Spatiotemporal Coherence based Annotation Placement for Surveillance Videos

  • Author(s):

Wei-Cheng Wang Chien-Yu Chiou Chun-Rong Huang Pau-Choo Chung Wei-Yun Huang

 


Introduction

In this paper, we propose a novel annotation placement approach for revealing information of foreground objects in surveillance videos. To arrange positions of annotations, spatiotemporal coherence between annotations and foreground objects is applied. The annotation placement problem is formulated as an optimization problem with respect to spatiotemporal coherence of annotations and foreground objects. The optimization problem is effectively solved by using Markov random fields (MRFs). To the best of our knowledge, this paper is the first work to discuss and solve the annotation placement problem for surveillance videos by considering the relationships between annotations and foreground objects with trajectories. As shown in the experiments, the proposed approach can arrange annotations based on the moving trajectories of foreground objects and prevent the occlusions between different annotations and foreground objects. It also achieves better quantitative and qualitative results compared to state-of-the-art approaches.


Demo Video Download

Download Demo Video

 

  • There are six videos: Crossroad, PETS 2009, Campus, Crossing, Venice, and TownCentre.

  • The demo video is composed by the results of five annotation placement approaches. The upper left frame shows the original frames. The upper center frame shows the results of the bounding box based approach. The upper right frame shows the results of the image based approach. The lower left frame shows the results of the clustering based approach. The lower center frame shows the results of the clutter-aware based approach. The lower right frame shows the results of the proposed approach.

  


Publications

[1] Wei-Cheng Wang, Chien-Yu Chiou, Chun-Rong Huang, Pau-Choo Chung, Wei-Yun Huang, "Spatiotemporal Coherence based Annotation Placement for Surveillance Videos," IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 3, pp. 787-801, 2018.