Preprint Open Access
Enabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoT
Francesco Paissan; Massimo Gottardi; Elisabetta Farella
The Internet of Things (IoT) and smart city paradigm includes ubiquitous technology to extract context information in order to return useful services to users and citizens. An essential role in this scenario is often played by computer vision applications, requiring the acquisition of images from specific devices. The need for high-end cameras often penalizes this process since they are power-hungry and ask for high computational resources to be processed. Thus, the availability of novel low-power vision sensors, implementing advanced features like in-hardware motion detection, is crucial for computer vision in the IoT domain. Unfortunately, to be highly energy-efficient, these sensors might worsen the perception performance (e.g., resolution, frame rate, color). Therefore, domain-specific pipelines are usually delivered in order to exploit the full potential of these cameras. This paper presents the development, analysis, and embedded implementation of a realtime detection, classification and tracking pipeline able to exploit the full potential of background filtering Smart Vision Sensors (SVS). The power consumption obtained for the inference - which requires 8ms - is 7.5 mW.
| Name | Size | |
|---|---|---|
|
2102.01340.pdf
md5:5ea6356e8b22c56d6919899241a7196f |
467.8 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 346 | 346 |
| Downloads | 130 | 130 |
| Data volume | 60.8 MB | 60.8 MB |
| Unique views | 204 | 204 |
| Unique downloads | 125 | 125 |
- Publication date:
- February 5, 2021
- DOI:
-
- Grants:
-
European Commission:
- MARVEL - Multimodal Extreme Scale Data Analytics for Smart Cities Environments (957337)
- Meeting:
- DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021), Virtual, 5 February 2021
- Related identifiers:
- Published in
- 10.48550/arXiv.2102.01340 (Conference paper)
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International