Planning algorithms are impacting technical disciplines and industries around the world, including robotics, computer-aided design, manufacturing, computer graphics, aerospace applications, drug design, and protein folding. This coherent and comprehensive book unifies material from several sources, including robotics, control theory, artificial intelligence, and algorithms. The treatment is centered on robot motion planning but integrates material on planning in discrete spaces. A major part of the book is devoted to planning under uncertainty, including decision theory, Markov decision processes, and information spaces, which are the “configuration spaces” of all sensor-based planning problems. The last part of the book delves into planning under differential constraints that arise when automating the motions of virtually any mechanical system. Developed from courses taught by the author, the book is intended for students, engineers, and researchers in robotics, artificial intelligence, and control theory as well as computer graphics, algorithms, and computational biology.

Planning Algorithms: Introductory Material

3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is becoming increasingly important to have a powerful 3D shape representation in the loop. Apart from category recognition, recovering full 3D shapes from view-based 2.5D depth maps is also a critical part of visual understanding. To this end, we propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representation automatically. It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning. To train our 3D deep learning model, we construct ModelNet - a large-scale 3D CAD model dataset. Extensive experiments show that our 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.

/pdf/3d-shapenets-a-deep-representation-for-volumetric-shapes-1ii3phcu91.pdf

3D ShapeNets: A deep representation for volumetric shapes

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

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

Multisensor data fusion is an emerging technology applied to Department of Defense (DoD) areas such as automated target recognition, battlefield surveillance, and guidance and control of autonomous vehicles, and to non-DoD applications such as monitoring of complex machinery, medical diagnosis, and smart buildings. Techniques for multisensor data fusion are drawn from a wide range of areas including artificial intelligence, pattern recognition, statistical estimation and other areas. This paper provides a tutorial on data fusion, introducing data fusion applications, process models, and identification of applicable techniques. Comments are made on the state-of-the-art in data fusion.

An introduction to multisensor data fusion

In comparison with 2D face images, 3D face models have the advantage of being illumination and pose invariant, which provides improved capability of handling changing environments in practical surveillance. Feature detection, as the initial process of reconstructing 3D face models from 2D uncalibrated image sequences, plays an important role and directly affects the accuracy and robustness of the resulting reconstruction. In this paper, we propose an automated scene-specific selection algorithm that adaptively chooses an optimal feature detector according to the input image sequence for the purpose of 3D face reconstruction. We compare the performance of various feature detectors in terms of accuracy and robustness of the sparse and dense reconstructions. Our experimental results demonstrate the effectiveness of the proposed selection method from the observation that the chosen feature detector produces 3D reconstructed face models with superior accuracy and robustness to image noise.

/pdf/automated-scene-specific-selection-of-feature-detectors-for-4de9p7wfoc.pdf

Automated scene-specific selection of feature detectors for 3D face reconstruction

Most existing performance evaluation methods concentrate on defining various metrics over a wide range of conditions and generating standard benchmarking video sequences to examine the effectiveness of a video tracking system. It is a common practice to incorporate a robustness margin or factor into the system/algorithm design. However, these methods, deterministic approaches, often lead to overdesign, thus increasing costs, or underdesign, causing frequent system failures. In order to overcome the aforementioned limitations, we propose an alternative framework to analyze the physics of the failure process via the concept of reliability. In comparison with existing approaches where system performance is evaluated based on a given benchmarking sequence, the advantage of our proposed framework lies in that a unified and statistical index is used to evaluate the performance of an automated video surveillance system independent of input sequences. Meanwhile, based on our proposed framework, the uncertainty problem of a failure process caused by the system’s complexity, imprecise measurements of the relevant physical constants and variables, and the indeterminate nature of future events can be addressed accordingly.

A novel performance evaluation paradigm for automated video surveillance systems

Aberration correction has revolutionized electron microscopy, for the first time allowing direct imaging of sub-angstrom atomic spacings. Using this technique for catalytic materials has been especially beneficial – the improved signal-to-noise ratios now allow for detection of quantities of some elements as small as a single atom, giving a complete picture of particle size distribution. Wider probe-forming apertures θ used in aberration-corrected STEMs also result in reduced depth of field (Δz = λ/θ), making it possible to optically section through a sample, similar to widefield optical microscopy. For modern C3and C3, C5-corrected instruments, convergence angles are in the rage of 20 to 35 mrad or more, resulting in the depth of field of low single nanometers (in amorphous and off-axis media). This makes it possible to examine 3D structure of realistic heterogeneous catalysts in three dimensions with nanoscale vertical resolution. STEM focal series can be used to detect single atoms and in suitable cases, determine of their height with subnanometer precision [1, 2]. In the higher end of the currently achievable range of the convergence angles, it is in principle possible to detect a single dopant atom even in an aligned crystal [3].

https://imaging.utk.edu/publications/papers/2008/mm08_ab.pdf

3D Scanning Transmission Electron Microscopy for Catalysts: Imaging and Data Analysis

This chapter presents an adaptive regularized image interpolation algorithm, which is developed in a general framework of data fusion, to enlarge noisy-blurred, low-resolution (LR) image sequences. Initially, the assumption is made that each LR image frame is obtained by subsampling the corresponding original high-resolution (HR) image frame. Then the mathematical model of the subsampling process is obtained. Given a sequence of LR image frames and the mathematical model of subsampling, the general regularized image interpolation estimates HR image frames by minimizing the residual between the given LR image frame and the subsampled estimated solution with appropriate smoothness constraints.

Regularized Image Interpolation Based on Data Fusion

Scene segmentation is a pre-processing step for many vision systems. We are concerned with segmentation as a precursor to 3D scene modeling. Segmentation of a scene for this purpose usually involves dividing an image into areas that are relatively uniform in some value (e.g. intensity, range, or curvature). This single segmented image represents the analogous segmented scene. This paper presents a segmentation method that uses features to indicate boundaries or edges between regions. We incorporate features from multiple images types to obtain an more accurate segmentation of objects or object parts in the scene. Multiple features are not only combined directly to improve segmentation results, but they are also used to guide a smoothing operation. This smoothing technique preserves features representing edges while smoothing noise in the images.

Mongi A. Abidi

Papers

Automated scene-specific selection of feature detectors for 3D face reconstruction

A novel performance evaluation paradigm for automated video surveillance systems

3D Scanning Transmission Electron Microscopy for Catalysts: Imaging and Data Analysis

Regularized Image Interpolation Based on Data Fusion

Scene segmentation from vector-valued images using anisotropic diffusion