Incremental Linear Discriminant Analysis Using Sufficient Spanning Sets and Its Applications

This paper presents an incremental learning solution for Linear Discriminant Analysis (LDA) and its applications to object recognition problems. We apply the sufficient spanning set approximation in three steps i.e. update for the total scatter matrix, between-class scatter matrix and the projected data matrix, which leads an online solution which closely agrees with the batch solution in accuracy while significantly reducing the computational complexity. The algorithm yields an efficient solution to incremental LDA even when the number of classes as well as the set size is large. The incremental LDA method has been also shown useful for semi-supervised online learning. Label propagation is done by integrating the incremental LDA into an EM framework. The method has been demonstrated in the task of merging large datasets which were collected during MPEG standardization for face image retrieval, face authentication using the BANCA dataset, and object categorisation using the Caltech101 dataset. © 2010 Springer Science+Business Media, LLC.

Multiscale object features from clustered complex wavelet coefficients

This paper introduces a method by which intuitive feature entities can be created from ILP (InterLevel Product) coefficients. The ILP transform is a pyramid of decimated complex-valued coefficients at multiple scales, derived from dual-tree complex wavelets, whose phases indicate the presence of different feature types (edges and ridges). We use an Expectation-Maximization algorithm to cluster large ILP coefficients that are spatially adjacent and similar in phase. We then demonstrate the relationship that these clusters possess with respect to observable image content, and conclude with a look at potential applications of these clusters, such as rotation- and scale-invariant object recognition. © 2005 IEEE.

A new distance for scale-invariant 3D shape recognition and registration

This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for the first time. We introduce a new distance between poses in this spacethe SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form mean, in contrast to Riemannian distance, so is fast to compute. We demonstrate improved performance over the state of the art in both recognition and registration on a real and challenging dataset, by comparing our distance with others in a mean shift framework, as well as with the commonly used Hough voting approach. © 2011 IEEE.

Large Scale Column Detection for Bridge Inspection

Manually inspecting bridges is a time-consuming and costly task. There are over 600,000 bridges in the US, and not all of them can be inspected and maintained within the specified time frame as some state DOTs cannot afford the essential costs and manpower. This paper presents a novel method that can detect bridge concrete columns from visual data for the purpose of eventually creating an automated bridge condition assessment system. The method employs SIFT feature detection and matching to find overlapping areas among images. Affine transformation matrices are then calculated to combine images containing different segments of one column into a single image. Following that, the bridge columns are detected by identifying the boundaries in the stitched image and classifying the material within each boundary. Preliminary test results using real bridge images indicate that most columns in stitched images can be correctly detected and thus, the viability of the application of this research.

Enhancement of Construction Equipment Detection in Video Frames by Combining with Tracking

Vision-based object detection has been introduced in construction for recognizing and locating construction entities in on-site camera views. It can provide spatial locations of a large number of entities, which is beneficial in large-scale, congested construction sites. However, even a few false detections prevent its practical applications. In resolving this issue, this paper presents a novel hybrid method for locating construction equipment that fuses the function of detection and tracking algorithms. This method detects construction equipment in the video view by taking advantage of entities' motion, shape, and color distribution. Background subtraction, Haar-like features, and eigen-images are used for motion, shape, and color information, respectively. A tracking algorithm steps in the process to make up for the false detections. False detections are identified by catching drastic changes in object size and appearance. The identified false detections are replaced with tracking results. Preliminary experiments show that the combination with tracking has the potential to enhance the detection performance.

Achievements and Challenges in Recognizing and Reconstructing Civil Infrastructure

The US National Academy of Engineering recently identified restoring and improving urban infrastructure as one of the grand challenges of engineering. Part of this challenge stems from the lack of viable methods to map/label existing infrastructure. For computer vision, this challenge becomes “How can we automate the process of extracting geometric, object oriented models of infrastructure from visual data?” Object recognition and reconstruction methods have been successfully devised and/or adapted to answer this question for small or linear objects (e.g. columns). However, many infrastructure objects are large and/or planar without significant and distinctive features, such as walls, floor slabs, and bridge decks. How can we recognize and reconstruct them in a 3D model? In this paper, strategies for infrastructure object recognition and reconstruction are presented, to set the stage for posing the question above and discuss future research in featureless, large/planar object recognition and modeling.

