2nd Workshop on Deepview: Global Multi-Target Visual Surveillance Based on Real-Time Large-Scale Analysis

Abstract

In recent years, there has been great progress in demand for visual surveillance systems and intelligent cities capable of providing accurate traffic measurements and essential information for user-friendly monitoring and real-world applications. It is a very practical and essential system that is based on large-scale camera network systems consisting of object detection, tracking, re-identification, and human behavior analysis. However, in many emerging applications, there are still main challenges due to the real-world scenes taken by large-scale cameras, such as illumination changes, dynamic backgrounds, poor data quality, and the lack of high-quality models. In order to tackle key challenges, researchers and engineers strive for developing robust algorithms that can be applied to large-scale surveillance systems. Based on our fundamental knowledge, we want to further upgrade our knowledge of the topic through cooperation with various researchers. In this workshop, we seek original contributions reporting the most recent progress on different computer vision methodologies for surveillance analysis of large-scale visual content and its wide applications that will help make smart systems.