An Address-Event Vision Sensor for Multiple Transient Object Detection

We present a vision sensor chip designed to detect multiple transient objects - objects that either move or change in light intensity - and output their locations using address-event representation. The sensor uses a novel onset detector to detect transient objects and a dynamically-wired winner-takes-all circuit to group pixels and select the brightest pixel in each object. This paper describes the circuits and also presents measurements that characterize the performance of the sensor chip.

[1]  Timothy K. Horiuchi,et al.  Object-Based Selection Within an Analog VLSI Visual Attention System , 1998 .

[2]  Giacomo Indiveri,et al.  A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity , 2006, IEEE Transactions on Neural Networks.

[3]  Kwabena Boahen,et al.  Point-to-point connectivity between neuromorphic chips using address events , 2000 .

[4]  Alexander Fish,et al.  An APS with 2-D winner-take-all selection employing adaptive spatial filtering and false alarm reduction , 2003 .

[5]  Kwabena Boahen.  Retinomorphic vision systems , 1996, Proceedings of Fifth International Conference on Microelectronics for Neural Networks.

[6]  C. Toumazou,et al.  A micropower centroiding vision processor , 2006, IEEE Journal of Solid-State Circuits.

[7]  Giacomo Indiveri,et al.  A neuromorphic VLSI device for implementing 2D selective attention systems , 2001, IEEE Trans. Neural Networks.

[8]  T. Delbruck,et al.  A 64x64 aer logarithmic temporal derivative silicon retina , 2005, Research in Microelectronics and Electronics, 2005 PhD.

[9]  Carver A. Mead,et al.  Analog VLSI Phototransduction by continuous-time, adaptive, logarithmic photoreceptor circuits , 1995 .

[10]  Giacomo Indiveri,et al.  Neuromorphic analog VLSI sensor for visual tracking: circuits and application examples , 1999 .

[11]  John Lazzaro,et al.  Winner-Take-All Networks of O(N) Complexity , 1988, NIPS.

[12]  Jörg Kramer,et al.  An on/off transient imager with event-driven, asynchronous read-out , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[13]  Tobi Delbrück,et al.  A 128 X 128 120db 30mw asynchronous vision sensor that responds to relative intensity change , 2006, 2006 IEEE International Solid State Circuits Conference - Digest of Technical Papers.

[14]  Idaku Ishii,et al.  A digital vision chip specialized for high-speed target tracking , 2003 .

[15]  Ralph Etienne-Cummings,et al.  A dual pixel-type array for imaging and motion centroid localization , 2002 .

[16]  Ralph Etienne-Cummings,et al.  VLSI Implementation of Motion Centroid Localization for Autonomous Navigation , 1998, NIPS.

[17]  Stephen P. DeWeerth,et al.  Analog VLSI circuits for stimulus localization and centroid computation , 1992, International Journal of Computer Vision.

[18]  Giacomo Indiveri,et al.  A low-power adaptive integrate-and-fire neuron circuit , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[19]  Giacomo Indiveri,et al.  An adaptive visual tracking sensor with a hysteretic winner-take-all network , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[20]  T. G. Morris,et al.  An analog VLSI focal-plane processing array that performs object-based attentive selection , 1997, Proceedings of 40th Midwest Symposium on Circuits and Systems. Dedicated to the Memory of Professor Mac Van Valkenburg.