E2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles
Zhenyu Hu, Pengcheng Pi, Zhenyu Wu, Yunhe Xue, Jiayi Shen, Jianchao Tan, Xiangru Lian, Zhangyang Wang, Ji yin Liu · 2021
Unmanned Aerial Vehicles (UAVs) based video text spot-ting has been extensively used in civil and military domains. UAV’s limited battery capacity motivates us to develop an energy-efficient video text spotting solution. In this paper, we first revisit RCNN’s crop & resize training strategy and empirically find that it outperforms aligned RoI sampling on a real-world video text dataset captured by UAV. To re-duce energy consumption, we further propose a multi-stage image processor that takes videos’ redundancy, continuity, and mixed degradation into account. The model is pruned and quantized before deployed on Raspberry Pi. Our pro-posed energy-efficient video text spotting solution, dubbed as E2V T S, outperforms all previous methods by achieving a competitive tradeoff between energy efficiency and performance. All our codes and pre-trained models are available at https://github.com/wuzhenyusjtu/LPCVC20-VideoTextSpotting.