Object recognition from local scale-invariant features
20 Sep 1999-Vol. 2, pp 1150-1157
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Abstract: 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.
Citations
More filters
TL;DR: In this paper, the impact of image filtering and skipping features detected at the highest scales on the performance of SIFT operator for SAR image registration is analyzed based on multisensor, multitemporal and different viewpoint SAR images.
Abstract: The SIFT operator's success for computer vision applications makes it an attractive alternative to the intricate feature based SAR image registration problem. The SIFT operator processing chain is capable of detecting and matching scale and affine invariant features. For SAR images, the operator is expected to detect stable features at lower scales where speckle influence diminishes. To adapt the operator performance to SAR images we analyse the impact of image filtering and of skipping features detected at the highest scales. We present our analysis based on multisensor, multitemporal and different viewpoint SAR images. The operator shows potential to become a robust alternative for point feature based registration of SAR images as subpixel registration consistency was achieved for most of the tested datasets. Our findings indicate that operator performance in terms of repeatability and matching capability is affected by an increase in acquisition differences within the imagery. We also show that the proposed adaptations result in a significant speed-up compared to the original SIFT operator.
140 citations
Cites background or methods from "Object recognition from local scale..."
...A few examples are: l object recognition (Lowe 1999); l robot localization and mapping (Se et al. 2001); l panorama stitching (Brown and Lowe 2003)....
[...]
...The SIFT operator is a feature detector introduced in 1999 and improved in 2004 by Lowe (1999, 2004)....
[...]
...2.5 Matching Even though the main SIFT operator objective is to detect stable keypoints, Lowe (1999) also proposed a matching strategy for the keypoints....
[...]
19 Apr 2017
TL;DR: KeystoneML is presented, a system that captures and optimizes the end-to-end large-scale machine learning applications for high-throughput training in a distributed environment with a high-level API that offers increased ease of use and higher performance over existing systems for large scale learning.
Abstract: Modern advanced analytics applications make use of machine learning techniques and contain multiple steps of domain-specific and general-purpose processing with high resource requirements. We present KeystoneML, a system that captures and optimizes the end-to-end large-scale machine learning applications for high-throughput training in a distributed environment with a high-level API. This approach offers increased ease of use and higher performance over existing systems for large scale learning. We demonstrate the effectiveness of KeystoneML in achieving high quality statistical accuracy and scalable training using real world datasets in several domains.
139 citations
Cites methods from "Object recognition from local scale..."
...KeystoneML makes it easy to modularize the pipeline to use efficient implementations of image processing operators like SIFT [38] and Fisher Vectors [52, 11]....
[...]
...When memory is not unconstrained (80 GB per node), the outputs from the SIFT, ReduceDimensions, Normalize and TrainingLabels are cached....
[...]
Journal Article•
TL;DR: By showing how place recognition along a route is feasible even with severely degraded image sequences, this paper hopes to provoke a re-examination of how to develop and test future localization and mapping systems.
Abstract: In this paper we use the algorithm SeqSLAM to address the question, how little and what quality of visual information is needed to localize along a familiar route? We conduct a comprehensive investigation of place recognition performance on seven datasets while varying image resolution (primarily 1 to 512 pixel images), pixel bit depth, field of view, motion blur, image compression and matching sequence length. Results confirm that place recognition using single images or short image sequences is poor, but improves to match or exceed current benchmarks as the matching sequence length increases. We then present place recognition results from two experiments where low-quality imagery is directly caused by sensor limitations; in one, place recognition is achieved along an unlit mountain road by using noisy, long-exposure blurred images, and in the other, two single pixel light sensors are used to localize in an indoor environment. We also show failure modes caused by pose variance and sequence aliasing, and discuss ways in which they may be overcome. By showing how place recognition along a route is feasible even with severely degraded image sequences, we hope to provoke a re-examination of how we develop and test future localization and mapping systems.
139 citations
Cites background from "Object recognition from local scale..."
...The SeqSLAM algorithm attempts to match route segments rather than individual images, and is similar in concept to work by Newman et al. (2006), in which loop closure was performed by comparing sequences of images based on the similarity of 128D vectors of SIFT descriptors....
[...]
...Many of the state of the art feature detectors such as scale-invariant feature transforms (SIFT) (Lowe, 1999) and speeded up robust features (SURF) (Bay et al....
[...]
...Many of the state of the art feature detectors such as scale-invariant feature transforms (SIFT) (Lowe, 1999) and speeded up robust features (SURF) (Bay et al., 2006) exhibit desirable properties such as scale and rotation invariance, and a limited degree of illumination invariance....
[...]
