Accuracy vs. Efficiency Trade-offs in Optical Flow Algorithms

There have been two thrusts in the development of optical flow algorithms. One has emphasized higher accuracy; the other faster implementation. These two thrusts, however, have been independently pursued, without addressing the accuracy vs. efficiency trade-offs. Although the accuracy-efficiency characteristic is algorithm dependent, an understanding of a general pattern is crucial in evaluating an algorithm as far as real world tasks are concerned, which often pose various performance requirements. This paper addresses many implementation issues that have often been neglected in previous research, including subsampling, temporal filtering of the output stream, algorithms' flexibility and robustness, etc. Their impacts on accuracy and/or efficiency are emphasized. We present a critical survey of different approaches toward the goal of higher performance and present experimental studies on accuracy vs. efficiency trade-offs. The goal of this paper is to bridge the gap between the accuracy and the efficiency-oriented approaches.

[1]  William G. Rippey,et al.  An Integrated Vision Touch-Probe System for Dimensional Inspection Tasks , 1995 .

[2]  Brian G. Schunck,et al.  Image Flow Segmentation and Estimation by Constraint Line Clustering , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Yasushi Yagi,et al.  Real-time omnidirectional image sensor (COPIS) for vision-guided navigation , 1994, IEEE Trans. Robotics Autom..

[4]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[5]  H. K. Nishihara.  Real-time stereo- and motion-based figure ground discrimination and tracking using LOG sign correlation , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[6]  Rama Chellappa,et al.  A generalized motion model for estimating optical flow using 3-D Hermite polynomials , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[7]  Ta Camus,et al.  Calculating Time-to-Contact Using Real-Time Quantized Optical Flow , 1995 .

[8]  Hans-Hellmut Nagel,et al.  Displacement vectors derived from second-order intensity variations in image sequences , 1983, Comput. Vis. Graph. Image Process..

[9]  Peter K. Allen,et al.  Automated tracking and grasping of a moving object with a robotic hand-eye system , 1993, IEEE Trans. Robotics Autom..

[10]  Christof Koch,et al.  Multiplication-based analog motion detection chip , 1991, Defense, Security, and Sensing.

[11]  Tsai Hong Hong,et al.  Three-dimensional reconstruction from optical flow using temporal integration , 1991, Other Conferences.

[12]  Alberto Del Bimbo,et al.  A Robust Algorithm for Optical Flow Estimation , 1995, Comput. Vis. Image Underst..

[13]  T. Poggio,et al.  A parallel algorithm for real-time computation of optical flow , 1989, Nature.

[14]  Rama Chellappa,et al.  A reliable optical flow algorithm using 3-D hermite polynomials , 1993 .

[15]  Ta Camus,et al.  Real-time quantized optical flow , 1995, Proceedings of Conference on Computer Architectures for Machine Perception.

[16]  T. Delbruck.  Silicon retina with correlation-based, velocity-tuned pixels , 1993 .

[17]  Derek Abbott,et al.  An analog implementation of early visual processing in insects , 1993, 1993 International Symposium on VLSI Technology, Systems, and Applications Proceedings of Technical Papers.

[18]  Martin Herman,et al.  Real-time obstacle avoidance using central flow divergence and peripheral flow , 2017, Proceedings of IEEE International Conference on Computer Vision.

[19]  P. Weiss,et al.  Real time implementation of subpixel motion estimation for broadcast applications , 1990 .

[20]  Gin-Shu Young.  SAFE NAVIGATION AND ACTIVE VISION FOR AUTONOMOUS VEHICLES A PURPOSIVE AND DIRECT SOLUTION , 1993 .

[21]  Ramin Zabih,et al.  An Algorithm for Real-Time Tracking of Non-Rigid Objects , 1991, AAAI.

[22]  Rama Chellappa,et al.  Motion-model-based boundary extraction , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[23]  F. Jutand,et al.  A versatile and powerful chip for real-time motion estimation , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[24]  Rama Chellappa,et al.  VLSI neuroprocessors for video motion detection , 1993, IEEE Trans. Neural Networks.

[25]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[26]  Carlo S. Regazzoni,et al.  Real-time approach to 3-D object tracking in complex scenes , 1994 .

[27]  Masayuki Inaba,et al.  Robot vision system with a correlation chip for real-time tracking, optical flow and depth map generation , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[28]  J. Kittler,et al.  Robust motion analysis , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[30]  Tsai Hong Hong,et al.  Real-time Obstacle Avoidance Using Central Flow Divergence and Peripheral Flow | NIST , 1995 .

[31]  Hans-Hellmut Nagel,et al.  Estimation of Optical Flow Based on Higher-Order Spatiotemporal Derivatives in Interlaced and Non-Interlaced Image Sequences , 1995, Artif. Intell..

[32]  Donald J. Patterson,et al.  Computer organization and design: the hardware-software interface (appendix a , 1993 .

[33]  Ze-Nian Li,et al.  Real-time motion stereo , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Hongche Liu.  A general motion model and spatio-temporal filters for 3-D motion interpretations , 1995 .

[35]  J. Van der Spiegel,et al.  Real-time 2D analog motion detector VLSI circuit , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[36]  Nicola Ancona,et al.  Optical flow from 1-D correlation: Application to a simple time-to-crash detector , 1993, 1993 (4th) International Conference on Computer Vision.

[37]  Carver A. Mead,et al.  An Integrated Analog Optical Motion Sensor , 1986 .