MDIC '01 Proceedings of the Second International Workshop on Multimedia Databases and Image Communication
Augmenting cartographic resources for autonomous driving
Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
Self-supervised aerial image analysis for extracting parking lot structure
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Automatic video activity detection using compressed domain motion trajectories for H.264 videos
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
We propose an elevation based approach to parkinglot structure analysis from aerial imagery. In contrastto image-based methods, the new approach treats parkedvehicles as 3-D microstructures and attempts to locatethem in the elevation domain. The STME (SurfaceTexture and Microstructure Extraction) system is applied tothe elevation maps to extract the 3-D microstructures. Ahybrid application of this system to both intensity and elevation maps results in a complete extraction of individual vehicles. Based on a comparison of texture exploitation techniques, a WCC weighted combination criterion algorithm is presented to generate a clean parking lot ground surface, which facilitates visualization andsimulation of parking lot activities with a high degree ofvisual realism.