Object Classification from Shape Detection

We evaluate the problem of object detection and classification based on a single model for five diverse classes. The class detection problem is implemented by enabling a method which detects the presence or absence of every shape-based model in every instance of a class. Low-level feature extraction is also performed to facilitate object categorization on one-dimensional information of the dataset. We compute the categorization performance for both the modalities in separate as well as combined representations to produce improved experimental results. The combined obtained solutions provide a classification of the object into the five classes. We have evaluated our approach on the ETHZ dataset and found that it performs with an accuracy of 88.2% in classification based on object detection.

[1]  Ronen Basri,et al.  Determining the similarity of deformable shapes , 1998, Vision Research.

[2]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Björn Stenger,et al.  Shape context and chamfer matching in cluttered scenes , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Andrea Salgian,et al.  A cubist approach to object recognition , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[5]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[6]  Jonathan T. Barron,et al.  Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Zhou Wang,et al.  Multi-scale structural similarity for image quality assessment , 2003 .

[9]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[10]  B. S. Manjunath,et al.  Introduction to MPEG-7: Multimedia Content Description Interface , 2002 .

[11]  Bernt Schiele,et al.  Pedestrian detection in crowded scenes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

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

[14]  Cordelia Schmid,et al.  Bandit Algorithms for Tree Search , 2007, UAI.

[15]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).