On benchmarking optical flow

Computer Vision and Image Understanding

Volumn 84, Issue 1, 2001, Pages 126-143

  McCane, B ^a   Novins, K ^b   Crannitch, D ^a   Galvin, B ^a  

^a UNIVERSITY OF OTAGO   (New Zealand)

^b UNIVERSITY OF AUCKLAND   (New Zealand)

Author keywords

Optical flow; Quantitative evaluation

Indexed keywords

ALGORITHMS; IMAGE ANALYSIS; IMAGE UNDERSTANDING; MATRIX ALGEBRA;

COMPLEX SCENES;

COMPUTER VISION;

EID: 0035481131     PISSN: 10773142     EISSN: None     Source Type: Journal    
DOI: 10.1006/cviu.2001.0930     Document Type: Article

References (21)

1. Spatiotemporal energy models for the perception of motion
2. A computational framework and an algorithm for the measurement of visual motion
3. Performance of optical flow techniques
4. Real-time quantized optical flow
5. Determining optical flow: A retrospective
6. Optical flow estimation: An error analysis of gradient based methods with local optimization
7. An iterative image registration technique with an application to stereo vision
8. Generating motion fields for the evaluation of optical flow algorithms on complex scenes
9. Displacement vectors derived from second-order intensity variations in image sequences
10. On the estimation of optical flow: Relations between different approaches and some new results
11. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences
12. Estimation of optical flow based on higher-order spatiotemporal derivatives in interlaced and non-interlaced image sequences
13. Determination of optical flow and its discontinuities using non-linear diffusion
14. A versatile camera calibration technique for high-accuracy 3d machine vision metrology using off-the-shelf tv cameras and lenses
15. A computational approach to motion perception