数据分析技术实验室系列学术报告---Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior

报告人：张敬 杭州电子科技大学

报告时间：12月11日13:00-14:00

报告地点：数学与统计学院一楼报告厅

主办单位：数学与统计学院

欢迎光临！

报告摘要：In this talk, we first present a novel haze removal method for nighttime image using the proposed maximum reflectance prior. Then, we show its influence on image semantic segmentation task. Finally, we discuss relations between low-level image processing and high-level image classification/understanding tasks. Specifically, we address a haze removal problem from a single nighttime image, even in the presence of varicolored and non-uniform illumination. The core idea lies in a novel maximum reflectance prior. We first introduce the night time hazy imaging model, which includes a local ambient illumination item in both direct attenuation term and scattering term. Then, we propose a simple but effective image prior, maximum reflectance prior, to estimate the varying ambient illumination. The maximum reflectance prior is based on a key observation: for most daytime haze-free image patches, each color channel has very high intensity at some pixels. For the nighttime haze image, the local maximum intensities at each color channel are mainly contributed by the ambient illumination. Therefore, we can directly estimate the ambient illumination and transmission map, and consequently restore a high quality haze-free image. Experimental results on various nighttime hazy images demonstrate the effectiveness of the proposed approach. In particular, our approach has the advantage of computational efficiency, which is 10-100 times faster than state-of-the-art methods.

报告人简介

张敬：2010年毕业于河南大学理科实验班数学专业，获数学与应用数学学士学位，2015年毕业于中国科学技术大学自动化系，获控制科学与工程博士学位。毕业后先后就职于中兴通讯上海研发中心、科大讯飞人工智能研究院研究员，担任“蓝剑计划”算法工程师、深度学习研究员（智能驾驶研究方向技术负责人）。主要从事计算机视觉与模式识别等方向的研究，在移动端图像复原和增强、道路场景图像识别和理解等方面有丰富的实践。在IEEE TCSVT、CVPR等国际著名期刊和会议上发表论文16余篇，曾带领团队在KITTI、Cityscapes等道路场景图像语义分割任务上取得国际第一名，参与两项国家基金重点项目、两项国家基金面上项目。