Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision
Abstract
We describe an efficient method of improving the performance of vision algorithms operating on video streams by reducing the amount of data captured and transferred from image sensors to analysis servers in a data-aware manner. The key concept is to combine guided, highly heterogeneous sampling with an intelligent Scene Cache. This enables the system to adapt to spatial and temporal patterns in the scene, thus reducing redundant data capture and processing. A software prototype of our framework running on a general-purpose embedded processor enables superior object detection accuracy (by 56%) at similar energy consumption (slight improvement of 4%) compared to an H.264 hardware accelerator.
Cite
Text
Simpson et al. "Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00370Markdown
[Simpson et al. "Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/simpson2020cvprw-intelligent/) doi:10.1109/CVPRW50498.2020.00370BibTeX
@inproceedings{simpson2020cvprw-intelligent,
title = {{Intelligent Scene Caching to Improve Accuracy for Energy-Constrained Embedded Vision}},
author = {Simpson, Benjamin and Lubana, Ekdeep Singh and Liu, Yuchen and Dick, Robert P.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {3114-3122},
doi = {10.1109/CVPRW50498.2020.00370},
url = {https://mlanthology.org/cvprw/2020/simpson2020cvprw-intelligent/}
}