电子学报2023，Vol.51Issue(10)：2821-2830,10.DOI:10.12263/DZXB.20221396
一种基于Night-YOLOX的低照度目标检测方法
A Low-Illumination Object Detection Method Based on Night-YOLOX
摘要
Abstract
Images captured in low-illumination environments often have many quality problems,such as weak bright-ness,low contrast,much noise,and detail loss.These problems will lead to inaccurate localization and object classification errors when using the existing object detection models to detect low-light images,resulting in low detection accuracy.Aim-ing at the above phenomena,this paper proposes a low-illumination object detection method called Night-YOLOX.First,the low-level feature gathering module(LFGM)is designed to be incorporated into the backbone.Capturing more effective low-level features in low-illumination scenes is beneficial to locating objects.The LFGM aggregates more discriminative low-lev-el features from the shallow feature maps and feeds them into the high-level feature maps and the deep convolution stages,so as to compensate for the loss of low-level edge,contour,and texture features during feature extraction in low-light images.Then,the attention guidance block(AGB)is designed to be embedded in the neck of the detection model.The AGB reduces the influence of noise interference in low-light images,guides the detection model to infer the complete object regions and ex-tract more useful object feature information,so as to improve the accuracy of object classification.Finally,experiments are conducted on the real low-light image dataset ExDark.The experimental results show that compared with other mainstream object detection methods,the proposed Night-YOLOX has better detection performance in low-illumination scenarios.关键词
目标检测/低照度图像/低级特征/注意力机制/YOLOXKey words
object detection/low-light images/low-level features/attention mechanism/YOLOX分类
信息技术与安全科学引用本文复制引用
江泽涛,施道权,雷晓春,何玉婷,李慧,周永刚..一种基于Night-YOLOX的低照度目标检测方法[J].电子学报,2023,51(10):2821-2830,10.基金项目
国家自然科学基金(No.62172118) （No.62172118）
广西自然科学基金重点项目(No.2021GXNSFDA196002) （No.2021GXNSFDA196002）
广西图像图形智能处理重点实验项目(No.GIIP2203,No.GIIP2204) （No.GIIP2203,No.GIIP2204）
广西研究生教育创新计划(No.YCB2021070,No.YCBZ2018052,No.YCSW2022269,No.2021YCXS071)National Natural Science Foundation of China(No.62172118) （No.YCB2021070,No.YCBZ2018052,No.YCSW2022269,No.2021YCXS071）
Key Projects of Guangxi Natural Science Foundation(No.2021GXNSFDA196002) （No.2021GXNSFDA196002）
Guangxi Key Laboratory of Image and Graphic Intelligent Processing(No.GIIP2203,No.GIIP2204) （No.GIIP2203,No.GIIP2204）
Innovation Project of Guangxi Graduate Education(No.YCB2021070,No.YCBZ2018052,No.YCSW2022269,No.2021YCXS071) （No.YCB2021070,No.YCBZ2018052,No.YCSW2022269,No.2021YCXS071）
