Object Detection and Localization Using Random Forest

In this paper, we present a method for object detection and localization using the technique of random forest. In the process of supervised learning to construct random forest, we use the descriptor vectors of the SIFT features as input samples and their class information as supervised information. For each leaf node of the decision tree, the offsets of local features reach this node along with their class information, and the class information of this node are stored. Therefore, all leaf nodes construct a discriminative tree-structured codebook model. In object detection, the discriminative codebook is used to estimate the object's location via a probabilistic computation called probabilistic Hough vote. The experimental results show that our algorithm can provide a better detection results even in the complicated environment such as multi-scale, multi-perspective, occlusion and strong background noise.

[1]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[2]  B. Schiele,et al.  Combined Object Categorization and Segmentation With an Implicit Shape Model , 2004 .

[3]  Vincent Lepetit,et al.  Randomized trees for real-time keypoint recognition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.

[5]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[6]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[7]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Frédéric Jurie,et al.  Fast Discriminative Visual Codebooks using Randomized Clustering Forests , 2006, NIPS.

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

[11]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[12]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Jitendra Malik,et al.  Object detection using a max-margin Hough transform , 2009, CVPR.

[15]  Jitendra Malik,et al.  Shape Context: A New Descriptor for Shape Matching and Object Recognition , 2000, NIPS.

[16]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[17]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[18]  Antonio Criminisi,et al.  Object Class Segmentation using Random Forests , 2008, BMVC.

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

[20]  Florent Perronnin,et al.  Universal and Adapted Vocabularies for Generic Visual Categorization , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Pietro Perona,et al.  Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition , 2007, International Journal of Computer Vision.