Forensic CG Video Generation with Augmented Reality Technology

This paper presents a technology for supporting in-house forensic CG video generation by police and prosecution. For confidentiality, it is usually not allowed to generate criminal CG video through subcontracting, whereas existing CG modeling and video editing systems are too complicated to use for police or prosecution. The proposed technique solves this problem with Augmented Reality (AR) technology. We propose to deploy multiple cameras and AR markers on criminal site. While a user of the police or the prosecution plays a role of the criminal wearing a video see-through head mount display, video is automatically generated. CG objects, such as the virtual victim, are displayed on the head mount display and rendered in the video. Our main contributions in this research are concurrent displaying of first-person and third-person views for visualizing spatial relationship between the user and its surroundings, and complementary use of marker information from multiple cameras for solving the occlusion problem inherently caused by operating at the actual criminal site.