A 130 nm 165 nJ/frame Compressed-Domain Smashed-Filter-Based Mixed-Signal Classifier for “In-Sensor” Analytics in Smart Cameras

To avoid data deluge at the back end, it is imperative that advanced sensor nodes perform “in-sensor” processing to extract relevant features from data. We propose a compressed-domain smashed-filter-based object recognition system and measurements from a 130 nm mixed-signal test chip to demonstrate reconfigurable and ultra-low power operation. We measure greater than 90% accuracy in object localization with 165 nJ energy per frame on image data sets.