The PASCAL Visual Object Classes Challenge

http://cvssp-data.eps.surrey.ac.uk/Personal/AdrianHilton/Publications_files/survey_techrep.pdf

A survey of advances in vision-based human motion capture and analysis

Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables systematic development of optimal vision algorithms when used with optimization principles. This detailed and thoroughly enhanced third edition presents a comprehensive study / reference to theories, methodologies and recent developments in solving computer vision problems based on MRFs, statistics and optimisation. It treats various problems in low- and high-level computational vision in a systematic and unified way within the MAP-MRF framework. Among the main issues covered are: how to use MRFs to encode contextual constraints that are indispensable to image understanding; how to derive the objective function for the optimal solution to a problem; and how to design computational algorithms for finding an optimal solution. Easy-to-follow and coherent, the revised edition is accessible, includes the most recent advances, and has new and expanded sections on such topics as: Discriminative Random Fields (DRF) Strong Random Fields (SRF) Spatial-Temporal Models Total Variation Models Learning MRF for Classification (motivation + DRF) Relation to Graphic Models Graph Cuts Belief Propagation Features: Focuses on the application of Markov random fields to computer vision problems, such as image restoration and edge detection in the low-level domain, and object matching and recognition in the high-level domain Presents various vision models in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation Uses a variety of examples to illustrate how to convert a specific vision problem involving uncertainties and constraints into essentially an optimization problem under the MRF setting Introduces readers to the basic concepts, important models and various special classes of MRFs on the regular image lattice and MRFs on relational graphs derived from images Examines the problems of parameter estimation and function optimization Includes an extensive list of references This broad-ranging and comprehensive volume is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition and applications of MRFs. It has been class-tested and is suitable as a textbook for advanced courses relating to these areas.

Markov Random Field Modeling in Image Analysis

From the Publisher:
Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms systematically when used with optimization principles. This book presents a comprehensive study on the use of MRFs for solving computer vision problems. The book covers the following parts essential to the subject: introduction to fundamental theories, formulations of MRF vision models, MRF parameter estimation, and optimization algorithms. Various vision models are presented in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This book is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition, and applications of MRFs. It is also suitable as a text for advanced courses in these areas.

Markov Random Field Modeling in Computer Vision

Human eyes can recognize person identities based on some small salient regions. However, such valuable salient information is often hidden when computing similarities of images with existing approaches. Moreover, many existing approaches learn discriminative features and handle drastic viewpoint change in a supervised way and require labeling new training data for a different pair of camera views. In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning. Distinctive features are extracted without requiring identity labels in the training procedure. First, we apply adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations. Second, we learn human salience in an unsupervised manner. To improve the performance of person re-identification, human salience is incorporated in patch matching to find reliable and discriminative matched patches. The effectiveness of our approach is validated on the widely used VIPeR dataset and ETHZ dataset.

/pdf/unsupervised-salience-learning-for-person-re-identification-2bduniehmd.pdf

Unsupervised Salience Learning for Person Re-identification

In this paper, we develop a novel method for view-based recognition of human action/activity from videos. By observing just a few frames, we can identify the activity that takes place in a video sequence. The basic idea of our method is that activities can be positively identified from a sparsely sampled sequence of a few body poses acquired from videos. In our approach, an activity is represented by a set of pose and velocity vectors for the major body parts (hands, legs, and torso) and stored in a set of multidimensional hash tables. We develop a theoretical foundation that shows that robust recognition of a sequence of body pose vectors can be achieved by a method of indexing and sequencing and it requires only a few pose vectors (i.e., sampled body poses in video frames). We find that the probability of false alarm drops exponentially with the increased number of sampled body poses. So, matching only a few body poses guarantees high probability for correct recognition. Our approach is parallel, i.e., all possible model activities are examined at one indexing operation. In addition, our method is robust to partial occlusion since each body part is indexed separately. We use a sequence-based voting approach to recognize the activity invariant to the activity speed.

