On Evaluation of 6D Object Pose Estimation

A pose of a rigid object has 6 degrees of freedom and its full knowledge is required in many robotic and scene understanding applications. Evaluation of 6D object pose estimates is not straightforward. Object pose may be ambiguous due to object symmetries and occlusions, i.e. there can be multiple object poses that are indistinguishable in the given image and should be therefore treated as equivalent. The paper defines 6D object pose estimation problems, proposes an evaluation methodology and introduces three new pose error functions that deal with pose ambiguity. The new error functions are compared with functions commonly used in the literature and shown to remove certain types of non-intuitive outcomes. Evaluation tools are provided at: https://github.com/thodan/obj_pose_eval.

[1]  Niloy J. Mitra,et al.  Symmetry in 3D Geometry: Extraction and Applications , 2013, Comput. Graph. Forum.

[2]  Vincent Lepetit,et al.  Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes , 2012, ACCV.

[3]  Eric Brachmann,et al.  Learning 6D Object Pose Estimation Using 3D Object Coordinates , 2014, ECCV.

[4]  Nassir Navab,et al.  Model globally, match locally: Efficient and robust 3D object recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Jitendra Malik,et al.  Viewpoints and keypoints , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Adam Morawiec,et al.  Orientations and Rotations , 2004 .

[7]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[8]  Tinne Tuytelaars,et al.  Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach , 2013, 2013 IEEE International Conference on Computer Vision.

[9]  Silvio Savarese,et al.  Beyond PASCAL: A benchmark for 3D object detection in the wild , 2014, IEEE Winter Conference on Applications of Computer Vision.

[10]  Tae-Kyun Kim,et al.  Latent-Class Hough Forests for 3D Object Detection and Pose Estimation , 2014, ECCV.

[11]  Kourosh Khoshelham,et al.  Accuracy analysis of kinect depth data , 2012 .

[12]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[13]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[14]  Manolis I. A. Lourakis,et al.  Detection and fine 3D pose estimation of texture-less objects in RGB-D images , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Henrik I. Christensen,et al.  3D pose estimation of daily objects using an RGB-D camera , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Andrew W. Fitzgibbon,et al.  Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Vincent Lepetit,et al.  Learning descriptors for object recognition and 3D pose estimation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Adam Morawiec,et al.  Orientations and Rotations: Computations in Crystallographic Textures , 1999 .

[19]  Ravindra K. Ahuja,et al.  Network Flows , 2011 .

[20]  Eric Brachmann,et al.  Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).