs to the technical field of human body detection, and in particular relates to a human body detection method, electronic equipment and storage medium based on image enhancement in a low illumination environment. Background technique [0002] Human detection in a low-light environment refers to the precise positioning of human targets in the captured images under environmental conditions where the illumination is lower than the normal standard. Images taken in low-illumination environments generally have the characteristics of low brightness, low contrast, reduced gray value range, and color distortion. There are problems such as loss of human target feature information in the image and indistinguishable foreground and background. The probability of missed detection and false detection in the optimized general human detection method is greatly increased. [0003] Image enhancement is performed on low-illumination images to improve c...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the embodiments of the present invention is to provide an image enhancement-based human body detection method in a low-light environment, electronic equipment, and a storage medium, to construct an illumination enhancement curve estimation network, to construct an end-to-end low-light human body detection framework, to construct a multi-task loss function, and to realize High-precision human detection in low-illumination environments, to solve the adverse effects of low-light environments on the performance of human detection algorithms and the problem of not paying attention to the accuracy of subsequent target detection advanced tasks in low-light image enhancement

Images