Yan, Mingxuan and Wang, Yi and Xiao, Xuedou and Luo, Zhiqing and He, Jianhua and Wang, Wei (2023) Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation. In: MM '23: The 31st ACM International Conference on Multimedia, 2023-10-29 - 2023-11-03, Ottawa ON Canada.
Yan, Mingxuan and Wang, Yi and Xiao, Xuedou and Luo, Zhiqing and He, Jianhua and Wang, Wei (2023) Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation. In: MM '23: The 31st ACM International Conference on Multimedia, 2023-10-29 - 2023-11-03, Ottawa ON Canada.
Yan, Mingxuan and Wang, Yi and Xiao, Xuedou and Luo, Zhiqing and He, Jianhua and Wang, Wei (2023) Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation. In: MM '23: The 31st ACM International Conference on Multimedia, 2023-10-29 - 2023-11-03, Ottawa ON Canada.
Abstract
Offloading computing to edge servers is a promising solution to support growing video understanding applications at resource-constrained IoT devices. Recent efforts have been made to enhance the scalability of such systems by reducing inference costs on edge servers. However, existing research is not directly applicable to pixel-level vision tasks such as video semantic segmentation (VSS), partly due to the fluctuating VSS accuracy and segment bitrate caused by the dynamic video content. In response, we present Penance, a new edge inference cost reduction framework. By exploiting softmax outputs of VSS models and the prediction mechanism of H.264/AVC codecs, Penance optimizes model selection and compression settings to minimize the inference cost while meeting the required accuracy within the available bandwidth constraints. We implement Penance in a commercial IoT device with only CPUs. Experimental results show that Penance consumes a negligible 6.8% more computation resources than the optimal strategy while satisfying accuracy and bandwidth constraints with a low failure rate.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | video analytics, edge offloading, video semantic segmentation |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 27 Jun 2025 14:08 |
Last Modified: | 27 Jun 2025 14:09 |
URI: | http://repository.essex.ac.uk/id/eprint/37795 |
Available files
Filename: Think_before_You_Leap.pdf
Licence: Creative Commons: Attribution 4.0