Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (16 results)

  • Article
  • Peer Reviewed
Technical Reports (2008)
The goal of object categorization is to locate and identify instances of an object category within an image. Recognizing an object in an image is difficult when images present occlusion, poor quality, noise or background clutter, and this task becomes even more challenging when many objects are present in the same scene. Several models for object categorization use appearance and context information from objects to improve recognition accuracy. Appearance information, based on visual cues, can successfully identify object classes up to a certain extent. Context information, based on the interaction among objects in the scene or on global scene statistics, can help successfully disambiguate appearance inputs in recognition tasks. In this work we review different approaches of using contextual information in the field of object categorization and discuss scalability, optimizations and possible future approaches.

Pre-2018 CSE ID: CS2008-0928

    Cover page: Context Based Object Categorization: A Critical Survey
    • Article
    • Peer Reviewed
    Technical Reports (2003)
    We show how to exploit temporal periodicity of moving objects to perform 3D reconstruction. The collection of period-separated frames serve as a surrogate for multiple rigid views of a particular pose of the moving target, thus allowing the use of standard techniques of multiview geometry. We motivate our approach using human motion capture data, for which the true 3D positions of the markers are known. We next apply our approach to image sequences of pedestrians captured with a camcorder. Applications of our proposed approach include 3D motion capture of natural and manmade periodic moving targets from monocular video sequences.

    Pre-2018 CSE ID: CS2003-0767

      Cover page: Structure from Periodic Motion
      • Article
      • Peer Reviewed
      Technical Reports (2003)
      Planar motion models can provide gross motion estimation and good segmentation for image pairs with large inter-frame disparity. However, as the disparity becomes larger, the resulting dense correspondences will become increasingly inaccurate for everything but purely planar objects. Flexible motion models, on the other hand, tend to overfit and thus make partitioning difficult. For this reason, to achieve dense optical flow for image sequences with large inter-frame disparity, we propose a two stage process in which a planar model is used to get an approximation for the segmentation and the gross motion, and then a spline is used to refine the fit. We present experimental results for dense optical flow estimation on image pairs with large inter-frame disparity that are beyond the scope of existing approaches.

      Pre-2018 CSE ID: CS2003-0768

        Cover page: A Feature-based Approach for Determining Dense Long Range Correspondences
        • Article
        • Peer Reviewed
        Technical Reports (2005)
        License Plate Recognition (LPR) is a fairly well explored problem and is already a component of several commercially operational systems. Many of these systems, however, require sophisticated video capture hardware possibly combined with infrared strobe lights or exploit the large size of license plates in certain geographical regions and the (artificially) high discriminability of characters. In this paper, we describe an LPR system that achieves a high recognition rate without the need for a high quality video signal from expensive hardware. We also explore the problem of car make and model recognition for purposes of searching surveillance video archives for a partial license plate number combined with some visual description of a car. Our proposed methods will provide valuable situational information for law enforcement units in a variety of civil infrastructures.

        Pre-2018 CSE ID: CS2005-0833

          Cover page: Recognizing Cars
          • Article
          • Peer Reviewed
          Technical Reports (2003)
          The thin plate spline (TPS) is an effective tool for modeling coordinate transformations that has been applied successfully in several computer vision applications. Unfortunately the solution requires the inversion of a p x p matrix, where p is the number of points in the data set, thus making it impractical for large scale applications. In practical applications, however, a surprisingly good approximate solution is often possible using only a small subset of corresponding points. We begin by discussing the obvious approach of using this subset to estimate a transformation that is then applied to all the points, and we show the drawbacks of this method. We then proceed to borrow a technique from the machine learning community for function approximation using radial basis functions (RBFs) and adapt it to the task at hand. Using this method, we demonstrate a significant improvement over the naive method. One drawback of this method, however, is that is does not allow for principal warp analysis, a technique for studying shape deformations introduced by Bookstein based on the eigenvectors of the p x p bending energy matrix. To address this, we describe a third approximation method based on a classic matrix completion technique that allows for principal warp analysis as a by-product. By means of experiments on real and synthetic data, we demonstrate the pros and cons of these different approximations so as to allow the reader to make an informed decision suited to his or her application.

