This Article 
 Bibliographic References 
 Add to: 
Constraint-Based Sensor Planning for Scene Modeling
December 2000 (vol. 22 no. 12)
pp. 1460-1467

Abstract—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] S. Abrams, P.K. Allen, and K.A. Tarabanis, “Computing Camera Viewpoints in an Active Robot Workcell,” Int'l J. Robotics Research, vol. 18, no. 3, pp. 267-285, Mar. 1999.
[2] J.E. Banta, Y Zhen, X.Z. Wang, G. Zhang, M.T. Smith, and M.A. Abidi, “A“Best-Next-View”Algorithm for Three-Dimensional Scene Reconstruction Using Range Cameras,” Proc. Intelligent Systems and Advanced Manufacturing Symp., 1995.
[3] Y. Chen and G. Medioni, "Object Modeling by Registration of Multiple Range Views," Proc. IEEE Int'l Conf. Robotics and Automation, pp. 2,724-2,729,Sacramento, Calif., 1991.
[4] J. Cohen, A. Varshney, D. Manocha, G. Turk, H. Weber, P. Agarwal, F.P. Brooks Jr., and W.V. Wright, "Simplification Envelopes," Computer Graphics Proc. Ann. Conf. Series (Proc. Siggraph '96), pp. 119-128, 1996.
[5] C. Connolly, “The Determination of Next Best Views,” Proc. IEEE Int'l Conf. Robotics and Automation, pp. 432-435, 1985.
[6] B. Curless and M. Levoy, “A Volumetric Method for Building Complex Models from Range Images,” Proc. SIGGRAPH '96, pp. 303-312, 1996.
[7] A. Hoover, D. Goldgof, and K. Bowyer, “Building a B-Rep from a Segmented Range Image,” Proc. Second CAD-Based Vision Workshop, pp. 74-81, Feb. 1994.
[8] K.N. Kutulakos, “Exploring Three-Dimensional Objects by Controlling the Point of Observation,” PhD thesis, Computer Sciences Dept., Univ. of Wisconsin, 1994.
[9] R. Pito and R. Bajcsy, “A Solution to the Next Best View Problem for Automated CAD Model Acquisition of Free-form Objects using Range Cameras,” Proc. SPIE Symp. Intelligent Systems and Advanced Manufacturing, 1995.
[10] J. Maver and R. Bajcsy, “How to Decide from the First View Where to Look Next,” Proc. DARPA Image Understanding Workshop, pp. 482-496, 1990.
[11] M. Reed, P.K. Allen, and I. Stamos, “Automated Model Acquisition from Range Images with View Planning,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1997.
[12] M. Reed and P.K. Allen, “3D Modeling from Range Imagery,” Image and Vision Computing, vol. 17, no. 2, pp. 99-111, Feb. 1999.
[13] IEEE Std 1149.1-1990, Test Access Port and Boundary-Scan Architecture, IEEE, Piscataway, N.J., Jan. 1992.
[14] I. Stamos and P.K. Allen, “Interactive Sensor Planning,” Conf. Computer Vision and Pattern Recognition, pp. 489-495, June 1998.
[15] K. Tarabanis, R.Y. Tsai, and P.K. Allen, “Satisfying the Resolution Constraint in the MVP Machine Vision Planning System,” Proc. 13th IASTED Int'l Symp. Robotics and Manufacturing, (also in Proc. DARPA Image Understanding Workshop), 1990.
[16] K. Tarabanis, P. Allen, and R. Tsai, A Survey of Sensor Planning in Computer Vision IEEE Trans. Robotics and Automation, vol. 11, pp. 86-104, 1995.
[17] K.A. Tarabanis, R.Y. Tsai, and P.K. Allen, "The MVP Sensor Planning System for Robotic Vision Tasks," IEEE Trans. Robotics and Automation, vol. 11, no. 1, pp. 72-85, 1995.
[18] G. Turk and M. Levoy, “Zippered Polygon Meshes from Range Images,” Proc. SIGGRAPH '94, pp. 311-318, 1994.
[19] P. Whaite and F.P. Ferrie, "Autonomous Exploration: Driven by Uncertainty," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 3, pp. 193-205, Mar. 1997.
[20] P. Whaite and F.P. Ferrie,“Uncertain views,” Proc. IEEE Computer Society Conf. on Computer Vision and PatternRecognition, pp. 3-9,Champaign, Ill., June15-18, 1992.
[21] M. Wheeler, Y. Sato, and K. Ikeuchi, "Consensus Surfaces for Modeling 3D Objects from Multiple Range Images," Proc. IEEE Int'l Conf. Computer Vision, pp. 917-924,Bombay, India, Jan. 1998.

Index Terms:
3D scene reconstruction, model acquisition, sensor planning, active vision.
Michael K. Reed, Peter K. Allen, "Constraint-Based Sensor Planning for Scene Modeling," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp. 1460-1467, Dec. 2000, doi:10.1109/34.895979
Usage of this product signifies your acceptance of the Terms of Use.