From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

The PASCAL Visual Object Classes Challenge

https://www-i6.informatik.rwth-aachen.de/publications/download/996/Koller-CVIU-2015.pdf

Continuous Sign Language Recognition: Towards Large Vocabulary Statistical Recognition Systems Handling Multiple Signers

Marine cabled video-observatories allow the non-destructive sampling of species at frequencies and durations that have never been attained before Nevertheless, the lack of appropriate methods to automatically process video imagery limits this technology for the purposes of ecosystem monitoring Automation is a prerequisite to deal with the huge quantities of video footage captured by cameras, which can then transform these devices into true autonomous sensors In this study, we have developed a novel methodology that is based on genetic programming for content-based image analysis Our aim was to capture the temporal dynamics of fish abundance We processed more than 20,000 images that were acquired in a challenging real-world coastal scenario at the OBSEA-EMSO testing-site The images were collected at 30-min frequency, continuously for two years, over day and night The highly variable environmental conditions allowed us to test the effectiveness of our approach under changing light radiation, water turbidity, background confusion, and bio-fouling growth on the camera housing The automated recognition results were highly correlated with the manual counts and they were highly reliable when used to track fish variations at different hourly, daily, and monthly time scales In addition, our methodology could be easily transferred to other cabled video-observatories

/pdf/tracking-fish-abundance-by-underwater-image-recognition-1cm5ak5xnj.pdf

Tracking Fish Abundance by Underwater Image Recognition

The objective of this paper is to recognize gestures in videos – both localizing the gesture and classifying it into one of multiple classes.

/pdf/domain-adaptive-discriminative-one-shot-learning-of-gestures-jg1odq8jps.pdf

Domain-Adaptive Discriminative One-Shot Learning of Gestures

Rapidly acquiring the shape and pose information of unknown objects is an essential characteristic of modern robotic systems in order to perform efficient manipulation tasks. In this work, we present a framework for 3D geometric shape recovery and pose estimation from unorganized point cloud data. We propose a low latency multi-scale voxelization strategy that rapidly fits superquadrics to single view 3D point clouds. As a result, we are able to quickly and accurately estimate the shape and pose parameters of relevant objects in a scene. We evaluate our approach on two datasets of common household objects collected using Microsoft's Kinect sensor. We also compare our work to the state of the art and achieve comparable results in less computational time. Our experimental results demonstrate the efficacy of our approach.

Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects

Salient image regions permit non-uniform allocation of computational resources. The selection of a commensurate set of salient regions is often a step taken in the initial stages of many computer vision algorithms, thereby facilitating object recognition, visual search and image matching. In this study, the authors survey the role and advancement of saliency algorithms over the past decade. The authors first offer a concise introduction to saliency. Next, the authors present a summary of saliency literature cast into their respective categories then further differentiated by their domains, computational methods, features, context and use of scale. The authors then discuss the achievements and limitations of the current state of the art. This information is augmented by an outline of the datasets and performance measures utilised as well as the computational techniques pervasive in the literature.

Saliency in images and video: a brief survey

We present a probabilistic framework to automatically learn models of recurring signs from multiple sign language video sequences containing the vocabulary of interest. We extract the parts of the signs that are present in most occurrences of the sign in context and are robust to the variations produced by adjacent signs. Each sentence video is first transformed into a multidimensional time series representation, capturing the motion and shape aspects of the sign. Skin color blobs are extracted from frames of color video sequences, and a probabilistic relational distribution is formed for each frame using the contour and edge pixels from the skin blobs. Each sentence is represented as a trajectory in a low dimensional space called the space of relational distributions. Given these time series trajectories, we extract signemes from multiple sentences concurrently using iterated conditional modes (ICM). We show results by learning single signs from a collection of sentences with one common pervading sign, multiple signs from a collection of sentences with more than one common sign, and single signs from a mixed collection of sentences. The extracted signemes demonstrate that our approach is robust to some extent to the variations produced within a sign due to different contexts. We also show results whereby these learned sign models are used for spotting signs in test sequences.

/pdf/finding-recurrent-patterns-from-continuous-sign-language-58e8mjk3va.pdf

Finding recurrent patterns from continuous sign language sentences for automated extraction of signs

Salient regions in an image facilitate the non-uniform allocation of computational resources to just the interesting parts of an image. In this paper, we present a saliency detection mechanism using relational distributions that capture geometric statistics based on distance and gradient direction relationships between pixels. The entropy of these normalized distributions is related to saliency. We employ an efficient technique for calculating the Renyi entropy of the probabilistic relational distributions using Parzen window weighted samples, thus eliminating the need for constructing intermediate histogram representations. We quantitatively demonstrate the biological plausibility of our method by showing how the saliency maps produced strongly correlate to human fixations in still images and to dominant objects in video. We find that our approach is better than six other saliency models.

Relational entropy-based saliency detection in images and videos

In order for assistive robots to collaborate effectively with humans, they must be endowed with the ability to perceive scenes and more importantly, recognize human intentions. These intentions are often inferred from observed physical actions and direct communication from fully-functional individuals. For individuals with reduced capabilities, it may be difficult or impossible to perform physical actions or easily communicate. Therefore, their intentions must be inferred differently. To this end, we propose an intention recognition framework that is appropriate for persons with limited physical capabilities. This framework determines and learns human intentions based on scene objects, the actions that can be performed on them, and past interaction history. It is based on a Markov model formulation entitled Object-Action Intention Networks, which constitute the crux of a computer vision-based human-robot collaborative system that reduces the necessary interactions for communicating tasks to a robot. Evaluations were conducted on multiple scenes comprised of multiple possible object categories and actions. We achieve approximately 81% reduction in interactions overall after learning, when compared to other intention recognition approaches.

/pdf/scene-dependent-intention-recognition-for-task-communication-52q1d8jg5o.pdf

Kester Duncan

Papers

Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects

Saliency in images and video: a brief survey

Finding recurrent patterns from continuous sign language sentences for automated extraction of signs

Relational entropy-based saliency detection in images and videos

Scene-Dependent Intention Recognition for Task Communication with Reduced Human-Robot Interaction