Title :
Learning to compensate for sensor variability at the focal plane
Author :
Pouliquen, Philippe O. ; Andreou, Andreas G. ; Cauwenberghs, Gert ; Terril, Conrad W.
Author_Institution :
Johns Hopkins Univ., Baltimore, MD, USA
fDate :
6/21/1905 12:00:00 AM
Abstract :
We present the design of neuromorphic CMOS integrated circuit imager arrays that performs analog computation on-chip prior to conventional off-chip digitizing. These imagers are capable of performing real-time nonuniformity correction using Scribner´s scene-based nonuniformity correction (SBNUC) algorithm and can therefore learn to cancel the offsets of the sensor array dynamically
Keywords :
CMOS analogue integrated circuits; CMOS image sensors; analogue processing circuits; array signal processing; compensation; focal planes; real-time systems; SBNUC algorithm; focal plane; neuromorphic CMOS integrated circuit imager array design; on-chip analog computation; real-time nonuniformity correction; scene-based nonuniformity correction algorithm; sensor array offset cancellation; sensor variability compensation learning; CMOS analog integrated circuits; CMOS integrated circuits; Capacitors; Charge coupled devices; Infrared detectors; Integrated circuit noise; Low pass filters; Neuromorphics; Noise reduction; Sensor arrays;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.833429
