Multi-modal big-data management for film production

Abstract

Modern digital film production uses large quantities of data from videos, digital photographs, LIDAR scans, spherical photography and many other sources to create the final film frames. The processing and management of this massive amount of heterogeneous data consumes enormous resources. We propose an integrated pipeline for 2D/3D data registration for film production. We present the prototype application Jigsaw, which allows users to efficiently manage and process various data from digital photographs to 3D point clouds. A key requirement in the use of multi-modal 2D/3D data for content production is the registration into a common coordinate frame. 3D geometric information is reconstructed from 2D data and registered to the reference 3D models using 3D feature matching. We provide a public multi-modal database captured with a wide variety of devices in different environments to assist further research. An order of magnitude gain in efficiency is achieved with the proposed approach.

A review on applications of activity recognition systems with regard to performance and evaluation

“…This system showed a reliable average recognition rate of 89.99% as their final result. An intelligent monitoring system proposed by Chen et al 88 monitors the ''elopement'' events of dementia 73 Teleconferencing, 3D video processing, 3D video rendering, 3D audio processing Three infrared (IR) cameras, three color XGA cameras, and one Kinect B Petit et al 74 Multi-camera, real time, 3D modeling, telepresence Eight 1-megapixel cameras Z Huang et al 75 3D tele-immersion, synchronization 3D video camera Kurillo et al 77 Tele-immersion, rehabilitation, tele-rehabilitation, lower extremities 3D video stream Chun-Han Lin et al 78 Virtual collaboration, motion-sensing techniques, gesturecollaborative games 3D motion sensor data Yunpeng Liu et al 79 Depth map, compression, 3D tele-immersion Depth image streams H Kim et al 80 Big data management, multimodal data registration, film production 2D/3D video data 2D: two-dimensional; 3D: three-dimensional.…”

Down-Sampling of Large LiDAR Dataset in the Context of Off-Road Objects Extraction

“…Given the possibility of using LiDAR sensors in both terrestrial and aerial surveys (Terrestrial Laser Scanning (TLS), Mobile Laser Scanning (MLS), Airborne Laser Scanning (ALS)), the number of applications exploiting such kind of technology is continuously increasing, including nowadays several fields such as civil and structural engineering [1], forestry and environmental protection [2], road engineering [3], and assisted/autonomous driving. Many possible applications include, for instance, infrastructure documentation, construction of roads and highways [4], production of digital terrain models [5], inventory mapping [6], design of streetscape [7], extraction of traffic signs and buildings [8], safety improvements [9], and more recently, even the creation of three-dimensional (3D) models to support visual effects in the film industry [10].…”