We describe an integrated vision system which reliably detects persons in static color natural scenes, or other targets among distracting objects. The system is built upon the biologically-inspired synergy between two processing stages: A fast trainable visual attention front-end (where), which rapidly selects a restricted number of conspicuous image locations, and a computationally expensive object recognition back-end (what), which determines whether the selected locations are targets of interest. We experiment with two recognition back-ends: One uses a support vector machine algorithm and achieves highly reliable recognition of pedestrians in natural scenes, but is not particularly biologically plausible, while the other is directly inspired from the neurobiology of inferotemporal cortex, but is not yet as robust with natural images. Integrating the attention and recognition algorithms yields substantial speedup over exhaustive search, while preserving detection rate. The success of this approach demonstrates that using a biological attention-based strategy to guide an object recognition system may represent an efficient strategy for rapid scene analysis.
Neuromorphic algorithms for computer vision and attention
Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation IV ; 2001 ; San Diego,CA,United States
Proc. SPIE ; 4479
2001-11-14
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Neuromorphic vision processing system
IET Digital Library Archive | 1997
|Feedback control of dynamical systems using neuromorphic vision sensors
DSpace@MIT | 2016
|Analysing Driver's Attention Level using Computer Vision
IEEE | 2008
|Finding the gap: neuromorphic motion-vision in dense environments
DataCite | 2024
|Performance of Computer Vision Algorithms
British Library Online Contents | 1994
|