适合跨域目标检测的雾霾图像增强  

Cross-domain object detection based foggy image enhancement

作　　者：郭强[1] 浦世亮[2] 张世峰 李波[1] Guo Qiang;Pu Shiliang;Zhang Shifeng;Li Bo(Beijing Key Laboratory of Digital Media,Beihang University,Beijing 100191,China;Hangzhou Hikvision Digital Technology Company,Hangzhou 310000,China)

机构地区：[1]北京航空航天大学数字媒体实验室,北京100191 [2]杭州海康威视数字技术股份有限公司,杭州310000

出　　处：《中国图象图形学报》2022年第5期1481-1492,共12页Journal of Image and Graphics

基　　金：浙江省科技计划项目(2022C01082);海康威视—北航智能感知与计算联合实验室资助项目。

摘　　要：目的室外监控在雾霾天气所采集图像的成像清晰度和目标显著程度均会降低,当在雾霾图像提取与人眼视觉质量相关的自然场景统计特征和与目标检测精度相关的目标类别语义特征时,这些特征与从清晰图像提取的特征存在明显差别。为了提升图像质量并且在缺乏雾霾天气目标检测标注数据的情况下提升跨域目标检测效果,本文综合利用传统方法和深度学习方法,提出了一种无监督先验混合图像特征级增强网络。方法利用本文提出的传统先验构成雾气先验模块;其后连接一个特征级增强网络模块,将去散射图像视为输入图像,利用像素域和特征域的损失实现场景统计特征和目标类别语义相关表观特征的增强。该混合网络突破了传统像素级增强方法难以表征抽象特征的制约,同时克服了对抗迁移网络难以准确衡量无重合图像域在特征空间分布差异的弱点,也减弱了识别算法对于低能见度天候采集图像标注数据的依赖,可以同时提高雾霾图像整体视觉感知质量以及局部目标可识别表现。结果实验在两个真实雾霾图像数据集、真实图像任务驱动的测试数据集(real-world taskdriven testing set,RTTS)和自动驾驶雾天数据集(foggy driving dense)上与最新的5种散射去除方法进行了比较,相比于各指标中性能第2的算法,本文方法结果中梯度比指标R值平均提高了50.83%,属于感知质量指标的集成自然图像质量评价指标(integrated local natural image quality evaluator,IL-NIQE)值平均提高了6.33%,属于跨域目标检测指标的平均精准率(mean average precision,MAP)值平均提高了6.40%,平均查全率Recall值平均提高了7.79%。实验结果表明,本文方法结果在视觉质量和目标可识别层面都优于对比方法,并且本文方法对于高清视频的处理速度达50帧/s,且无需标注数据,因而在监控系统具有更高的实用价值。结论本文方法可ObjectiveThe acquired images relating fog,mist and damp weather conditions are subjected to the atmospheric scattering,affecting the observation and target analysis of intelligent detection systems.The scattering of reflected lights deduct the contrast of images in the context of the increased scene depth,and the uneven sky illumination constrains images visibility.This two constraints yield to deduction and fuzzes on the weak texture in foggy images.The degradation of foggy images affects the pixels based statistical distributions like saturation and weber contrast and changes the statistical distribution between pixels,such as target contour intensity.Thus,visual perception quality related to natural scene statistical(NSS)features of fog image and the target detection accuracy related target category semantic(TCS)features are significantly different with ground truth,Traditional image restoration methods can build the defogging mapping to improve image contrast based on the conventional scattering model.But,it is challenged to remove the severe scattering of image features.Deep learning based image enhancement methods have better scattering image removal results close to the distribution of training data.It is a challenged issue of insufficient generalization ability like dense artifacts for ground truth foggy images derived of complex degradation the degradation in synthetic foggy images excluded.Current methods have focused on semisupervision technique based generalization ability improvement but the large domain distance constrains between real and synthetic foggy images existing.To optimize the image features,current deep learning based methods are challenged to achieve the niches between visual quality and machine perception quality via image classification or target detection.To interpret pros and cons of prior-based and deep leaning based methods,a semi-supervision prior hyrid network for feature enhancement is illustrated to demonstrate the feature enhancement for detection and object analysis.MethodOur

关 键 词：图像去雾 特征增强 先验混合网络 无监督学习 图像域转换 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]