Object Detection in Multi-view 3D Reconstruction Using Semantic and Geometric Context
- School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel 91904
Keywords: Object Detection, Context, Segmentation, Semantic Classification, 3D Virtual City
Abstract. We present a method for object detection in a multi view 3D model. We use highly overlapping views, geometric data, and semantic surface classification in order to boost existing 2D algorithms. Specifically, a 3D model is computed from the overlapping views, and the model is segmented into semantic labels using height information, color and planar qualities. 2D detector is run on all images and then detections are mapped into 3D via the model. The detections are clustered in 3D and represented by 3D boxes. Finally, the detections, visibility maps and semantic labels are combined using a Support Vector Machine to achieve a more robust object detector.