Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
An Efficient Solution to the Five-Point Relative Pose Problem
IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Photo tourism: exploring photo collections in 3D
ACM SIGGRAPH 2006 Papers
RANSAC for (Quasi-)Degenerate data (QDEGSAC)
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
International Journal of Computer Vision
Scene completion using millions of photographs
ACM SIGGRAPH 2007 papers
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Detecting and identifying people in mobile videos
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Bilinear deep learning for image classification
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Landmark recognition and retrieval: from 2D to 3D
J-HGBU '11 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding
Hi-index | 0.00 |
Most of the existing approaches for landmark image classification utilize either holistic features or interest of points in the whole image to train the classification model, which may lead to unsatisfactory result due to involvement of much information non-located on the landmark in the training process. In this paper, we propose a novel approach to improve landmark image classification result via a process of 2D to 3D reconstruction and 3D to 2D projection of iconic landmark images. Particularly, we first select iconic images from labeled landmark image collections to reconstruct a 3D landmark represented in point clouds. Then, 3D point clouds are projected back onto the same iconic images to obtain the landmark-region of each iconic image and subsequently extract SIFT features from the landmark-region to construct a k-dimensional tree (kd-tree) for each landmark. This process is able to filter out noise points corresponding to clutter background and non-landmark objects in the iconic images. Finally, the unlabeled images can be classified into predefined landmark categories based on the amount of matched feature points between the image features and the kd-trees. The experimental result and comparison with the state-of-the-art demonstrate the effectiveness of our approach.