Integrating Recognition and Reconstruction for Cognitive Traffic Scene Analysis from a Moving Vehicle
This paper presents a practical system for vision-based traffic scene analysis from a moving vehicle based on a cognitive feedback loop which integrates real-time geometry estimation with appearance-based object detection. We demonstrate how those two components can benefit from each other’s continuous input and how the transferred knowledge can be used to improve scene analysis. Thus, scene interpretation is not left as a matter of logical reasoning, but is instead addressed by the repeated interaction and consistency checks between different levels and modes of visual processing. As our results show, the proposed tight integration significantly increases recognition performance, as well as overall system robustness. In addition, it enables the construction of novel capabilities such as the accurate 3D estimation of object locations and orientations and their temporal integration in a world coordinate frame. The system is evaluated on a challenging real-world car detection task in an urban scenario.
KeywordsObject Detection Stereo Pair Scene Analysis Reconstruction Module Scene Geometry
Unable to display preview. Download preview PDF.
- 1.Andreone, L., Antonello, P.C., Bertozzi, M., Broggi, A., Fascioli, A., Ranzato, D.: Vehicle detection and localization in infra-red images. In: Intel. Vehicles Symp. 2002 (2002)Google Scholar
- 3.Cornelis, N., Cornelis, K., Van Gool, L.: Fast compact city modeling for navigation pre-visualization. In: CVPR 2006 (2006)Google Scholar
- 5.Gavrila, D., Philomin, V.: Real-time object detection for smart vehicles. In: ICCV 1999, pp. 87–93 (1999)Google Scholar
- 9.Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: CVPR 2005 (2005)Google Scholar
- 10.Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2) (2004)Google Scholar
- 11.Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27(10) (2005)Google Scholar
- 13.Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. Technical Report AIM-2005-025, MIT AI Lab (2005)Google Scholar