Abstract

Object detection and recognition has achieved a signi ficant progress in recent years. However robust 3D object detection and segmentation in noisy 3D data volumes remains a challenging problem. Localizing an object generally requires its spatial configuration (i.e., pose, size) being aligned with the trained object model, while estimation of an object ’s spatial configuration is only valid at locations where the object appears. Detecting object while exhaustively searching its spatial parameters, is computationally prohibitive due to the high dimension- ality of 3D search space. In this paper, we circumvent this computational com- plexity by proposing a novel framework capable of incrementally learning the object parameters (IPL) of location, pose and scale. This method is based on a sequence of binary encodings of the projected true positives from the original 3D object annotations (i.e., the projections of the global optima from the global space into the sections of subspaces). The training samples in each projected subspace are labeled as positive or negative, according their spatial registration distances towards annotations as ground-truth. Each encoding process can be considered as a general binary classi fication problem and is implemented using probabilis- tic boosting tree algorithm. We validate our approach with extensive experiments and performance evaluations for Ileo-Cecal Valve (ICV) detection in both clean and tagged 3D CT colonography scans. Our final ICV detection system also in- cludes an optional prior learning procedure for IPL which further speeds up the detection.