Challenge I: Challenge on Advanced Traffic Monitoring
The increasing progress of transportation systems has caused a tremendous increase in demand for smart systems capable of monitoring traffic states and street safety. Fundamental to these applications are algorithms for multi-object detection and multi-object tracking. It is thus important for practitioners to know the pros and cons of different works in these categories. It is goal of this Challenge to provide a comprehensive performance evaluation of state-of-the-art detection and tracking algorithms.
The challenge is based on UA-DETRAC, a real-world multi-object detection and multi-object tracking benchmark. The dataset is based on a huge set of traffic video sequences opportunely annotated with bounding boxes, tracking paths, and difficult/environment difficulty levels. We divided the challenge in two different task (detection and tracking), and two different degrees of difficulty.
The challenge has been organized in conjunction with the International Workshop on Traffic and Street Surveillance for Safety and Security (IWT4S), currently proposed in AVSS 2018, in order to guarantee the publication of papers associated with the solutions proposed for the challenge.
Further Details: PDF
- Marco Del Coco (Institute of Applied Sciences and Intelligent Systems, CNR, Italy)
- Siwei Lyu (University at Albany, USA)
- Pierluigi Calcagni (Institute of Applied Sciences and Intelligent Systems, CNR, Italy)
- Ming-Ching Chang (University at Albany, USA)
In surveillance and security today it is a common goal to locate a subject of interest purely from a semantic description; think an offender description form handed into a law enforcement agency. To date, these tasks are primarily undertaken by operators on the ground either by manually searching a premises or by combing through hours of video footage. As such, the Australian Federal Police identified this area as a significant problem within law enforcement. To date, researchers have focused on person re-identification methodologies to solve this complex problem, however, in circumstances where pre-search subject enrollment images are not available, these techniques fail.
Semantic search is of primary interest as it does not require pre-search subject enrollment and instead searches video footage based on a textually supplied target query. The aim of this challenge is to attempt to solve this problem through two tasks, each of these tasks aims to locate a subject of interest based on a soft biometric signature.
- Michael Halstead (Queensland University of Technology, Australia)
- Simon Denman (Queensland University of Technology, Australia)
- Clinton Fookes (Queensland University of Technology, Australia)
- YingLi Tian (The City University of New York, USA)
- Mark S. NIxon (University of Southampton, UK)