Title :
Fast obstacle detection using targeted optical flow
Author :
Boroujeni, N.S. ; Etemad, S. Ali ; Whitehead, A.
Author_Institution :
Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, ON, Canada
fDate :
Sept. 30 2012-Oct. 3 2012
Abstract :
This paper presents a new method for obstacle detection using optical flow. The method employs a highly efficient and accurate adaptive motion detection algorithm for determining the regions in the image which are more likely to contain obstacles. These regions then have optical flow performed on them. We call this method targeted optical flow. Targeted optical flow performs significantly faster compared to regular optical flow. We employ two types of optical flow to demonstrate the performance and speed increase of the proposed system. Finally, k-means clustering is employed for obstacle reconstruction. The system is designed for color videos for better performance. Several benchmark and recorded sequences have been used for testing the system.
Keywords :
collision avoidance; control engineering computing; image colour analysis; image motion analysis; image reconstruction; image sequences; learning (artificial intelligence); pattern clustering; color video; image region determination; k-means clustering; motion detection algorithm; obstacle detection; obstacle reconstruction; targeted optical flow method; Computer vision; Image color analysis; Image motion analysis; Optical imaging; Optical sensors; Optical signal processing; Vectors; Obstacle detection; clustering; motion estimation; optical flow;
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2012.6466796