AN ALGORITHM AND SYSTEM FOR FINDING THE NEXT BEST VIEW IN A 3-D OBJECT MODELING TASK A thesis

Sensor placement for 3-D modeling is a growing area of computer vision and robotics. The objective of a sensor placement system is to make task-directed decisions for optimal pose selection. This thesis proposes a Next Best View (NBV) solution to the sensor placement problem. Our algorithm computes the next best view by optimizing an objective function that measures the quantity of unknown information in each of a group of potential viewpoints. The potential views are either placed uniformly around the object or are calculated from the surface normals of the occupancy grid model. For each iteration, the optimal pose from the objective function calculation is selected to initiate the collection of new data. The model is incrementally updated from the information acquired in each new view. This process terminates when the number of recovered voxels ceases to increase, yielding the nal model. We tested two di erent algorithms on 8 objects of various complexity, including objects with simple concave, simple hole, and complex hole self-occlusions. The rst algorithm chooses new views optimally but is slow to compute. The second algorithm is fast but not as e ective as the rst algorithm. The two NBV algorithms successfully model all 8 of the tested objects. The models compare well visually with the original objects within the constraints of occupancy grid resolution. Objects of complexity greater than mentioned above were not tested due to the time required for modeling. A mathematical comparison was not made between the objects and their corresponding models since we are concerned only with the acquisition of complete models, not the accuracy of the models.

[1]  Wang Ke,et al.  Next best view of range sensor , 1996, Proceedings of the 1996 IEEE IECON. 22nd International Conference on Industrial Electronics, Control, and Instrumentation.

[2]  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.

[3]  Avinash C. Kak,et al.  Planning sensing strategies in a robot work cell with multi-sensor capabilities , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[4]  Kiriakos N. Kutulakos,et al.  Global surface reconstruction by purposive control of observer motion , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  M. Isabel Ribeiro,et al.  Active view selection for efficient 3D scene reconstruction , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[6]  Michael Werman,et al.  Active vision: 3D from an image sequence , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[7]  Randy E. Ellis.  Planning Tactile Recognition Paths in Two and Three Dimensions , 1992 .

[8]  Hugh F. Durrant-Whyte,et al.  A Bayesian Approach to Optimal Sensor Placement , 1990, Int. J. Robotics Res..

[9]  Christian Laugier,et al.  Automatic camera placement for robot vision tasks , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

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

[11]  Masayoshi Kakikura,et al.  Occlusion avoidance of visual sensors based on a hand-eye action simulator system: HEAVEN , 1987, Adv. Robotics.

[12]  Richard A. Volz,et al.  Object recognition using multiple views , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[13]  Konstantinos A. Tarabanis,et al.  Computing camera viewpoints in a robot work-cell , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[14]  Franc Solina,et al.  Planning the Next View Using the Max-Min Principle , 1993, CAIP.

[15]  James J. Clark,et al.  Modal Control Of An Attentive Vision System , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[16]  Hugh F. Durrant-Whyte.  Uncertain geometry in robotics , 1988, IEEE J. Robotics Autom..

[17]  Hongbin Zha,et al.  Active modeling of 3-D objects: planning on the next best pose (NBP) for acquiring range images , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[18]  Roger Y. Tsai,et al.  Analytical characterization of the feature detectability constraints of resolution, focus, and field-of-view for vision sensor planning , 1994 .

[19]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[20]  Peter K. Allen,et al.  Sensor planning in an active robotic work cell , 1992, Other Conferences.

[21]  D. W. Bouldin,et al.  Automatic sensor placement for volumetric object characterization , 1995 .

[22]  Hiromi T. Tanaka,et al.  Active 3D modeling by recursive viewpoint selection based on symmetry , 1995, Other Conferences.

[23]  W. Eric L. Grimson.  Disambiguating sensory interpretations using minimal sets of sensory data , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[24]  John K. Tsotsos,et al.  Behaviors for active object recognition , 1993, Other Conferences.

[25]  Éric Marchand,et al.  Controlled camera motions for scene reconstruction and exploration , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Cregg K. Cowan.  Model-based synthesis of sensor location , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[27]  Fumio Kishino,et al.  Active camera controlling for manipulation , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  Yulin Yao,et al.  Computing robust viewpoints with multi-constraints using tree annealing , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

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

[30]  Claus B. Madsen,et al.  A Viewpoint Planning Strategy for Determining True Angles on Polyhedral Objects by Camera Alignment , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Carl-Johan Westelius,et al.  Focus of attention and gaze control for robot vision , 1995 .

[32]  Günther Seliger,et al.  Analysis of the geometrical features detectability constraints for laser-scanner sensor planning , 1994 .

[33]  Arun K. Pujari,et al.  Volume intersection with optimal set of directions , 1991, Pattern Recognit. Lett..

[34]  Hernsoo Hahn,et al.  An Optimal Sensing Strategy for Recognition and Localization of 3D Natural Quadric Objects , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Katsushi Ikeuchi,et al.  Task-oriented generation of visual sensing strategies , 1995, Proceedings of IEEE International Conference on Computer Vision.

[36]  A. David Marshall,et al.  Automatically planning the inspection of three-dimensional objects using stereo computer vision , 1996, Other Conferences.

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

[38]  Xueyin Lin,et al.  Model-based next view planning by using rules-automatic feature prediction and detection , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Glenn H. Tarbox,et al.  Planning for Complete Sensor Coverage in Inspection , 1995, Comput. Vis. Image Underst..

[40]  Besma Abidi.  Automatic sensor placement , 1995, Other Conferences.

[41]  Konstantinos A. Tarabanis,et al.  Computing Occlusion-Free Viewpoints , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

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

[43]  Andrea Califano,et al.  Data and model driven foveation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[44]  Anthony A. Maciejewski,et al.  Camera and light placement for automated assembly inspection , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[45]  Denis Laurendeau,et al.  Processing of a multiscale triangulated surface model of a 3D scene for a robotics application , 1993, Optics & Photonics.

[46]  Xiaobu Yuan,et al.  A Mechanism of Automatic 3D Object Modeling , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[47]  Lester A. Gerhardt,et al.  Three-dimensional view planning for noncontact dimensional inspection , 1996, Electronic Imaging.

[48]  Ioannis Stamos,et al.  3-D modeling from range imagery: an incremental method with a planning component , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[49]  Ruzena Bajcsy,et al.  Occlusions as a Guide for Planning the Next View , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

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

[51]  Xueyin Lin,et al.  Optimal sensor planning with minimal cost for 3D object recognition using sparse structured light images , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[52]  Armin Grün,et al.  Automatic Sensor Placement for Accurate Dimensional Inspection , 1995, Comput. Vis. Image Underst..