Temporal Photoreception for Adaptive Dynamic Range Image Sensing and Encoding
Abstract
We have implemented two analog VLSI computational sensors for sensing and encoding high dynamic range images by exploiting temporal dimension of photoreception. The first sensor is a multi-integration time photoreceptor that automatically adapts to use different integration periods depending on light intensity. It exhibits a dynamic range 128 times larger than that of a single integration period photoreceptor, approximately 1: 128 000. The second sensor is an intensity-to-time processing paradigm that is based on the notion that stronger stimuli elicit responses before weaker ones. The paradigm sorts pixels of sensed images by their intensities, thus achieving information-theoretic optimal encoding of images. It handles dynamic range of approximately 1 : 1 000 000. Both implementations can operate at standard video rate of 30 frames/sec.
BibTeX
@article{Brajovic-1998-14788,author = {Vladimir Brajovic and Ryohei Miyagawa and Takeo Kanade},
title = {Temporal Photoreception for Adaptive Dynamic Range Image Sensing and Encoding},
journal = {Neural Networks},
year = {1998},
month = {October},
volume = {11},
number = {7},
pages = {1149 - 1158},
}