Scene understanding with tri-training

Lin Zhu, Jie Zhou, Jingyan SongProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2007 · DOI

Abstract

Scene understanding needs not only detecting objects in the scene, but also obtaining the relationship between the objects and the scene, for example the reasonable size and occurrence possibility of objects at one position in the scene. With this relationship, the traditional object detection approach, which may misclassify objects with wrong sizes or position of the scene, can be greatly improved. In this paper, a novel scale model is proposed to describe the understanding of the scene. The scale model consists of the occurrence possibility and the reasonable size of pedestrian in each position of the scene. The scale model is learned by counting the pedestrian examples with different sizes in different positions of the scene for a period of time, instead of computing the geometry and viewpoint information in a single image. The examples are detected automatically by a detector which is trained with tri-training based semi-supervised approach. Experimental results indicate that the scale model of the scene can be learned with semi-supervised detection without the information of the 3D geometry and the assumption of plain ground.
BibTeX
@inproceedings{zhu2007scene,
  author = {Lin Zhu and Jie Zhou and Jingyan Song},
  title = {{Scene understanding with tri-training}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2007},
  doi = {10.1117/12.750064},
}

Loading related content...

Figure