Latency-Based Motion Detection in Spiking Neural Networks

Authors: Mohammad Saleh Vahdatpour, Yanqing Zhang

Abstract:

Understanding the neural mechanisms underlying motion detection in the human visual system has long been a fascinating challenge in neuroscience and artificial intelligence. This paper presents a spiking neural network model inspired by the processing of motion information in the primate visual system, particularly focusing on the Middle Temporal (MT) area. In our study, we propose a multi-layer spiking neural network model to perform motion detection tasks, leveraging the idea that synaptic delays in neuronal communication are pivotal in motion perception. Synaptic delay, determined by factors like axon length and myelin insulation, affects the temporal order of input spikes, thereby encoding motion direction and speed. Overall, our spiking neural network model demonstrates the feasibility of capturing motion detection principles observed in the primate visual system. The combination of synaptic delays, learning mechanisms, and shared weights and delays in SMD provides a promising framework for motion perception in artificial systems, with potential applications in computer vision and robotics.

Keywords: Neural networks, motion detection, signature detection, convolutional neural network.

References:

[1] Frisby, John P., and James V. Stone. “Seeing: The computational approach to biological vision.” The MIT Press, 2010.
[2] Borst, Alexander, and Martin Egelhaaf. “Principles of visual motion detection.” Trends in neurosciences 12.8 (1989): 297-306.
[3] Beauchemin, Steven S., and John L. Barron. “The computation of optical flow.” ACM computing surveys (CSUR) 27.3 (1995): 433-466.
[4] Singla, Nishu. “Motion detection based on frame difference method.” International Journal of Information & Computation Technology 4.15 (2014): 1559-1565.
[5] Shon, Aaron P., Rajesh PN Rao, and Terrence J. Sejnowski. “Motion detection and prediction through spike-timing dependent plasticity.” Network: Computation in Neural Systems 15.3 (2004): 179-198.
[6] Gu, Pengjie, et al. “STCA: Spatio-temporal credit assignment with delayed feedback in deep spiking neural networks.” IJCAI. Vol. 15. 2019.
[7] Orchard, Garrick, et al. “A spiking neural network architecture for visual motion estimation.” Biomedical Circuits and Systems Conference (BioCAS), 2013 IEEE. IEEE, 2013.
[8] Izhikevich, Eugene M. “Solving the distal reward problem through linkage of STDP and dopamine signaling.” Cerebral cortex 17.10 (2007): 2443-2452.
[9] Fang, Wei, et al. “Deep residual learning in spiking neural networks.” Advances in Neural Information Processing Systems 34 (2021): 21056-21069.
[10] Masquelier, Timothée, and Simon J. Thorpe. “Unsupervised learning of visual features through spike timing dependent plasticity.” PLoS computational biology 3, no. 2 (2007): e31
[11] Angelova, Anelia, Alex Krizhevsky, Vincent Vanhoucke, Abhijit S. Ogale, and Dave Ferguson. “Real-Time Pedestrian Detection with Deep Network Cascades.” In BMVC, vol. 2, p. 4. 2015.
[12] Pylvänäinen, Timo. “Accelerometer based gesture recognition using continuous HMMs.” Pattern Recognition and Image Analysis (2005): 413-430.
[13] Liu, Jiayang, Lin Zhong, Jehan Wickramasuriya, and Venu Vasudevan. “uWave: Accelerometer-based personalized gesture recognition and its applications. ” Pervasive and Mobile Computing 5, no. 6 (2009): 657-675.
[14] Wu, Jiahui, Gang Pan, Daqing Zhang, Guande Qi, and Shijian Li. “Gesture recognition with a 3-d accelerometer.” In International Conference on Ubiquitous Intelligence and Computing, pp. 25-38. Springer Berlin Heidelberg, 2009.
[15] Kholmatov, Alisher and Yanıkoglu, Berrin (2009) “SUSIG: an on-line signature database, associated protocols and benchmark results.” Pattern Analysis & Applications, 12 (3). pp. 227-236. ISSN 1433-7541.
[16] Vass, Lindsay K., and Russell A. Epstein. “Abstract representations of location and facing direction in the human brain.” Journal of Neuroscience 33, no. 14 (2013): 6133-6142.
[17] Vahdatpour, Mohammad Saleh. "Addressing the Knapsack Challenge through Cultural Algorithm Optimization." CS & IT Conference Proceedings. Vol. 13. No. 19. CS & IT Conference Proceedings, 2023.