题目：People Search in A Smart City
主讲人：Prof.Shaogang Gong ,Queen Mary University of London
日期： 2018年10月12日 星期五
The amount of video data from urban environments is growing exponentially from 24/7 operating infrastructure cameras, online social media sources, self-driving cars, and smart city intelligent transportation systems, with 1.4 trillion hours CCTV video in 2017 and growing to 3.3 trillion hours by 2020. The scale and diversity of these videos make it very difficult to filter and extract useful information in a timely manner. Finding people and searching for the same individuals against a large population of unknowns in urban spaces of a smart city pose a significant challenge to computer vision and machine learning. Established techniques such as face recognition, although successful for document verification in controlled environments and on smart phones, are poor for people search in unstructured videos of wide-field views due to low-resolution, motion blur, and a lack of detectable facial imagery in unconstrained scenes. In contrast to face recognition, person re-identification considers pedestrian whole-body appearance matching by exploring clothing characteristics and body-part attributes from arbitrary views. In the past decade, significant progresses have been made on person re-identification for matching people in increasingly larger scale benchmarks. However, such progresses rely heavily on supervised learning with strong assumptions on both model training and testing data being sampled from the same domain, and the availability of pair-wise labelled training data exhaustively sampled for every camera pair in each domain. Such assumptions render most existing techniques unscalable to large scale videos from unknown number of unknown sources. In this talk, I will give an overview of recent progress and present current research on people search in big video data by deep learning for visual attention selection, unsupervised multi-camera multi-object tracking association, and attribute-based domain adaptation.
Prof Sean Gong is a pioneer of computer vision research for visual surveillance. He is a world authority on Person Re-Identification and its applications to law enforcement video forensics and analysis. Prof Gong has served on the Steering Panel of the UK Government Chief Scientific Adviser's Science Review, and is a Turing Fellow of the Alan Turing Institute, the UK's national institute for data science and artificial intelligence. Prof Gong has published over 400 academic papers in computer vision and machine learning (Google Scholar Citations 20,240; H-index 74), and is the principal author of 2 research monographs on Video Behaviour Recognition (2011) and Face Recognition (2000), and 5 edited books on Person Re-Identification (2014), Video Analysis for Business Intelligence (2012), and Face & Gesture Analysis (2007, 2005, 2003). Prof Gong received his D.Phil. in Computer Vision from the Oxford University in 1989 and founded the Queen Mary Computer Vision Laboratory in 1993. He is the Director of the Queen Mary Computer Vision Group (currently 4 professors, 3 associate professors, 35 PhDs and postdocs). Prof Gong is the Chief Scientist of three start-ups and won the 2017 Queen Mary Academic Commercial Enterprise Award.