Synchronization of user-generated videos through trajectory correspondence and a refinement procedure

Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied through the time-stamp information embedded in the video streams. User-generated videos shot using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. Our first contribution is a synchronization technique which tries to establish correspondence between feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. We evaluate performance using a number of real video recordings and show that our method is able to synchronize to within 1 sec, which is significantly better than previous approaches. Our second contribution is a robust and unsupervised view-invariant activity recognition descriptor that exploits recurrence plot theory on spatial tiles. The descriptor is individually shown to better characterize the activities from different views under occlusions than state-of-the-art approaches. We combine this descriptor with our proposed synchronization method and show that it can further refine the synchronization index. © 2013 ACM.

Robust recognition of chess-boards under deformation

Current methods for formation of detected chess-board vertices into a grid structure tend to be weak in situations with a warped grid, and false and missing vertex-features. In this paper we present a highly robust, yet efficient, scheme suitable for inference of regular 2D square mesh structure from vertices recorded both during projection of a chess-board pattern onto 3D objects, and in the more simple case of camera calibration. Examples of the method's performance in a lung function measuring application, observing chess-boards projected on to patients' chests, are given. The method presented is resilient to significant surface deformation, and tolerates inexact vertex-feature detection. This robustness results from the scheme's novel exploitation of feature orientation information. © 2013 IEEE.

Semantic transform: Weakly supervised semantic inference for relating visual attributes

Relative (comparative) attributes are promising for thematic ranking of visual entities, which also aids in recognition tasks. However, attribute rank learning often requires a substantial amount of relational supervision, which is highly tedious, and apparently impractical for real-world applications. In this paper, we introduce the Semantic Transform, which under minimal supervision, adaptively finds a semantic feature space along with a class ordering that is related in the best possible way. Such a semantic space is found for every attribute category. To relate the classes under weak supervision, the class ordering needs to be refined according to a cost function in an iterative procedure. This problem is ideally NP-hard, and we thus propose a constrained search tree formulation for the same. Driven by the adaptive semantic feature space representation, our model achieves the best results to date for all of the tasks of relative, absolute and zero-shot classification on two popular datasets. © 2013 IEEE.

Single camera pose estimation using Bayesian filtering and Kinect motion priors

Traditional approaches to upper body pose estimation using monocular vision rely on complex body models and a large variety of geometric constraints. We argue that this is not ideal and somewhat inelegant as it results in large processing burdens, and instead attempt to incorporate these constraints through priors obtained directly from training data. A prior distribution covering the probability of a human pose occurring is used to incorporate likely human poses. This distribution is obtained offline, by fitting a Gaussian mixture model to a large dataset of recorded human body poses, tracked using a Kinect sensor. We combine this prior information with a random walk transition model to obtain an upper body model, suitable for use within a recursive Bayesian filtering framework. Our model can be viewed as a mixture of discrete Ornstein-Uhlenbeck processes, in that states behave as random walks, but drift towards a set of typically observed poses. This model is combined with measurements of the human head and hand positions, using recursive Bayesian estimation to incorporate temporal information. Measurements are obtained using face detection and a simple skin colour hand detector, trained using the detected face. The suggested model is designed with analytical tractability in mind and we show that the pose tracking can be Rao-Blackwellised using the mixture Kalman filter, allowing for computational efficiency while still incorporating bio-mechanical properties of the upper body. In addition, the use of the proposed upper body model allows reliable three-dimensional pose estimates to be obtained indirectly for a number of joints that are often difficult to detect using traditional object recognition strategies. Comparisons with Kinect sensor results and the state of the art in 2D pose estimation highlight the efficacy of the proposed approach.