/pdf/human-activity-recognition-using-multidimensional-indexing-2ao3tkls9j.pdf

Human activity recognition using multidimensional indexing

Discusses the application of a newly developed expansion matching method for edge detection. Expansion matching optimizes a novel matching criterion called the discriminative signal-to-noise ratio (DSNR) and has been shown to robustly recognize templates under conditions of noise, severe occlusion and superposition. The DSNR criterion is better suited to evaluate matching in practical conditions than the traditional SNR since it considers as "noise" even the off-center response of the filter to the template itself. We introduce a family of optimal DSNR edge detectors based on the expansion filter for several edge models. For step edges, the optimal DSNR step expansion filter (SEF) is compared with the widely used Canny edge detector (CED). Experimental comparisons show that our edge detector yields better performance than the CED in terms of DSNR even under very adverse noise conditions. As for boundary detection, the SEF consistently yields higher figures of merit than the CED on a synthetic binary image over a wide range of noise levels. Results also show that the design parameters of size or width of the SEF are less critical than the CED variance. This means that a single scale of the SEF spans a larger range of input noise than a single scale of the CED. Experiments on a noisy image reveal that the SEF yields less noisy edge elements and preserves structural details more accurately. On the other hand, the CED output has better suppression of multiple responses than the corresponding SEF output. >

Optimal edge detection using expansion matching and restoration

Two novel probabilistic models for viewed angles and distances are derived using an observability sphere method. The method, which is based on the assumption that the prior probability density is isotropic for all viewing orientations, can be used for the computation of observation probabilities for object's aspects, features, and probability densities of their quantitative attributes. Using the sphere, it is discovered that the probability densities of viewed angles, distances, and even projected curvature have sharp peaks at their original values. From this peaking effect, it is concluded that in most cases, the values of angles and distances are being altered only slightly by the imaging process, and they can still serve as a strong cue for model-based recognition. The probabilistic models for 3-D object recognition from monocular images are used. To form the angular elements that are needed, the objects are represented by their linear features and specific points primitives. Using the joint density model of angles and distances, the probabilities of initial matching hypotheses and mutual information coefficients are estimated. These results are then used for object recognition by optimal matching search and stochastic labeling schemes. Various synthetic and real objects are recognized by this approach. >

The probabilistic peaking effect of viewed angles and distances with application to 3-D object recognition

Describes an efficient approach to pose invariant pictorial object recognition employing spectral signatures of image patches that correspond to object surfaces which are roughly planar. Based on singular value decomposition (SVD), the affine transform is decomposed into slant, tilt, swing, scale, and 2D translation. Unlike previous log-polar representations which were not invariant to slant, our log-log sampling configuration in the frequency domain yields complete affine invariance. The images are preprocessed by a novel model-based segmentation scheme that detects and segments objects that are affine-similar to members of a model set of basic geometric shapes. The segmented objects are then recognized by their signatures using multidimensional indexing in a pictorial dataset represented in the frequency domain. Experimental results with a dataset of 26 models show 100 percent recognition rates in a wide range of 3D pose parameters and imaging degradations: 0-360/spl deg/ swing and tilt, 0-82/spl deg/ of slant, more than three octaves in scale change, window-limited translation, high noise levels (0 dB), and significantly reduced resolution (1:5).

Pictorial recognition of objects employing affine invariance in the frequency domain

A novel method for representing 3D objects that unifies viewer and model centered object representations is presented. A unified 3D frequency-domain representation, called volumetric frequency representation (VFR), encapsulates both the spatial structure of the object and a continuum of its views in the same data structure. The frequency-domain image of an object viewed from any direction can be directly extracted employing an extension of the projection slice theorem, where each Fourier-transformed view is a planar slice of the volumetric frequency representation. The VFR is employed for pose-invariant recognition of complex objects, such as faces. The recognition and pose estimation is based on an efficient matching algorithm in a four-dimensional Fourier space. Experimental examples of pose estimation and recognition of faces in various poses are also presented.

Jezekiel Ben-Arie

Papers

Human activity recognition using multidimensional indexing

Optimal edge detection using expansion matching and restoration

The probabilistic peaking effect of viewed angles and distances with application to 3-D object recognition

Pictorial recognition of objects employing affine invariance in the frequency domain

A volumetric/iconic frequency domain representation for objects with application for pose invariant face recognition