基于无源领域自适应的低光照显著性目标检测  

Low-Light Salient Object Detection Based on Source-Free Domain Adaptation

作　　者：李书玮 黄正翔 胡云[1,2] 刘兴 卢笑 郭畅 吴成中 王耀南 LI Shuwei;HUANG Zhengxiang;HU Yun;LIU Xing;LU Xiao;GUO Chang;WU Chengzhong;WANG Yaonan(College of Engineering and Design,Hunan Normnal University,Changsha 410081,Hunan,China;The Key Laboratory of lntelligent Sernsing and Rehabilitation Robotics of Hunan Province Universities,Changsha 410081,Hunan,China;Jiangxi Communication Terminal Industrial Technology Research Institute Co.,Ltd,Ji'an 343600,Jiangxi,Chima)

机构地区：[1]湖南师范大学工程与设计学院,湖南长沙410081 [2]智能传感与康复机器人湖南省高校重点实验室,湖南长沙410081 [3]江西省通讯终端产业技术研究院有限公司,江西吉安343600

出　　处：《计算机工程》2025年第4期75-84,共10页Computer Engineering

基　　金：国家自然科学基金(62007007,62277004);湖南省学位与研究生教学改革研究重点项目(2022JGZD026);湖南省自然科学基金(2023JJ30415,2022JJ30395);江西省重大科技研发专项项目(20232ACC01007,20232ABC03A09);吉安市科技计划“揭榜挂帅”项目(20233TGV06020)。

摘　　要：为了解决低光照条件下校园环境等场景监控摄像头图像质量和监控效果受影响而带来的安全问题,提出一种低光照显著性目标检测(SOD)方法,以提高低光照条件下目标检测能力。针对低光照条件下图像的显著性特征弱化和缺乏大规模标注数据的问题,提出一种无源领域自适应(SFDA)方法,将正常光照图像(源域)下训练的模型知识迁移至低光照条件图像(目标域)。该方法采用两阶段策略:在第一阶段,利用源域模型生成低光照图像的伪标签,为提高伪标签生成的质量,提出集合熵最小化损失抑制高熵区域,同时引入选择性投票方法来增强伪标签的生成;在第二阶段,采用基于增强引导一致性的教师-学生网络自训练方法对显著图进行精细化,进一步提高检测结果的精度。在SOD-LL数据集上的实验结果表明,所提出的方法在低光照场景下总体性能优于其他图像显著性检测方法,相较于正常光照的SOD方法,其平均绝对误差(MAE)降低15.15%,加权F1值(wFm)提高4.73%。To address the security issues arising from the degradation of image quality and monitor the effectiveness of surveillance cameras in low-light campus environments,a low-light Salient Object Detection(SOD)method is proposed to enhance target detection capability under low-light conditions.Given the challenges of weakened salient features and the lack of large-scale annotated data in low-light images,a Source-Free Domain Adaptation(SFDA)method for low-light SOD is proposed to transfer the model knowledge trained on normallighting images(source domain)to low-light images(target domain).The proposed method employs a two-stage strategy.In the first stage,pseudo-labels for low-light images are generated using the source domain model.To improve the quality of the pseudo-label generation,an ensemble entropy minimization loss is proposed to suppress high-entropy regions.In addition,a selective voting method is introduced to enhance pseudo-label generation.In the second stage,a teacher-student network self-training method based on enhanced guided consistency is employed to refine the saliency maps,further improving the accuracy of the detection results.Experimental results on the SOD-LL dataset show that the proposed method outperforms other image saliency detection methods in low-light scenarios.Compared to normal-light SOD methods,the Mean Absolute Error(MAE)is reduced by 15.15%,and the Weighted F1 value(wFm)is increased by 4.73%.

关 键 词：显著性目标检测 低光照场景 无源领域自适应 伪标签 教师-学生网络 集合熵最小化 选择性投票 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]