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

Many engineering problems, particularly in image processing, can be expressed as optimization problems. Often, we must make approximations of our mathematical models in order to cast the problems into optimization form. This chapter considers basic optimization theory and application as related to image processing. The focus presented in the examples will be to functions of one dimension, or line functions. Later chapters will give emphasis to the multidimensional case.

Introduction to Optimization

An analytic method for the fusion of range and intensity edge maps is proposed for applications in robotic vision and sensing. This method addresses the integration of registered information to increase one's confidence about the presence/absence of a feature (edge) in a depicted scene. The algorithm is based on the interaction between the following two constraints: the principle of token corroboration, which tends to maximize the value of the output edge map at a given location if one input edge map features an edge, and the principle of belief enhancement/withdrawal, which adjusts this value according to the edge content in the other input edge map at the same location, by maximizing the similarity between them. These two principles are combined by maximizing a linear positive combination of these two constraints related by a fusion function, to be determined. The latter maximization is achieved using the Euler-Lagrange equations. This method was tested with real data, and the resulting edge maps combining both range and intensity data were found to satisfy both principles. >

Analytic fusion of edge maps

In this paper, we present a robust recognition method for license plate numbers that are severely distorted by down-sampling, low light level illumination, and geometric distortion. The proposed method adopts a novel approach, where a set of reference license plate images are intentionally degraded using the same degradation factors estimated from the input distorted images. We first generate a set of reference images using notch filter, band-pass filter, and geometric transformation. We then compare input images with the degraded version of the reference images in the sense of sum of absolute difference (SAD). The proposed method provides an acceptable recognition rate for severely distorted input images that cannot be recognized by human vision.

Recognition of severely distorted license plate numbers: Part 1 theory

Three-dimensional (3D) object representation and shape reconstruction play an important role in the field of computer vision. In this chapter, a parametric model is proposed as a coarse description of the volumetric part of 3D objects for object recognition. The parameterized part-based superquadric model is used as a volumetric parameter model. This superquadric model has the advantage that it can describe various primitive shapes using a finite number of parameters including translation, rotation, and global deformation. Shape recovery is performed by least square minimization of the objective function for all range points belonging to a single part of the object. The set of superquadric parameters representing each single part of the 3D object can then be obtained.

Volumetric Description of Three-Dimensional Objects for Object Recognition

The successful implementation of spherical aberration correction in the scanning transmission electron microscope (STEM) is one of the most significant accomplishments in electron optics in the last few decades. Correction of magnetic lens aberrations to the third order has led to significant improvements in point resolution and signal-to-noise ratio, expanding the range of accessible lattice spacings into the sub-Angstrom regime [1]. The greatly reduced depth of field of the aberrationcorrected STEM probes has also enabled three-dimensional imaging by optical sectioning [2]. Fig. 1 shows a 3D rendered STEM data set of a (Pt, Au)/TiO2 catalyst sample. The data has been acquired using a VG Microscopes HB603U STEM at ORNL. The metal particles appear elongated in the depth direction, reflecting the defocus spread of the STEM probe. Deconvolution techniques similar to those used in confocal optical microscopy can help achieve closer correspondence with the real structure of the material [2].

https://imaging.utk.edu/publications/papers/2007/MandM-07ak.pdf

Mongi A. Abidi

Papers

Introduction to Optimization

Analytic fusion of edge maps

Recognition of severely distorted license plate numbers: Part 1 theory

Volumetric Description of Three-Dimensional Objects for Object Recognition

Improving 3D Reconstruction from STEM Data