Proceedings ArticleDOI
Object recognition from local scale-invariant features
David G. Lowe
- Vol. 2, pp 1150-1157
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.Abstract:Â
An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.read more
Citations
More filters
Posted Content
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Haoran Tang,Rein Houthooft,Davis Foote,Adam Stooke,Xi Chen,Yan Duan,John Schulman,Filip De Turck,Pieter Abbeel +8 more
TL;DR: A simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks, and is found that simple hash functions can achieve surprisingly good results on many challenging tasks.
Proceedings Article
Distributional Semantics in Technicolor
TL;DR: While visual models with state-of-the-art computer vision techniques perform worse than textual models in general tasks, they are as good or better models of the meaning of words with visual correlates such as color terms, even in a nontrivial task that involves nonliteral uses of such words.
Proceedings ArticleDOI
Nonparametric scene parsing: Label transfer via dense scene alignment
TL;DR: Compared to existing object recognition approaches that require training for each object category, the proposed nonparametric scene parsing system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.
Posted Content
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
TL;DR: In this paper, a factorized spatio-temporal convolutional networks (FstCN) is proposed to factorize the original 3D convolution kernel learning as a sequential process of learning 2D spatial kernels in the lower layers, followed by learning 1D temporal kernel in the upper layers.
Proceedings ArticleDOI
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation
Thomas Berg,Peter N. Belhumeur +1 more
TL;DR: A method to automatically learn a large and diverse set of highly discriminative intermediate features that are called Part-based One-vs-One Features (POOFs), each of these features specializes in discrimination between two particular classes based on the appearance at a particular part.
References
More filters
Journal ArticleDOI
Color indexing
Michael J. Swain,Dana H. Ballard +1 more
TL;DR: In this paper, color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models, and they can differentiate among a large number of objects.
Journal ArticleDOI
Generalizing the hough transform to detect arbitrary shapes
TL;DR: It is shown how the boundaries of an arbitrary non-analytic shape can be used to construct a mapping between image space and Hough transform space, which makes the generalized Houghtransform a kind of universal transform which can beused to find arbitrarily complex shapes.
Journal ArticleDOI
Visual learning and recognition of 3-D objects from appearance
Hiroshi Murase,Shree K. Nayar +1 more
TL;DR: A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
Journal ArticleDOI
Local grayvalue invariants for image retrieval
Cordelia Schmid,Roger Mohr +1 more
TL;DR: This paper addresses the problem of retrieving images from large image databases with a method based on local grayvalue invariants which are computed at automatically detected interest points and allows for efficient retrieval from a database of more than 1,000 images.
Journal ArticleDOI
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry
TL;DR: A robust approach to image matching by exploiting the only available geometric constraint, namely, the epipolar constraint, is proposed and a new strategy for updating matches is developed, which only selects those matches having both high matching support and low matching ambiguity.