Object recognition from local scale-invariant features
- D. Lowe
- Computer ScienceProceedings of the Seventh IEEE International…
- 20 September 1999
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Distinctive Image Features from Scale-Invariant Keypoints
- D. Lowe
- Computer ScienceInternational Journal of Computer Vision
- 1 November 2004
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Unsupervised Learning of Depth and Ego-Motion from Video
- Tinghui Zhou, Matthew A. Brown, Noah Snavely, D. Lowe
- Computer ScienceComputer Vision and Pattern Recognition
- 25 April 2017
Empirical evaluation demonstrates the effectiveness of the unsupervised learning framework for monocular depth performs comparably with supervised methods that use either ground-truth pose or depth for training, and pose estimation performs favorably compared to established SLAM systems under comparable input settings.
Automatic Panoramic Image Stitching using Invariant Features
This work forms stitching as a multi-image matching problem, and uses invariant local features to find matches between all of the images, and is insensitive to the ordering, orientation, scale and illumination of the input images.
Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration
A system that answers the question, “What is the fastest approximate nearest-neighbor algorithm for my data?” and a new algorithm that applies priority search on hierarchical k-means trees, which is found to provide the best known performance on many datasets.
Scalable Nearest Neighbor Algorithms for High Dimensional Data
It is shown that the optimal nearest neighbor algorithm and its parameters depend on the data set characteristics and an automated configuration procedure for finding the best algorithm to search a particular data set is described.
Shape indexing using approximate nearest-neighbour search in high-dimensional spaces
This paper shows that a new variant of the k-d tree search algorithm makes indexing in higher-dimensional spaces practical, and is integrated into a fully developed recognition system, which is able to detect complex objects in real, cluttered scenes in just a few seconds.
Perceptual organization and visual recognition
- D. Lowe
- Computer Science
- 14 February 2012
Spatial organization and recognition are shown to be a practical basis for current systems and to provide a promising path for further development of improved visual capabilities.
Three-Dimensional Object Recognition from Single Two-Dimensional Images
- D. Lowe
- Computer ScienceArtificial Intelligence
- 1 March 1987
Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields
This work investigates the role of sparsity and localized features in a biologically-inspired model of visual object classification and demonstrates the value of retaining some position and scale information above the intermediate feature level.