| Summary: | Automated recognition and analysis of objects in images from urban transport corridors are important for many applications including asset management, measurement, location, analysis and change detection. Vehicle-based mobile mapping systems capture co-registered imagery and 3D point cloud information over hundreds of kilometers of transport corridor. Methods for extracting information from these large datasets are labour intensive and automatic methods are desired. This paper uses a depth map to segment regions of interest in colour images. Quantitative tests were carried out on two datasets. Experiments show that the resulting regions are relatively coarse, but overall the method is effective, and has the benefit of easy implementation.
|
|---|