A New Multi-Camera Dataset with Surveillance, Mobile and Stereo Cameras for Tracking, Situation Analysis and Crime Scene Investigation Applications
Proceedings of the 2018 the 2nd International Conference on Video and Image Processing(2018)
Abstract
Nowadays, cameras are ubiquitous. In the event of a crime or terrorist attack, plenty of video data can be collected from surveillance cameras or mobile phone cameras from witnesses. This paper presents a new dataset, "IOSB-4D," which includes data from multiple static and mobile cameras (from potential witnesses) that record a site. We provide several scenarios involving 10 actors that contain scenes of kidnapping, attack of a person by a group, loading a briefcase into a trunk, and more. In total, there are recordings from three perspectives from stereo cameras as well as two static surveillance cameras and up to six mobile cameras. For all cameras, we provide intrinsic parameters, and for the static cameras, we provide 6DOF pose parameters. Furthermore, high resolution images of all actors are available. This new dataset is valuable for object tracking and situation analysis, or research on innovative visualizations of combined camera and video footage, for example, to create a visualization in 3D/4D for a post analytic crime scene investigation.
MoreTranslated text
Key words
Crime Scene Investigation, Dataset, Mobile Camera, Multi-Camera Calibration, Stereo, Surveillance Camera
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined