Rhythmic pixel regions: multi-resolution visual sensing system towards high-precision visual computing at low power
| Autor: | Alexander Shearer, Van Nguyen, Venkatesh Kodukula, Yifei Liu, Srinivas Lingutla, Robert LiKamWa |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
010302 applied physics
Pixel business.industry Computer science Interface (computing) Frame (networking) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology 01 natural sciences Pipeline (software) 020202 computer hardware & architecture Visual computing Encoding (memory) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Memory footprint Computer vision Artificial intelligence business Image resolution |
| Zdroj: | ASPLOS |
| DOI: | 10.1145/3445814.3446737 |
| Popis: | High spatiotemporal resolution can offer high precision for vision applications, which is particularly useful to capture the nuances of visual features, such as for augmented reality. Unfortunately, capturing and processing high spatiotemporal visual frames generates energy-expensive memory traffic. On the other hand, low resolution frames can reduce pixel memory throughput, but reduce also the opportunities of high-precision visual sensing. However, our intuition is that not all parts of the scene need to be captured at a uniform resolution. Selectively and opportunistically reducing resolution for different regions of image frames can yield high-precision visual computing at energy-efficient memory data rates. To this end, we develop a visual sensing pipeline architecture that flexibly allows application developers to dynamically adapt the spatial resolution and update rate of different "rhythmic pixel regions" in the scene. We develop a system that ingests pixel streams from commercial image sensors with their standard raster-scan pixel read-out patterns, but only encodes relevant pixels prior to storing them in the memory. We also present streaming hardware to decode the stored rhythmic pixel region stream into traditional frame-based representations to feed into standard computer vision algorithms. We integrate our encoding and decoding hardware modules into existing video pipelines. On top of this, we develop runtime support allowing developers to flexibly specify the region labels. Evaluating our system on a Xilinx FPGA platform over three vision workloads shows 43-64% reduction in interface traffic and memory footprint, while providing controllable task accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|