https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimo dal, cannot represent simultaneous alternative hypotheses. The Condensation algorithm uses “factored sampling”, previously applied to the interpretation of static images, in which the probability distribution of possible interpretations is represented by a randomly generated set. Condensation uses learned dynamical models, together with visual observations, to propagate the random set over time. The result is highly robust tracking of agile motion. Notwithstanding the use of stochastic methods, the algorithm runs in near real-time.

/pdf/c-ondensation-conditional-density-propagation-forvisual-2zlkn4lnac.pdf

C ONDENSATION —Conditional Density Propagation forVisual Tracking

Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

This article provides a tutorial introduction to visual servo control of robotic manipulators. Since the topic spans many disciplines our goal is limited to providing a basic conceptual framework. We begin by reviewing the prerequisite topics from robotics and computer vision, including a brief review of coordinate transformations, velocity representation, and a description of the geometric aspects of the image formation process. We then present a taxonomy of visual servo control systems. The two major classes of systems, position-based and image-based systems, are then discussed in detail. Since any visual servo system must be capable of tracking image features in a sequence of images, we also include an overview of feature-based and correlation-based methods for tracking. We conclude the tutorial with a number of observations on the current directions of the research field of visual servo control.

/pdf/a-tutorial-on-visual-servo-control-5cy6rje63g.pdf

A tutorial on visual servo control

This article describes the robot Stanley, which won the 2005 DARPA Grand Challenge. Stanley was developed for high-speed desert driving without human intervention. The robot’s software system relied predominately on state-of-the-art AI technologies, such as machine learning and probabilistic reasoning. This article describes the major components of this architecture, and discusses the results of the Grand Challenge race.

/pdf/stanley-the-robot-that-won-the-darpa-grand-challenge-4ee4z6po6l.pdf

Stanley: The Robot that Won the DARPA Grand Challenge

A new approach to real-time machine vision in dynamic scenes is presented based on special hardware and methods for feature extraction and information processing. Using integral spatio-temporal models, it by-passes the nonunique inversion of the perspective projection by applying recursive least squares filtering. By prediction error feedback methods similar to those used in modern control theory, all spatial state variables including the velocity components are estimated. Only the last image of the sequence needs to be evaluated, thereby alleviating the real-time image sequence processing task.

Dynamic monocular machine vision

The 4-D approach to real-time machine vision presented in the companion paper (Dickmanns and Graefe 1988, this volume) is applied here to two problem areas of widespread interest in robotics. Following a discussion of the vision hardware sed, first, the precise position control for planar docking between 3-D vehicles is discussed; second, the application to high speed road vehicle guidance is demonstrated. With the 5 ton test vehicle VaMoRs, speeds up to 96 km/h (limited by the speed capability of the basic vehicle) have been reached. The test run available, of more than 20 km length, has been driven autonomously several times under various weather conditions.

Applications of dynamic monocular machine vision

Autonomous High Speed Road Vehicle Guidance by Computer Vision 1

A passenger car Mercedes 500 SEL has been equipped with vision in the framework of the EUREKA-project 'Pometheus III'. Road and object recognition is performed both in a look-ahead and in a look-back region; this allows an internal servo-maintained representation of the entire situation around the vehicle using the 4D approach to dynamic machine vision. Obstacles are detected and tracked both in the forward and in the backward viewing range up to about 100 meters distance; depending on the computing power available for this purpose up to 4 or 5 objects may be tracked in parallel in each hemisphere. A fixation type viewing direction control with the capability of saccadic shifts of viewing direction for attention focussing has been developed. The overall system comprises about 60 transputers of T-222 and T-800. Beside a PC as transputer host all other processors in VaMoRs-P are transputers. A description of the parallel processing architecture is given; the system integration follows the well proven paradigm of orientation towards 4D physical objects and expectations with prediction error feedback. This allows frequent data driven bottom-up and model driven top-down integration steps for efficient and robust object tracking.

The seeing passenger car 'VaMoRs-P'

The paper gives a survey on the new Expectation-based Multifocal Saccadic vision (EMS-vision) system for autonomous vehicle guidance developed at the Universitat der Bundeswehr Munchen (UBM). EMS-Vision is the third generation dynamic vision system following the 4-D approach. Its core element is a new camera arrangement, mounted on a high bandwidth pan-tilt head for active gaze control. Central knowledge representation and a hierarchical system architecture allow efficient activation and control of behavioral capabilities for perception and action. The system has been implemented on commercial off-the-shelf (COTS) hardware components in both UBM test vehicles VaMoRs and VaMP Results from autonomous turnoff maneuvers, performed on army proving grounds, are discussed.

Ernst D. Dickmanns

Papers

Dynamic monocular machine vision

Applications of dynamic monocular machine vision

Autonomous High Speed Road Vehicle Guidance by Computer Vision 1

The seeing passenger car 'VaMoRs-P'

EMS-Vision: a perceptual system for autonomous vehicles