Efficient Feedforward Categorization of Objects and Human Postures with Address-Event Image Sensors

Citations Over TimeTop 10% of 2011 papers

Abstract

This paper proposes an algorithm for feedforward categorization of objects and, in particular, human postures in real-time video sequences from address-event temporal-difference image sensors. The system employs an innovative combination of event based hardware and bio-inspired software architecture. An event-based temporal difference image sensor is used to provide input video sequences, while a software module extracts size and position invariant line features inspired by models of the primate visual cortex. The detected line features are organized into vectorial segments. After feature extraction, a modified line segment Hausdorff distance classifier combined with on-the-fly cluster-based size and position invariant categorization. The system can achieve about 90 percent average success rate in the categorization of human postures, while using only a small number of training samples. Compared to state-of-the-art bio-inspired categorization methods, the proposed algorithm requires less hardware resource, reduces the computation complexity by at least five times, and is an ideal candidate for hardware implementation with event-based circuits.

Related Papers

• → Visual Search and the Collapse of Categorization.(2005)35 cited
• → The neurobiology of categorization(2010)4 cited
• → Two categorization patterns in idiom semantics(2016)1 cited
• On the Reasons for Cognitive Differences During Categorization(2009)
• → Is one object enough? Diagnosticity of single objects for fast scene categorization(2022)