Abstract
Continuous mobile vision is limited by the inability to efficiently capture image frames and process vision features. This is largely due to the energy burden of analog readout circuitry, data traffic, and intensive computation. To promote efficiency, we shift early vision processing into the analog domain. This results in RedEye, an analog convolutional image sensor that performs layers of a convolutional neural network in the analog domain before quantization. We design RedEye to mitigate analog design complexity, using a modular column-parallel design to promote physical design reuse and algorithmic cyclic reuse. RedEye uses programmable mechanisms to admit noise for tunable energy reduction. Compared to conventional systems, RedEye reports an 85% reduction in sensor energy, 73% reduction in cloudlet-based system energy, and a 45% reduction in computation-based system energy.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - 2016 43rd International Symposium on Computer Architecture, ISCA 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 255-266 |
Number of pages | 12 |
ISBN (Electronic) | 9781467389471 |
DOIs | |
State | Published - Aug 24 2016 |
Externally published | Yes |
Event | 43rd International Symposium on Computer Architecture, ISCA 2016 - Seoul, Korea, Republic of Duration: Jun 18 2016 → Jun 22 2016 |
Other
Other | 43rd International Symposium on Computer Architecture, ISCA 2016 |
---|---|
Country/Territory | Korea, Republic of |
City | Seoul |
Period | 6/18/16 → 6/22/16 |
Keywords
- computer vision
- continuous mobile vision
- pre-quantization processing
- programmable analog computing
ASJC Scopus subject areas
- Hardware and Architecture