Two-Frame Stereo Matching Algorithms—A Review

Abstract

Stereo matching is an important and difficult step in the stereovision paradigm, a passive range sensing technique for depth perception. Algorithms available in the current literature are categorized into area-based, feature-based and pixel-based techniques. In this paper, the merits and demerits of each of these techniques are presented. In addition, some of the algorithms are reviewed.

Indexing terms:

• Stereovision
• Stereo matching
• Stereo correspondence

Additional information

Notes on contributors

S Srinivas Kumar

S Srinivas Kumar is currently a Professor of ECE, JNTU College of I Engineering, Kakinada, Andhra Pradesh. He received his M Tech degree from Jawaharlal Nehru Technological University, Hyderabad and PhD degree from Indian Institute of Technology, Kharagpur. He has sixteen years experience of teaching under-graduate and post-graduate students and guided number of post-graduate theses. His research interests are in the areas of Digital Image Processing, Computer vision, and applications of Artificial Neural Network and Fuzzy logic to engineering problems.

B N Chatterji

B N Chatterji, FIETE & FIE, is currently Professor in E&ECE Department, IIT, Kharagpur. He received PhD & BTech (Hons) from E&ECE Department, IIT, Kharagpur in 1970 and 1965 respectively. He has been a teaching faculty in the Department since 1967. He has served the Institute under various administrative capacities as Head of Department, Dean (Academic) etc. He has chaired a couple of International & National Symposia and Conferences organized at Kharagpur apart from organizing 15 short-term courses for Industries and Engineering college teachers. He has guided more than 25 PhD scholars. He has published more than 150 papers in reputed International and National journals apart from authoring three Scientific Books. His research interests are Low-level Vision, Image Analysis, Pattern Recognition and Motion Analysis.