具有训练、学习和零件识别能力的计算机视觉系统

本文提出的系统主要为了在自动化传输带上进行零件的自动识别、定位、定向。曾用该系统对三十多种钟表零件进行反复验证,效果甚佳。

知觉组织在拥挤现象中的作用

Crowding, generally defined as the deleterious influence of nearby contours on visual discrimination, is ubiquitous in spatial vision. Specifically, long-range effects of non-overlapping distracters can alter the appearance of an object, making it unrecognizable. Theories in many domains, including vision computation and high-level attention, have been proposed to account for crowding. However, neither compulsory averaging model nor insufficient spatial esolution of attention provides an adequate explanation for crowding. The present study examined the effects of perceptual organization on crowding. We hypothesize that target-distractor segmentation in crowding is analogous to figure-ground segregation in Gestalt. When distractors can be grouped as a whole or when they are similar to each other but different from the target, the target can be distinguished from distractors. However, grouping target and distractors together by Gestalt principles may interfere with target-distractor separation. Six experiments were carried out to assess our theory. In experiments 1, 2, and 3, we manipulated the similarity between target and distractor as well as the configuration of distractors to investigate the effects of stimuli-driven grouping on target-distractor segmentation. In experiments 4, 5, and 6, we focused on the interaction between bottom-up and top-down processes of grouping, and their influences on target-distractor segmentation. Our results demonstrated that: (a) when distractors were similar to each other but different from target, crowding was eased; (b) when distractors formed a subjective contour or were placed regularly, crowding was also reduced; (c) both bottom-up and top-down processes could influence target-distractor grouping, mediating the effects of crowding. These results support our hypothesis that the figure-ground segregation and target-distractor segmentation in crowding may share similar processes. The present study not only provides a novel explanation for crowding, but also examines the processing bottleneck in object recognition. These findings have significant implications on computer vision and interface design as well as on clinical practice in amblyopia and dyslexia.

Distance Metric Between 3D Models and 3D Images for Recognition and Classification

Similarity measurements between 3D objects and 2D images are useful for the tasks of object recognition and classification. We distinguish between two types of similarity metrics: metrics computed in image-space (image metrics) and metrics computed in transformation-space (transformation metrics). Existing methods typically use image and the nearest view of the object. Example for such a measure is the Euclidean distance between feature points in the image and corresponding points in the nearest view. (Computing this measure is equivalent to solving the exterior orientation calibration problem.) In this paper we introduce a different type of metrics: transformation metrics. These metrics penalize for the deformatoins applied to the object to produce the observed image. We present a transformation metric that optimally penalizes for "affine deformations" under weak-perspective. A closed-form solution, together with the nearest view according to this metric, are derived. The metric is shown to be equivalent to the Euclidean image metric, in the sense that they bound each other from both above and below. For Euclidean image metric we offier a sub-optimal closed-form solution and an iterative scheme to compute the exact solution.

Vectorizing Face Images by Interpreting Shape and Texture Computations

The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. This representation has two components: (1) shape, or (x, y) feature locations, and (2) texture, defined as the image grey levels mapped onto the standard reference image. This paper explores an automatic technique for "vectorizing" face images. Our face vectorizer alternates back and forth between computation steps for shape and texture, and a key idea is to structure the two computations so that each one uses the output of the other. A hierarchical coarse-to-fine implementation is discussed, and applications are presented to the problems of facial feature detection and registration of two arbitrary faces.

Surface Reflectance Estimation and Natural Illumination Statistics

Humans recognize optical reflectance properties of surfaces such as metal, plastic, or paper from a single image without knowledge of illumination. We develop a machine vision system to perform similar recognition tasks automatically. Reflectance estimation under unknown, arbitrary illumination proves highly underconstrained due to the variety of potential illumination distributions and surface reflectance properties. We have found that the spatial structure of real-world illumination possesses some of the statistical regularities observed in the natural image statistics literature. A human or computer vision system may be able to exploit this prior information to determine the most likely surface reflectance given an observed image. We develop an algorithm for reflectance classification under unknown real-world illumination, which learns relationships between surface reflectance and certain features (statistics) computed from a single observed image. We also develop an automatic feature selection method.