Constraint-Based Sensor Planning for Scene Modeling

We describe an automated scene modeling system that consists of two components operating in an interleaved fashion: an incremental modeler that builds solid models from range imagery; and a sensor planner that analyzes the resulting model and computes the next sensor position. This planning component is target-driven and computes sensor positions using model information about the imaged surfaces and the unexplored space in a scene. The method is shape-independent and uses a continuous-space representation that preserves the accuracy of sensed data. It is able to completely acquire a scene by repeatedly planning sensor positions, utilizing a partial model to determine volumes of visibility for contiguous areas of unexplored scene. These visibility volumes are combined with sensor placement constraints to compute sets of occlusion-free sensor positions that are guaranteed to improve the quality of the model. We show results for the acquisition of a scene that includes multiple, distinct objects with high occlusion.

[1]  Dinesh Manocha,et al.  Simplification envelopes , 1996, SIGGRAPH.

[2]  Konstantinos A. Tarabanis,et al.  The MVP sensor planning system for robotic vision tasks , 1995, IEEE Trans. Robotics Autom..

[3]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[4]  Konstantinos A. Tarabanis,et al.  Computing Camera Viewpoints in an Active Robot Work Cell , 1999, Int. J. Robotics Res..

[5]  Mongi A. Abidi,et al.  Best-next-view algorithm for three-dimensional scene reconstruction using range images , 1995, Other Conferences.

[6]  Ioannis Stamos,et al.  Automated model acquisition from range images with view planning , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Dmitry B. Goldgof,et al.  Building a B-rep from a segmented range image , 1994, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[8]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[9]  Ruzena Bajcsy,et al.  How to Decide From the First View Where to Look Next , 1990 .

[10]  C. Ian Connolly,et al.  The determination of next best views , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[11]  Katsushi Ikeuchi,et al.  Consensus surfaces for modeling 3D objects from multiple range images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[12]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[13]  Ioannis Stamos,et al.  Interactive sensor planning , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[14]  Kiriakos N. Kutulakos.  Exploring three-dimensional objects by controlling the point of observation , 1995 .

[15]  Marc Levoy,et al.  Zippered polygon meshes from range images , 1994, SIGGRAPH.

[16]  Peter K. Allen,et al.  3-D Modeling from Range Imagery: An Incremental Method with a Planning Component , 1999, Image Vis. Comput..

[17]  Konstantinos A. Tarabanis,et al.  A survey of sensor planning in computer vision , 1995, IEEE Trans. Robotics Autom..

[18]  Frank P. Ferrie,et al.  Uncertain views , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Frank P. Ferrie,et al.  Autonomous Exploration: Driven by Uncertainty , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Ruzena Bajcsy,et al.  Solution to the next best view problem for automated CAD model acquisiton of free-form objects using range cameras , 1995, Optics East.