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
13 Jun 2010
TL;DR: It is shown that grouplets are more effective in classifying and detecting human-object interactions than other state-of-the-art methods and can make a robust distinction between humans playing the instruments and humans co-occurring with the instruments without playing.
Abstract: Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable a computer to do this is however a challenging task. Take people-playing-musical-instrument (PPMI) as an example; to distinguish a person playing violin from a person just holding a violin requires subtle distinction of characteristic image features and feature arrangements that differentiate these two scenes. Most of the existing image representation methods are either too coarse (e.g. BoW) or too sparse (e.g. constellation models) for performing this task. In this paper, we propose a new image feature representation called “grouplet”. The grouplet captures the structured information of an image by encoding a number of discriminative visual features and their spatial configurations. Using a dataset of 7 different PPMI activities, we show that grouplets are more effective in classifying and detecting human-object interactions than other state-of-the-art methods. In particular, our method can make a robust distinction between humans playing the instruments and humans co-occurring with the instruments without playing.
393 citations
Cites methods from "Object recognition from local scale..."
...We propose a novel data mining algorithm for discovering discriminative grouplets....
[...]
27 Jun 2004
TL;DR: This work describes a learning based method for recovering 3D human body pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes, and results are a factor of 3 better than the current state of the art for the much simpler upper body problem.
Abstract: We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body pans in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogram-of-shape-contexts descriptors. For the main regression, we evaluate both regularized least squares and relevance vector machine (RVM) regressors over both linear and kernel bases. The RVM's provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. For realism and good generalization with respect to viewpoints, we train the regressors on images resynthesized from real human motion capture data, and test it both quantitatively on similar independent test data, and qualitatively on a real image sequence. Mean angular errors of 6-7 degrees are obtained - a factor of 3 better than the current state of the art for the much simpler upper body problem.
393 citations
Cites background from "Object recognition from local scale..."
...mation is a good way to encode local shape robustly [8, 3]....
[...]
26 Dec 2007
TL;DR: Spatial-LTM represents an image containing objects in a hierarchical way by over-segmented image regions of homogeneous appearances and the salient image patches within the regions, enforcing the spatial coherency of the model.
Abstract: We present a novel generative model for simultaneously recognizing and segmenting object and scene classes. Our model is inspired by the traditional bag of words representation of texts and images as well as a number of related generative models, including probabilistic latent semantic analysis (pLSA) and latent Dirichlet allocation (LDA). A major drawback of the pLSA and LDA models is the assumption that each patch in the image is independently generated given its corresponding latent topic. While such representation provides an efficient computational method, it lacks the power to describe the visually coherent images and scenes. Instead, we propose a spatially coherent latent topic model (spatial-LTM). Spatial-LTM represents an image containing objects in a hierarchical way by over-segmented image regions of homogeneous appearances and the salient image patches within the regions. Only one single latent topic is assigned to the image patches within each region, enforcing the spatial coherency of the model. This idea gives rise to the following merits of spatial-LTM: (1) spatial-LTM provides a unified representation for spatially coherent bag of words topic models; (2) spatial-LTM can simultaneously segment and classify objects, even in the case of occlusion and multiple instances; and (3) spatial-LTM can be trained either unsupervised or supervised, as well as when partial object labels are provided. We verify the success of our model in a number of segmentation and classification experiments.
392 citations
Cites methods from "Object recognition from local scale..."
...It is worth mentioning that our model is not tied to a specific segmentation algorithm....
[...]
...In Section 3.1 we introduce the framework of Winn and Bishop’s Variational Message Passing (VMP) for our variational estimation [29]....
[...]
Posted Content•
TL;DR: YOLO as discussed by the authors predicts bounding boxes and class probabilities directly from full images in one evaluation, which can be optimized end-to-end directly on detection performance, and achieves state-of-the-art performance.
Abstract: We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.
Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.
390 citations
19 May 2016
TL;DR: In this article, the authors present a review of the state of the art on using Structure-from-Motion (SfM) workflows in geomorphometry and give an overview of terms and fields of application.
Abstract: . Photogrammetry and geosciences have been closely linked since the late 19th century due to the acquisition of high-quality 3-D data sets of the environment, but it has so far been restricted to a limited range of remote sensing specialists because of the considerable cost of metric systems for the acquisition and treatment of airborne imagery. Today, a wide range of commercial and open-source software tools enable the generation of 3-D and 4-D models of complex geomorphological features by geoscientists and other non-experts users. In addition, very recent rapid developments in unmanned aerial vehicle (UAV) technology allow for the flexible generation of high-quality aerial surveying and ortho-photography at a relatively low cost. The increasing computing capabilities during the last decade, together with the development of high-performance digital sensors and the important software innovations developed by computer-based vision and visual perception research fields, have extended the rigorous processing of stereoscopic image data to a 3-D point cloud generation from a series of non-calibrated images. Structure-from-motion (SfM) workflows are based upon algorithms for efficient and automatic orientation of large image sets without further data acquisition information, examples including robust feature detectors like the scale-invariant feature transform for 2-D imagery. Nevertheless, the importance of carrying out well-established fieldwork strategies, using proper camera settings, ground control points and ground truth for understanding the different sources of errors, still needs to be adapted in the common scientific practice. This review intends not only to summarise the current state of the art on using SfM workflows in geomorphometry but also to give an overview of terms and fields of application. Furthermore, this article aims to quantify already achieved accuracies and used scales, using different strategies in order to evaluate possible stagnations of current developments and to identify key future challenges. It is our belief that some lessons learned from former articles, scientific reports and book chapters concerning the identification of common errors or "bad practices" and some other valuable information may help in guiding the future use of SfM photogrammetry in geosciences.
389 citations
Cites methods from "Object recognition from local scale..."
...In depth descriptions of SIFT and SURF are given by Lowe (1999) and Bay (2008)....
[...]
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....
[...]