Record number :
1695080
Title of article :
Multi-spectral and multi-perspective video arrays for driver body tracking and activity analysis
Author/Authors :
Cheng، نويسنده , , Shinko Y. and Park، نويسنده , , Sangho and Trivedi، نويسنده , , Mohan M.، نويسنده ,
Issue Information :
روزنامه با شماره پیاپی سال 2007
Pages :
13
From page :
245
To page :
257
Abstract :
This paper presents a novel approach to recognizing driver activities using a multi-perspective (i.e., four camera views) multi-modal (i.e., thermal infrared and color) video-based system for robust and real-time tracking of important body parts. The multi-perspective characteristics of the system provides redundant trajectories of the body parts, while the multi-modal characteristics of the system provides robustness and reliability of feature detection and tracking. The combination of a deterministic activity grammar (called ‘operation-triplet’) and a Hidden Markov model-based classifier provides semantic-level analysis of human activity. The application context for this research is that of intelligent vehicles and driver assistance systems. Experimental results in real-world street driving demonstrate effectiveness of the proposed system.
Keywords :
Long-wavelength infrared , Tracking , Human–computer interaction , Template-based classification , Integration of multiple-cues , gesture recognition
Journal title :
Computer Vision and Image Understanding
Journal title :
Computer Vision and Image Understanding
Serial Year :
2007
Link To Document :
بازگشت