A heuristic for the retrieval of objects in low resolution video

International audienceIn this paper, we tackle the problem of matching of objects in video in the context of the rough indexing paradigm. In this context, the video data are of very low resolution and segmentation is consequently inaccurate. The region features (texture, color, shape) are not strongly relevant due to the resolution. The structure of the objects must be considered in order to improve the robustness of the matching of regions. Indeed, the problem of object matching can be expressed in terms of directed acyclic graph (DAG) matching. Here, we propose a method based on a heuristic in order to approach object matching. The results are compared with those of a method based on relaxation matching