2023 Low-Power Computer Vision Challenge (LPCVC) Summary
Leo Chen, Benjamin Boardley, Ping Hu, Yiru Wang, Yifan Pu, Xin Jin, Yongqiang Yao, Ruihao Gong, Bo Li, Gao Huang, Xianglong Liu, Zifu Wan, Xinwang Chen, Ning Liu, Ziyi Zhang, Dongping Liu, Ruijie Shan, Zhengping Che, Fachao Zhang, Xiaofeng Mou, Jian Tang, Maxim Chuprov, Ivan Malofeev, Alexander Goncharenko, Andrey Shcherbin, Arseny Yanchenko, Sergey Alyamkin, Xiao Hu, George K. Thiruvathukal, Yung Hsiang Lu
TL;DR
The paper analyzes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC), which targets semantic segmentation on UAV imagery under strict power constraints. It introduces the evaluation framework, including the mean Dice Score Coefficient ($mDSC$) for accuracy and a time-based score, evaluated on an NVIDIA Jetson Nano with a 5W limit, formalized as $\mathrm{Score} = \frac{\mathrm{Accuracy}}{\mathrm{Inference\ Time}}$. The study presents three winning approaches—Yocto-Revival Network (ModelTC), TopFormer-based (AidgetRock), and PIDNet (ENOT)—and highlights common optimization strategies such as TensorRT-based quantization, network fusion, pruning, and data augmentation, which together enable high accuracy with low latency. The findings demonstrate that strong, low-power semantic segmentation is feasible on edge devices for disaster response, offering practical implications for real-time UAV assessment and rapid decision-making in post-disaster scenarios.
Abstract
This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improving accuracy, at the expense of ever-growing sizes of machine models. LPCVC balances accuracy with resource requirements. Winners must achieve high accuracy with short execution time when their CV solutions run on an embedded device, such as Raspberry PI or Nvidia Jetson Nano. The vision problem for 2023 LPCVC is segmentation of images acquired by Unmanned Aerial Vehicles (UAVs, also called drones) after disasters. The 2023 LPCVC attracted 60 international teams that submitted 676 solutions during the submission window of one month. This article explains the setup of the competition and highlights the winners' methods that improve accuracy and shorten execution time.