A realtime vehicle status perception approach, which directly extracts vehicle status from our proposed novel video feature, temporal component-weight. Specifically, temporal component-weight is calculated based on a sampling of the whole frame.
[1] J. Chen, Y. Fang, H. Sheng, I. Masaki, B. Horn and Z. Xiong, "Real-time Vehicle Status Perception Without Frame-based Segmentation for Smart Camera Network," 2018 4th International Conference on Universal Village (UV), Boston, MA, USA, 2018, pp. 1-6.