IoT

EcoVis leverages mmWave sensing to identify regions of interest (ROIs) for compressing surveillance video frames, reducing static background transmission and optimizing resource usage. Unlike traditional video-based methods, our approach lowers energy consumption by ~40% and enhances efficiency by ~25% through dynamic camera sleep cycles. For tasks like vehicle detection, EcoVis minimizes camera reliance, enabling on-device processing and improving network efficiency by ~20%. We also introduce uniform and non-uniform tiling algorithms that use mmWave-derived ROIs for tile-specific Quantization Parameter (QP) encoding, optimizing video compression. It will be published in proceedings of PerCom 2025, Washington D.C, USA.

Recent Wi-Fi sensing literature uses deep neural networks to analyze wireless channel dynamics. This being a resource intensive process is usually carried out at the edge, but this isn’t always practical due to cost and bandwidth constraints. We propose on-device sensing for IoT platforms, introducing WISDOM to optimize inference models based on hardware and application needs. WISDOM achieves better utility than baseline models in over 85% of cases. It is published in proceedings of PerCom Workshop 2024, Biarritz, France.