Action Recognition Using a Bio-Inspired Feedforward Spiking Network

• Published in: International journal of computer vision Vol. 82; no. 3; pp. 284 - 301
• Main Authors: Escobar, Maria-Jose, Masson, Guillaume S., Vieville, Thierry, Kornprobst, Pierre
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.05.2009; Springer; Springer Nature B.V; Springer Verlag
• Subjects: Applied sciences; Artificial Intelligence; Brain; Cognitive Sciences; Computer Imaging; Computer Science; Computer science; control theory; systems; Exact sciences and technology; Image Processing and Computer Vision; Life Sciences; Neurons and Cognition; Pattern Recognition; Pattern Recognition and Graphics; Pattern recognition. Digital image processing. Computational geometry; Vision; Action recognition; Spiking networks; V1; Motion analysis; Bio-inspired model; MT; Human; Brain; Computer vision; Motion estimation; Image processing; Central nervous system; Neural network; Modeling; Encephalon; Motion analysis . V1; Biomimetics; Behavioral analysis; Database
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-008-0201-1

We propose a bio-inspired feedforward spiking network modeling two brain areas dedicated to motion (V1 and MT), and we show how the spiking output can be exploited in a computer vision application: action recognition. In order to analyze spike trains, we consider two characteristics of the neural code: mean firing rate of each neuron and synchrony between neurons. Interestingly, we show that they carry some relevant information for the action recognition application. We compare our results to Jhuang et al. (Proceedings of the 11th international conference on computer vision, pp. 1–8, 2007 ) on the Weizmann database. As a conclusion, we are convinced that spiking networks represent a powerful alternative framework for real vision applications that will benefit from recent advances in computational neuroscience.