Journal article
Cognitive Computation, vol. 17, 2025 Dec, p. 168
APA
Click to copy
Yedjour, H., Haddag, A., & Yedjour, D. (2025). A Correlation-Based Spiking Neural Network for Motion Boundary Detection and Segmentation in Dynamic Visual Sequences. Cognitive Computation, 17, 168. https://doi.org/10.1007/s12559-025-10527-w
Chicago/Turabian
Click to copy
Yedjour, Hayat, Abdelkader Haddag, and Dounia Yedjour. βA Correlation-Based Spiking Neural Network for Motion Boundary Detection and Segmentation in Dynamic Visual Sequences.β Cognitive Computation 17 (December 2025): 168.
MLA
Click to copy
Yedjour, Hayat, et al. βA Correlation-Based Spiking Neural Network for Motion Boundary Detection and Segmentation in Dynamic Visual Sequences.β Cognitive Computation, vol. 17, Dec. 2025, p. 168, doi:10.1007/s12559-025-10527-w.
BibTeX Click to copy
@article{yedjour2025a,
title = {A Correlation-Based Spiking Neural Network for Motion Boundary Detection and Segmentation in Dynamic Visual Sequences},
year = {2025},
month = dec,
journal = {Cognitive Computation},
pages = {168},
volume = {17},
doi = {10.1007/s12559-025-10527-w},
author = {Yedjour, Hayat and Haddag, Abdelkader and Yedjour, Dounia},
month_numeric = {12}
}
Abstract: Visual motion processing is a fundamental function of the visual system, extensively studied across species. Despite advances in understanding neural mechanisms, motion perception remains incompletely understood. Guided by a correlation-based paradigm, we propose a bio-inspired feedforward network of spiking neurons. This network employs the Hodgkin-Huxley model and spatiotemporal receptive field correlations, mimicking the direction-selective responses observed in the visual cortex. The network generates a motion map that delineates the boundaries of moving objects based on neuron firing rates. We evaluate the performance of our network across diverse video sequences from established datasets, confirming the modelβs capability for accurate moving boundary detection. Comparative evaluations against state-of-the-art spiking neural networks underscore its superior performance, notably achieving 89% accuracy on the CDnet-2014 dataset. Furthermore, we apply our model to motion segmentation, achieving state-of-the-art results on four benchmark datasets: Davis-16 (83.83%), Davis-2017 (86.1%), YouTube-VOS-18 (87.4%), and SegTrackv2 (83.30%). These results confirm the modelβs robust capability to distinguish foreground objects from the background.
Keywords: Visual motion processing, Bio-inspired model, Spatiotemporal correlation, Direction selectivity, Boundary detection
Corresponding author: Hayat Yedjour (*)