An event-based implementation of saliency-based visual attention for rapid scene analysis

• Published in: IEEE transactions on cognitive and developmental systems pp. 1 - 13
• Main Authors: Chane, Camille Simon, Niebur, Ernst, Benosman, Ryad, Ieng, Sio-Hoi
• Format: Journal Article
• Language: English
• Published: IEEE 24-10-2024; Institute of Electrical and Electronics Engineers, Inc
• Subjects: Cameras; Cognitive science; Computational modeling; Engineering Sciences; Event detection; Neuroscience; Observers; Retina; Robot sensing systems; Signal and Image processing; Spatiotemporal phenomena; Vision sensors; Visual systems; Visualization; Visualization; Event detection; Computational modeling; Vision sensors; Visual systems; Observers; Robot sensing systems; Cameras; Retina; Spatiotemporal phenomena
• ISSN: 2379-8920; 2379-8939
• DOI: 10.1109/TCDS.2024.3480153

Selective attention is an essential mechanism to filter sensory input and to select only its most important components, allowing the capacity-limited cognitive structures of the brain to process them in detail. The saliency map model, originally developed to understand the process of selective attention in the primate visual system, has also been extensively used in computer vision. Due to the wide-spread use of frame-based video, this is how dynamic input from non-stationary scenes is commonly implemented in saliency maps. However, the temporal structure of this input modality is very different from that of the primate visual system. Retinal input to the brain is massively parallel, local rather than frame-based, asynchronous rather than synchronous, and transmitted in the form of discrete events, neuronal action potentials (spikes). These features are captured by event-based cameras. We show that a computational saliency model can be obtained organically from such vision sensors, at minimal computational cost. We assess the performance of the model by comparing its predictions with the distribution of overt attention (fixations) of human observers, and we make available an event-based dataset that can be used as ground truth for future studies.