Networked 3D virtual environments allow multiple users to interact with each other over the Internet. Users can share some sense of telepresence by remotely animating an avatar that represents them. However, avatar control may be tedious and still render user gestures poorly. This work aims at animating a user s avatar from real time 3D motion capture by monocular computer vision, thus allowing virtual telepresence to anyone using a personal computer with a webcam. The approach followed consists of registering a 3D articulated upper-body model to a video sequence. The first contribution of this work is a method of allocating computing iterations under real-time constrain that achieves optimal robustness and accuracy. The major issue for robust 3D tracking from monocular images is the 3D/2D ambiguities that result from the lack of depth information. As a second contribution, this work enhances particle filtering for 3D/2D registration under limited computation constrains with a number of heuristics, the contribution of which is demonstrated experimentally. A parameterization of the arm pose based on their end-effector is proposed to better model uncertainty in the depth direction.
Recovery of dense geometry and camera motion from a set of monocular images is a well-known problem that can be solved quite reliably in well-conditioned environments. Typical algorithms dealing with this problem assume static lighting and presence of sufficient scene texture. There are, however, many situations where these prerequisites are not met, and common algorithms fail. One example is medical video-endoscopy, where surfaces do not exhibit much texture, and lighting conditions change due to the moving light source that is mounted on the camera. We suggest to address the problem by applying a purely intensity-based approach that also takes into account changes in lighting conditions. In this thesis, we investigate the applicability of sliding window intensity-based bundle-adjustment methods to this problem.
High Quality Content by WIKIPEDIA articles! High Quality Content by WIKIPEDIA articles! The lightweight helmet is the U.S. Marine Corps replacement for the PASGT combat helmet. As it is nearly identical to untrained eyes in shape to the PASGT, it is still called the "Fritz helmet" or "K-pot". Though heavier than the Army's advanced combat helmet, its larger size also offers more protection and is lighter than the PASGT. Featuring a V-neck strap and improved fit, it is much more comfortable than the PASGT. It entered service in late 2004 and will completely replace the PASGT by 2009. As with the PASGT helmet, it is an olive drab color, and can be fitted with cloth helmet covers in desert and woodland MARPAT camouflage patterns, as well as a mounting bracket on the front for any sort of night vision device, such as the AN/PVS-7 night vision goggle or AN/PVS-14 monocular night vision device. Marines currently can be issued with a sling suspension or a pad suspension to fit the inside of the helmet to the head. A nape protection system to add ballistic protection to the rear of the head is also being fielded.
Please note that the content of this book primarily consists of articles available from Wikipedia or other free sources online. An ocular prosthesis or artificial eye (a type of Craniofacial prosthesis) replaces an absent natural eye following an enucleation, evisceration, or orbital exenteration. The prosthetic fits over an orbital implant and under the eyelids. Typically known as a glass eye, the ocular prosthesis roughly takes the shape of a convex shell and is made of medical grade plastic acrylic. A few ocular prosthetics today are made of cryolite glass. A variant of the ocular prosthesis is a very thin hard shell known as a scleral shell which can be worn over a damaged eye. Makers of ocular prosthetics are known as ocularists. An ocular prosthetic does not provide vision, this would be a visual prosthetic. Someone with an ocular prosthetic is totally blind on the affected side and has monocular (one sided) vision which affects depth perception.
Please note that the content of this book primarily consists of articles available from Wikipedia or other free sources online. Ocular dominance columns are regions of neurons in the visual cortex that synapse with axons carrying transduced signals from either the left or right eye. The columns span multiple cortical layers, producing a striped pattern when the deeper levels are stained. Prior to birth, monocular transduction pathways are already established through a process known as Hebbian learning. Spontaneous retinal activity in one eye of the developing fetus leads to neuronal depolarization. Synapses that receive multiple inputs are more likely to propagate the signal, whereas errant connections will not be sufficient to trigger another action potential. Post-synaptic neurons that depolarize become permeable to calcium ions, if glutamate has been released by the pre-synaptic axon terminal. Calcium''s entry leads to a chemical process that strengthens the synapse, making it more likely to survive than other connections.
Scene interpretation is a fundamental task in both computer vision and robotic systems. We deal with two important aspects of scene interpretation, they are scene reconstruction and scene recognition. Scene reconstruction is determining 3D positions of world points and retrieving camera poses from images. It has several applications such as virtual building editing, video augmentation, and planning and navigation in robotics. Among several approaches to modeling the scene, we deal with piecewise planar modeling due to several advantages. We propose a convex optimization based, approach for piecewise planar reconstruction. Scene recognition in robotics, specifically terrain scene recognition is one of the fundamental tasks of autonomous navigation. Navigable terrains are examples of planar scenes. It has applications in various domains such as advanced driver assistance systems, remote sensing, etc. Various sensing modalities such as ladars, lasers, accelerometers, stereo cameras, or combination of them are used in literature. We propose an algorithm which is purely based on a single monocular camera.
High Quality Content by WIKIPEDIA articles! Stereopsis (from stereo meaning solidity, and opsis meaning vision or sight) is the process in visual perception leading to the sensation of depth from the two slightly different projections of the world onto the retinas of the two eyes. The differences in the two retinal images are called horizontal disparity, retinal disparity, or binocular disparity. The differences arise from the eyes' different positions in the head. Stereopsis is commonly referred to as depth perception. This is inaccurate, as depth perception relies on many more monocular cues than stereoptical ones, and individuals with only one functional eye still have full depth perception except in artificial cases (such as stereoscopic images) where only binocular cues are present.
This book presents a hardware architecture for the Simultaneous Localization And Mapping (SLAM) problem applied to embedded robots. The architecture is composed by highly specialized modules for robot localization and feature-based map building from images obtained directly from CMOS cameras in real time. The system is completely embedded on a Field-Programmable Gate Array (FPGA) device, where several hardware-orientated optimizations are exploited. The main modules of the architecture are the Extended Kalman Filter (EKF) and the feature detection system based on the SIFT (Scale Invariant Feature Transform) algorithm. Additionally, this book also presents basic concepts about mapping and state-of-the-art algorithms for SLAM with monocular and stereo vision.
Visual scene understanding is one of the ultimate goals in computer vision and has been in the field's focus since its early beginning. Despite continuous effort over several years, applications such as autonomous driving and robotics are still subject to active research. In recent years, improved probabilistic methods became a popular tool for state-of-the-art computer vision algorithms. Additionally, high resolution digital imaging devices and increased computational power became available. By leveraging these methodical and technical advancements current methods obtain encouraging results in well defined environments for robust object class detection, tracking and pixel-wise semantic scene labeling and give rise to renewed hope for further progress in scene understanding for real environments. This book improves state-of-the-art scene understanding with monocular cameras and aims for applications on mobile platforms such as service robots or driver assistance for automotive safety. It develops and improves approaches for object class detection and semantic scene labeling and integrates those into models for global scene reasoning which exploit context at different levels.