Gotowa bibliografia na temat „Structure- Motion”

The structure from motion (SfM) problem is that of determining 3-dimensional (3D) information of a scene from sequences of 2-dimensional (2D) images [59]. This information consists of object shape and motion and relative camera motion. In general, objects may undergo complex non-rigid motion and may be occluded by other objects or themselves. These aspects make the general SfM problem under-constrained and the solution subject to missing or incomplete data.

This master thesis investigates the difficulties of constructing a depth map using one low resolution grayscale camera mounted in the front of a car. The goal is to produce a depth map in real-time to assist other algorithms in the safety system of a car. This has been shown to be difficult using the evaluated combination of camera position and choice of algorithms. The main problem is to estimate an accurate optical flow. Another problem is to handle moving objects. The conclusion is that the implementations, mainly triangulation of corresponding points tracked using a Lucas Kanade tracker, provide information of too poor quality to be useful for the safety system of a car.<br>I detta examensarbete undersöks svårigheterna kring att skapa en djupbild från att endast använda en lågupplöst gråskalekamera monterad framtill i en bil. Målet är att producera en djupbild i realtid som kan nyttjas i andra delar av bilens säkerhetssystem. Detta har visat sig vara svårt att lösa med den undersökta kombinationen av kameraplacering och val av algoritmer. Det huvudsakliga problemet är att räkna ut ett noggrant optiskt flöde. Andra problem härrör från objekt som rör på sig. Slutsatsen är att implementationerna, mestadels triangulering av korresponderande punktpar som följts med hjälp av en Lucas Kanade-följare, ger resultat av för dålig kvalitet för att vara till nytta för bilens säkerhetssystem.

If humanoid robots should work along with humans and should be able to solve repetitive tasks, we need to enable them with a skill to autonomously plan motions. Motion planning is a longstanding core problem in robotics, and while its algorithmic foundation has been studied in depth, motion planning is still an NP-hard problem lacking efficient solutions. We want to open up a new perspective on the problem by highlighting its structure: the behavior of the robot, the mechanical system of the robot, and the environment of the robot. We will investigate the hypothesis that each structural component can be exploited to create more efficient motion planning algorithms. We present three algorithms exploiting structure, based on geometrical and topological arguments: first, we exploit the behavior of a walking robot by studying the feasibility of footstep transitions. The resulting algorithm is able to plan footsteps avoiding up to 60 objects on a 6 square meters planar surface. Second, we exploit the mechanical system of a humanoid robot by studying the linear linkage structures of its arms and legs. We introduce the concept of an irreducible motion, which is a completeness-preserving dimensionality reduction technique. The resulting algorithm is able to find motions in narrow environments, where previous sampling-based methods could not be applied. Third, we exploit the environment by reasoning about the topological structure of contact transitions. We show that analyzing the environment is an efficient method to precompute relevant information for efficient motion planning. Based on those results, we come to the conclusion that exploiting structure is an essential component of efficient motion planning. It follows that any humanoid robot, who wants to act efficiently in the real world, needs to be able to understand and to exploit structure.

Digital camera equipped cell phones were introduced in Japan in 2001, they quickly became popular and by 2003 outsold the entire stand-alone digital camera market. In 2010 sales passed one billion units and the market is still growing. Another trend is the rising popularity of smartphones which has led to a rapid development of the processing power on a phone, and many units sold today bear close resemblance to a personal computer. The combination of a powerful processor and a camera which is easily carried in your pocket, opens up a large eld of interesting computer vision applications. The core contribution of this thesis is the development of methods that allow an imaging device such as the cell phone camera to estimates its own motion and to capture the observed scene structure. One of the main focuses of this thesis is real-time performance, where a real-time constraint does not only result in shorter processing times, but also allows for user interaction. In computer vision, structure from motion refers to the process of estimating camera motion and 3D structure by exploring the motion in the image plane caused by the moving camera. This thesis presents several methods for estimating camera motion. Given the assumption that a set of images has known camera poses associated to them, we train a system to solve the camera pose very fast for a new image. For the cases where no a priory information is available a fast minimal case solver is developed. The solver uses ve points in two camera views to estimate the cameras relative position and orientation. This type of minimal case solver is usually used within a RANSAC framework. In order to increase accuracy and performance a renement to the random sampling strategy of RANSAC is proposed. It is shown that the new scheme doubles the performance for the ve point solver used on video data. For larger systems of cameras a new Bundle Adjustment method is developed which are able to handle video from cell phones. Demands for reduction in size, power consumption and price has led to a redesign of the image sensor. As a consequence the sensors have changed from a global shutter to a rolling shutter, where a rolling shutter image is acquired row by row. Classical structure from motion methods are modeled on the assumption of a global shutter and a rolling shutter can severely degrade their performance. One of the main contributions of this thesis is a new Bundle Adjustment method for cameras with a rolling shutter. The method accurately models the camera motion during image exposure with an interpolation scheme for both position and orientation. The developed methods are not restricted to cellphones only, but is rather applicable to any type of mobile platform that is equipped with cameras, such as a autonomous car or a robot. The domestic robot comes in many  avors, everything from vacuum cleaners to service and pet robots. A robot equipped with a camera that is capable of estimating its own motion while sensing its environment, like the human eye, can provide an eective means of navigation for the robot. Many of the presented methods are well suited of robots, where low latency and real-time constraints are crucial in order to allow them to interact with their environment.<br>Virtual Photo Set (VPS)

Perception of depth, ego-motion and robust keypoints is critical for SLAM andstructure from motion applications. Neural networks have achieved great perfor-mance in perception tasks in recent years. But collecting labeled data for super-vised training is labor intensive and costly. This thesis explores recent methodsin unsupervised training of neural networks that can predict depth, ego-motion,keypoints and do geometric consensus maximization. The benefit of unsuper-vised training is that the networks can learn from raw data collected from thecamera sensor, instead of labeled data. The thesis focuses on training on imagesfrom a monocular camera, where no stereo or LIDAR data is available. The exper-iments compare different techniques for depth and ego-motion prediction fromprevious research, and shows how the techniques can be combined successfully.A keypoint prediction network is evaluated and its performance is comparedwith the ORB detector provided by OpenCV. A geometric consensus network isalso implemented and its performance is compared with the RANSAC algorithmin OpenCV. The consensus maximization network is trained on the output of thekeypoint prediction network. For future work it is suggested that all networkscould be combined and trained jointly to reach a better overall performance. Theresults show (1) which techniques in unsupervised depth prediction are most ef-fective, (2) that the keypoint predicting network outperformed the ORB detector,and (3) that the consensus maximization network was able to classify outlierswith comparable performance to the RANSAC algorithm of OpenCV.

Thesis (Ph. D.) -- University of Maryland, College Park, 2006.<br>Thesis research directed by: Computer Science. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.