视频的异常检测——从功能重建到未来预测

Shenzhen Research Institute of Big Data

深圳市大数据研究院

▶ Topic:Anomaly detection in videos: from feature reconstruction to future prediction

▶ Time:2:30 - 3:30pm, July 11th

▶Venue:Room 207, Cheng Dao Building

▶ Speaker:Shenghua Gao

ShanghaiTech University

Abstract

讲座摘要

Anomaly detection in videos is a challenging problem in computer vision because only normal events are available in the training set. Most previous works handle the problem within a sparse representation framework: a dictionary is learnt to minimize the reconstruction error for normal events and abnormal events would lead to a large reconstruction error. However such sparse representation is computationally expensive in the testing phase. Inspired the optimization of sparse representation, we propose to build a special type of deep neural network, which is a counterpart of sparse coding. Then we simplify the network which not only improves the speed but also accuracy. Further, it is worth noting that anomaly detection refers to the identification of events that do not conform to expected behavior, so we propose to solve anomaly detection within the future video frame prediction framework. By simultaneously enforcing the spatial and temporal consistency of videos frames of normal videos, we can predict high-quality video frames for normal videos. Extensive experiments validate the effectiveness of such video frame prediction framework over feature reconstruction framework for anomaly detection.

Biography

主讲人简介

Shenghua Gao is an assistant professor in ShanghaiTech University, China. He received the B.E. degree from the University of Science and Technology of China in 2008, and received the Ph.D. degree from the Nanyang Technological University in 2012. From Jun 2012 to Aug 2014, he worked as a research scientist in UIUC Advanced Digital Sciences Center, Singapore. From Jan 2015 to June 2015, he visited UC Berkeley as a visiting professor. His research interests include computer vision and machine learning. He has published about 50 papers on image and video understanding in many top-tier international conferences and journals, including TPAMI, IJCV, TIP, TNNLS, CVPR, and ICCV, etc.

Shenzhen Research Institute of Big Data

深圳市大数据研究院

▶简介：

深圳市大数据研究院是在深圳市委、市政府的支持下于２０１６年3月组建，依托罗智泉教授领衔的大数据信息处理及应用孔雀团队和国家超级计算深圳中心。研究院以建立国际一流、具有自主知识产权、核心技术优势突出的“大数据处理分析研发基地”为目标，最大限度发挥国家超级计算深圳中心在大数据产业研发中的核心平台作用，充分利用中国香港中文大学（深圳）孔雀团队的科研力量，为打造集大数据分析处理技术创新研究、技术服务及交流、核心技术研究、人才引进与培养的综合性创新型研究机构，成为世界一流的大数据研发和公共服务平台，在智慧医疗、智能通信、智慧交通、城市管理等方面为深圳、全省乃至国家的科学研究、产业发展、政府决策、公共服务做贡献。

▶地址:中国广东省深圳市龙岗区龙翔大道2001号道远楼225室

▶电话：(86)755-84273615

▶邮箱：contact@sribd.cn