TL;DR: This study presents a computer vision application of the structure from motion technique in three dimensional high resolution gully monitoring in southern Morocco and demonstrates the advantages of SfM for soil erosion monitoring under complex surface conditions.
Abstract: This study presents a computer vision application of the structure from motion (SfM) technique in three dimensional high resolution gully monitoring in southern Morocco Due to impractical use of terrestrial Light Detection and Ranging (LiDAR) in difficult to access gully systems, the inexpensive SfM is a promising tool for analyzing and monitoring soil loss, gully head retreat and plunge pool development following heavy rain events Objects with known dimensions were placed around the gully scenes for scaling purposes as a workaround for ground control point (GCP) placement Additionally, the free scaling with objects was compared to terrestrial laser scanner (TLS) data in a field laboratory in Germany Results of the latter showed discrepancies of 56% in volume difference for erosion and 17% for accumulation between SfM and TLS In the Moroccan research area soil loss varied between 058 t in an 1865 m2 narrowly stretched gully incision and 525 t for 1745 m2 in a widely expanded headcut area following two heavy rain events Different techniques of data preparation were applied and the advantages of SfM for soil erosion monitoring under complex surface conditions were demonstrated
139 citations
Cites methods from "Object recognition from local scale..."
...their respective 3D locations is realized by a Scale-Invariant Feature Transform (SIFT) algorithm [31] in open source software....
[...]
TL;DR: This paper reviews almost three decades of methods for 3D histology reconstruction from serial sections, used in the study of many different types of tissue, and attempts to identify the trends and challenges that the field is facing.
138 citations
Cites background from "Object recognition from local scale..."
...It is based on local extrema (or blob) detection (Lowe, 1999)....
[...]
References
More filters
[...]
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.
Abstract: Computer vision is moving into a new era in which the aim is to develop visual skills for robots that allow them to interact with a dynamic, unconstrained environment. To achieve this aim, new kinds of vision algorithms need to be developed which run in real time and subserve the robot's goals. Two fundamental goals are determining the identity of an object with a known location, and determining the location of a known object. Color can be successfully used for both tasks.
This dissertation demonstrates that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models. It shows that color histograms are stable object representations in the presence of occlusion and over change in view, and that they can differentiate among a large number of objects. For solving the identification problem, it introduces a technique called Histogram Intersection, which matches model and image histograms and a fast incremental version of Histogram Intersection which allows real-time indexing into a large database of stored models. It demonstrates techniques for dealing with crowded scenes and with models with similar color signatures. For solving the location problem it introduces an algorithm called Histogram Backprojection which performs this task efficiently in crowded scenes.
5,672 citations
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.
4,310 citations
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.
Abstract: The problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties and constant for a rigid object, pose and illumination vary from scene to scene. A compact representation of object appearance is proposed that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a manifold. Given an unknown input image, the recognition system projects the image to eigenspace. The object is recognized based on the manifold it lies on. The exact position of the projection on the manifold determines the object's pose in the image. A variety of experiments are conducted using objects with complex appearance characteristics. The performance of the recognition and pose estimation algorithms is studied using over a thousand input images of sample objects. Sensitivity of recognition to the number of eigenspace dimensions and the number of learning samples is analyzed. For the objects used, appearance representation in eigenspaces with less than 20 dimensions produces accurate recognition results with an average pose estimation error of about 1.0 degree. A near real-time recognition system with 20 complex objects in the database has been developed. The paper is concluded with a discussion on various issues related to the proposed learning and recognition methodology.
2,037 citations
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.
Abstract: This paper addresses the problem of retrieving images from large image databases. The method is based on local grayvalue invariants which are computed at automatically detected interest points. A voting algorithm and semilocal constraints make retrieval possible. Indexing allows for efficient retrieval from a database of more than 1,000 images. Experimental results show correct retrieval in the case of partial visibility, similarity transformations, extraneous features, and small perspective deformations.
1,756 citations
"Object recognition from local scale..." refers background or methods in this paper
...This allows for the use of more distinctive image descriptors than the rotation-invariant ones used by Schmid and Mohr, and the descriptor is further modified to improve its stability to changes in affine projection and illumination....
[...]
...For the object recognition problem, Schmid & Mohr [19] also used the Harris corner detector to identify interest points, and then created a local image descriptor at each interest point from an orientation-invariant vector of derivative-of-Gaussian image measurements....
[...]
..., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
...However, recent research on the use of dense local features (e.g., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
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.
1,574 citations
"Object recognition from local scale..." refers methods in this paper
...[23] used the Harris corner detector to identify feature locations for epipolar alignment of images taken from differing viewpoints....
[...]