          Pre-2018 CSE ID: CS2003-0764

            Cover page: Approximation Methods for Thin Plate Spline Mappings and Principal Warps
            • Article
            • Peer Reviewed
            Technical Reports (2003)
            We describe an algorithm for segmenting a novel image based on the available segmentation of another image. The algorithm consists of two stages. In the first stage we construct a locally connected graph to represent the novel image. This graph is obtained by inheriting local connectivity between pixels based on the similarity of small neighborhoods in the two images. In the second stage a graph parititioning algorithm is used to partition the graph and recover the resulting segments in the image. We present experimental results on synthetic and real images and conclude with a discussion of the strengths and limitations of the method.

            Pre-2018 CSE ID: CS2003-0762

              Cover page: Segmentation by Example
              • Thesis
              • Peer Reviewed
              UC San Diego Electronic Theses and Dissertations (2018)

              Computer vision has seen great change in the last decade, characterized by shallow machine learning models on hand-tuned features in 2010, to deep models with end-to-end learned features in 2018.

              This dissertation includes work from both the pre- and post-deep-learning periods. It includes two chapters on local descriptors - functions of local regions of images, designed to produce objects with desirable properties when compared with particular distance functions.

              The first of these chapters describes the LUCID descriptor, a descriptor designed to run quickly on devices with limited floating-point support (e.g. mobile phones circa 2012). The second describes match-time covariance, a framework for building descriptors, which delegates to the distance computation the task of ensuring rotation and scale invariance. It also describes an instance of such a descriptor. Both these descriptors were hand designed, leveraging expertise in image formation and algorithms to create functions which would extract desired image information while discarding nuisance information.

              The final project presented herein is a deep learning system for computational microscopy. It uses the paradigm of image-to-image translation to predict hard-to-acquire fluorescence images from easy-to-acquire transmitted light images, enabling biological assays which were previously impossible. In this domain, accuracy is paramount while speed is secondary, necessitating the development of a new deep learning model for the domain of image-to-image translation.

                Cover page: From local descriptors to in silico labeling
                • Article
                • Peer Reviewed
                Technical Reports (2003)
                We address the problem of tracking multiple, identical, nonrigid moving targets through occlusion for purposes of rodent surveillance from a side view. Automated behavior analysis of individual mice promises to improve animal care and data collection in medical research. In our experiments, we consider the case of three brown mice that repeatedly occlude one another and have no stable trackable features. Our proposed algorithm computes and incorporates a hint of the future location of the target into layer-based ane optical flow estimation. The hint is based on the estimated correspondences between mice in different frames derived from a depth ordering heuristic. Our approach is simple, ecient, and does not require a manually constructed mouse template. We demonstrate encouraging results on a challenging test sequence containing multiple instances of severe occlusion.

                Pre-2018 CSE ID: CS2003-0763

                  Cover page: Three Brown Mice: See How They Run
                  • Article
                  • Peer Reviewed
                  Technical Reports (2007)
                  We present a new algorithm, Locally Smooth Manifold Learning (LSML), that learns a warping function from a point on an manifold to its neighbors. Important characteristics of LSML include the ability to recover the structure of the manifold in sparsely populated regions and beyond the support of the provided data. Applications of our proposed technique include embedding with a natural out-of-sample extension and tasks such as tangent distance estimation, frame rate up-conversion, video compression and motion transfer.

                  Pre-2018 CSE ID: CS2007-0876

                    Cover page: Learning to Traverse Image Manifolds
                    • Article
                    • Peer Reviewed
                    UC San Diego Previously Published Works (2015)
                    The detection of mine-like objects (MLOs) in sidescan sonar (SSS) imagery continues to be a challenging task. In practice, subject matter experts tediously analyze images searching for MLOs. In the literature, there are many attempts at automated target recognition (ATR) to detect the MLOs. This paper focuses on the classifiers that use computer vision and machine learning approaches. These techniques require large amounts of data, which is often prohibitive. For this reason, the use of synthetic and semisynthetic data sets for training and testing is commonplace. This paper shows how a simple semisynthetic data creation scheme can be used to pretest these data-hungry training algorithms to determine what features are of value. The paper provides real-world testing and training data sets in addition to the semisynthetic training and testing data sets. The paper considers the Haar-like and local binary pattern (LBP) features with boosting, showing improvements in performance with real classifiers over semisynthetic classifiers and improvements in performance as semisynthetic data set size increases.
                      Top