Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach

In this paper we propose a new method for detecting multiple specific 3D objects in real time. We start from the template-based approach based on the LINE2D/LINEMOD representation introduced recently by Hinterstoisser et al., yet extend it in two ways. First, we propose to learn the templates in a discriminative fashion. We show that this can be done online during the collection of the example images, in just a few milliseconds, and has a big impact on the accuracy of the detector. Second, we propose a scheme based on cascades that speeds up detection. Since detection of an object is fast, new objects can be added with very low cost, making our approach scale well. In our experiments, we easily handle 10-30 3D objects at frame rates above 10fps using a single CPU core. We outperform the state-of-the-art both in terms of speed as well as in terms of accuracy, as validated on 3 different datasets. This holds both when using monocular color images (with LINE2D) and when using RGBD images (with LINEMOD). Moreover, we propose a challenging new dataset made of 12 objects, for future competing methods on monocular color images.

[1]  Linda G. Shapiro,et al.  Unsupervised Template Learning for Fine-Grained Object Recognition , 2012, NIPS.

[2]  Vincent Lepetit,et al.  Dominant orientation templates for real-time detection of texture-less objects , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  Alexei A. Efros,et al.  Ensemble of exemplar-SVMs for object detection and beyond , 2011, 2011 International Conference on Computer Vision.

[5]  Dima Damen,et al.  Real-time Learning and Detection of 3D Texture-less Objects: A Scalable Approach , 2012, BMVC.

[6]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[7]  Paul A. Viola,et al.  Multiple-Instance Pruning For Learning Efficient Cascade Detectors , 2007, NIPS.

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

[9]  FuaPascal,et al.  Gradient Response Maps for Real-Time Detection of Textureless Objects , 2012 .

[10]  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.

[11]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  Marko Grobelnik,et al.  Feature selection using linear classifier weights: interaction with classification models , 2004, SIGIR '04.

[13]  C. Steger.  OCCLUSION , CLUTTER , AND ILLUMINATION INVARIANT OBJECT RECOGNITION , 2002 .

[14]  Dariu Gavrila,et al.  Real-time object detection for "smart" vehicles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.