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: A mobile phone based system, DietCam, to help assess food intakes with few human interventions, which only requires users to take three images or a short video around the meal, then it will do the rest.
230 citations
07 Sep 2015
TL;DR: Experimental results show that Vigil allows a video surveillance system to support a geographical area of coverage between five and 200 times greater than an approach that simply streams video over the wireless network.
Abstract: Internet-enabled cameras pervade daily life, generating a huge amount of data, but most of the video they generate is transmitted over wires and analyzed offline with a human in the loop. The ubiquity of cameras limits the amount of video that can be sent to the cloud, especially on wireless networks where capacity is at a premium. In this paper, we present Vigil, a real-time distributed wireless surveillance system that leverages edge computing to support real-time tracking and surveillance in enterprise campuses, retail stores, and across smart cities. Vigil intelligently partitions video processing between edge computing nodes co-located with cameras and the cloud to save wireless capacity, which can then be dedicated to Wi-Fi hotspots, offsetting their cost. Novel video frame prioritization and traffic scheduling algorithms further optimize Vigil's bandwidth utilization. We have deployed Vigil across three sites in both whitespace and Wi-Fi networks. Depending on the level of activity in the scene, experimental results show that Vigil allows a video surveillance system to support a geographical area of coverage between five and 200 times greater than an approach that simply streams video over the wireless network. For a fixed region of coverage and bandwidth, Vigil outperforms the default equal throughput allocation strategy of Wi-Fi by delivering up to 25% more objects relevant to a user's query.
230 citations
09 May 2011
TL;DR: This work defines a view-to-object distance where a novel view is compared simultaneously to all views of a previous object, and shows that this measure leads to superior classification performance on object category and instance recognition.
Abstract: In this work we address joint object category and instance recognition in the context of RGB-D (depth) cameras. Motivated by local distance learning, where a novel view of an object is compared to individual views of previously seen objects, we define a view-to-object distance where a novel view is compared simultaneously to all views of a previous object. This novel distance is based on a weighted combination of feature differences between views. We show, through jointly learning per-view weights, that this measure leads to superior classification performance on object category and instance recognition. More importantly, the proposed distance allows us to find a sparse solution via Group-Lasso regularization, where a small subset of representative views of an object is identified and used, with the rest discarded. This significantly reduces computational cost without compromising recognition accuracy. We evaluate the proposed technique, Instance Distance Learning (IDL), on the RGB-D Object Dataset, which consists of 300 object instances in 51 everyday categories and about 250,000 views of objects with both RGB color and depth. We empirically compare IDL to several alternative state-of-the-art approaches and also validate the use of visual and shape cues and their combination.
229 citations
Cites methods from "Object recognition from local scale..."
...To capture the visual appearance of a view, we extract SIFT [17] on a dense grid of 8×8 cells....
[...]
...We perform PCA on each cell and take the first 300 components, giving a 1500-dimensional EMK SIFT feature vector....
[...]
...Then we divide the image into a 2 × 2 grid and compute EMK features separately in each cell from only the SIFT features inside the cell....
[...]
...First we compute a 1000-dimensional EMK feature using SIFT descriptors from the entire image....
[...]
TL;DR: It is clear that artificial structures can pave the way and act as stepping stones or even corridors for some marine aliens, as do urban areas, roads and riparian environments in terrestrial ecosystems.
Abstract: Marine aliens are non-native species that have been transported across major geographical barriers by human activities, involving vectors that move propagules along pathways. Species may also be newly observed in a geographical area due to range shifts, generally in association with climate change. Artificial structures are considered to be either man-made materials or natural materials shaped or displaced to serve a specific function for human activities. All types of artificial structures are currently increasing dramatically in coastal zones due to increasing human populations on coastlines. Most of the significant marine vectors and pathways involve mobile artificial structures and are reviewed here. These include shipping (ballast water and hull fouling) and aquaculture, including stock transfer and unintentional introductions, all of which can move species into new biogeographical provinces. Some types of structures frequently move long distances but have low fouling loads (e.g., commercial shipping), whereas others (e.g., barges and pontoons) can be hyperfouled due to long stationary periods such that when moved they transport mature fouling communities. We also examine the presence of alien marine species on static (immobile) artificial structures, which support different communities from those on natural hard substrata. We consider the role of these structures, such as coastal defences, artificial reefs, and offshore platforms, in the dispersal and abundance of alien species. Marinas include both mobile and immobile structures and are apparently particularly favourable habitats for many aliens. For example, in coastal North America approximately 90% of the alien species inhabiting hard substrata have been reported from docks and marinas. Detailed case studies of alien marine species (two seaweeds and four invertebrates) are provided, with an analysis of their origin, vectors of transport, habitat in the introduced range, and potential impact. Although there are exceptions, a large majority of marine alien species seem to be associated, at least for some of the time, with artificial structures. It is clear that artificial structures can pave the way and act as stepping stones or even corridors for some marine aliens, as do urban areas, roads and riparian environments in terrestrial ecosystems. The observed acceleration of spread rates for marine invasions over the course of the last two centuries may partly be a result of the increase of artificial structures in coastal environments coupled with greater activity of vectors.
229 citations
Cites methods from "Object recognition from local scale..."
...627 SIFT is an algorithm employed in computer imaging used to detect and describe 628 local features in images (Lowe 1999)....
[...]
13 Jan 2006
TL;DR: In this paper, an efficient data structure for both, the detector and the descriptor is proposed, where the detector is based on orientation histograms, which is accelerated by the use of an integral orientation histogram.
Abstract: We propose a considerably faster approximation of the well known SIFT method. The main idea is to use efficient data structures for both, the detector and the descriptor. The detection of interest regions is considerably speed-up by using an integral image for scale space computation. The descriptor which is based on orientation histograms, is accelerated by the use of an integral orientation histogram. We present an analysis of the computational costs comparing both parts of our approach to the conventional method. Extensive experiments show a speed-up by a factor of eight while the matching and repeatability performance is decreased only slightly.
228 citations
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....
[...]