This paper presents a data-driven method to estimate a high quality depth map of a hand from a stereoscopic camera input by introducing a novel regression framework. The method first computes disparity using a robust stereo matching technique. Then, it applies Random Forest (RF) to learn the mapping between the estimated, noisy disparity and actual depth given ground truth data. We introduce Eigen Leaf Node Features (ELNFs) that perform feature selection at the leaf node in each RF tree to identify features that are most discriminative for depth regression. Experimental results demonstrate the promise of the method to produce high quality depth images of a hand using an inexpensive stereo camera.

This is the unspecified version of the paper.This version of the publication may differ from the final published version. Abstract-Artificial intelligence has become an increasingly important aspect of computer game technology, as designers attempt to deliver engaging experiences for players by creating characters with behavioural realism to match advances in graphics and physics. Recently, behaviour trees have come to the forefront of games AI technology, providing a more intuitive approach than previous techniques such as hierarchical state machines, which often required complex data structures producing poorly structured code when scaled up. The design and creation of behaviour trees, however, requires experience and effort. This research introduces Q-learning behaviour trees (QL-BT), a method for the application of reinforcement learning to behaviour tree design. The technique facilitates AI designers' use of behaviour trees by assisting them in identifying the most appropriate moment to execute each branch of AI logic, as well as providing an implementation that can be used to debug, analyse and optimize early behaviour tree prototypes. Initial experiments demonstrate that behaviour trees produced by the QL-BT algorithm effectively integrate RL, automate tree design, and are human-readable. Permanent repository link

This is the unspecified version of the paper.This version of the publication may differ from the final published version.Permanent repository link: http://openaccess.city.ac.uk/3002/ Link to published version: http://dx.Abstract. Apriori Stochastic Dependency Detection (ASDD) is an algorithm for fast induction of stochastic logic rules from a database of observations made by an agent situated in an environment. ASDD is based on features of the Apriori algorithm for mining association rules in large databases of sales transactions [1] and the MSDD algorithm for discovering stochastic dependencies in multiple streams of data [15]. Once these rules have been acquired the Precedence algorithm assigns operator precedence when two or more rules matching the input data are applicable to the same output variable. These algorithms currently learn propositional rules, with future extensions aimed towards learning first-order models. We show that stochastic rules produced by this algorithm are capable of reproducing an accurate world model in a simple predator-prey environment.

Abstract-Current depth capturing devices show serious drawbacks in certain applications, for example ego-centric depth recovery: they are cumbersome, have a high power requirement, and do not portray high resolution at near distance. Stereo-matching techniques are a suitable alternative, but whilst the idea behind these techniques is simple it is well known that recovery of an accurate disparity map by stereo-matching requires overcoming three main problems: occluded regions causing absence of corresponding pixels; existence of noise in the image capturing sensor and inconsistent color and brightness in the captured images.We propose a modified version of the Census-Hamming cost function which allows more robust matching with an emphasis on improving performance under radiometric variations of the input images.

Hand pose is emerging as an important interface for human-computer interaction. IntroductionThe problem of tracking articulated objects has attracted increasing attention in the field of computer vision, as it provides a natural method of Human Computer Interaction (HCI) [9], [10]. Inference of the pose and gesture of the human hand is an important challenge in this area. Active vision approaches for hand pose estimation using depth sensors such as Leap Motion and Kinect have made considerable progress in recent years. These cameras actively dissipate electromagnetic waves into the scene, probing how far each point in the field of view is away from the imaging device. While active vision techniques provide good shape information and robustness to clutter, they present several limitations, including: large energy consumption, a poor form factor, less accurate near distance coverage, and poor outdoor usage.In contrast, in this paper we explore the use of passive vision for the estimation of hand pose using a stereovision system composed of adjacent RGB cameras. Such a camera rig does not project light into the scene, and therefore has complementary advantages to depth imaging, including less energy consumption. However, hand pose estimation in this context is a more challenging computer vision problem, one that has received less attention in the literature. We address this gap by proposing a novel framework that combines jointly optimal depth and hand pose estimation in a unified framework using Markov-chain Monte Carlo (MCMC) sampling and deep learning. Our research is motivated by the possibility of estimating articulation with the input of stereo cameras from an egocentric, stereoscopic perspective. We are inspired by human vision, which can efficiently discern articulations and perform tracking activities with passive, binocular input. As our experiments show, our approach is compatible with inexpensive stereo vision systems, such as the rig shown in Figure 1, to produce robust hand pose inference. The proposed technique also relies on a robust hand segmentation procedure. We do not address hand segmentation in this paper as there is a large body of literature on this subject (see, for example, [1], [21]). ContributionUnlike several approaches to pose estimation from stereo capture that explicitly recover disparity before regressing for the pose in a sequential manner we present a joint optimization approach that is robust against potential errors Hand Pose Estimation Using Deep Stereovision and Markov-chain Monte Carlo