Optimal instantaneous rigid motion estimation 3 insensitive to local minima 4 Karl Pauwels * , Marc
نویسندگان
چکیده
9 A novel method is introduced for optimal estimation of rigid camera motion from instantaneous velocity measurements. The error 10 surface associated with this problem is highly complex and existing algorithms suffer heavily from local minima. Repeated minimization 11 with different random initializations and selection of the minimum-cost solution are a common (albeit ad hoc) procedure to increase the 12 likelihood of finding the global minimum. We instead show that the optimal estimation problem can be transformed into one of arbitrary 13 complexity, which allows for a gradual regularization of the error function. A simple reweighting scheme is presented that smoothly 14 increases the problem complexity at each iteration. We show that the resulting method retains all the desirable properties of optimal 15 algorithms, such as unbiasedness and minimal variance of the parameter estimates, but is substantially more robust to local minima. 16 This robustness comes at the expense of a slightly increased computational complexity. 17 2006 Published by Elsevier Inc.
منابع مشابه
Optimal instantaneous rigid motion estimation insensitive to local minima
A novel method is introduced for optimal estimation of rigid camera motion from instantaneous velocity measurements. The error surface associated with this problem is highly complex and existing algorithms suffer heavily from local minima. Repeated minimization with different random initializations and selection of the minimum-cost solution are a common (albeit ad hoc) procedure to increase the...
متن کاملSegmenting Independently Moving Objects from Egomotion Flow Fields
We describe a robust algorithm for the estimation of egomotion from noisy optic flow fields. The method is nonlinear, conceptually simple, and corrects for the well-known bias to which many egomotion-estimation algorithms are prone. Furthermore, techniques from robust statistics are employed to render the algorithm insensitive to the presence of large numbers of highly correlated outliers. Thes...
متن کاملA Globally Optimal Approach for 3D Elastic Motion Estimation from Stereo Sequences
Dense and markerless elastic 3D motion estimation based on stereo sequences is a challenge in computer vision. Solutions based on scene flow and 3D registration are mostly restricted to simple non-rigid motions, and suffer from the error accumulation. To address this problem, this paper proposes a globally optimal approach to non-rigid motion estimation which simultaneously recovers the 3D surf...
متن کاملOn the Benefits of Using Gyroscope Measurements with Structure from Motion
This paper is concerned with the benefits of using rotational measurements of a gyroscope in conjunction with optical flow to determine the instantaneous rigid motion. It presents an experimental study focusing on three main aspects: speedup, resolving ambiguities due to local minima and accuracy. For this sake, we developed a method to minimize simultaneously the reprojected optical flow error...
متن کاملReal-time RGB-D-based Object and Manipulator Pose Estimation
We present an overview of our recent work on real-time model-based object pose estimation from intensity and depth cues. We have developed a system that can simultaneously track the pose of hundreds of rigid objects. By incorporating proprioceptive information, objects can be tracked together with their robotic manipulator, enabling accurate visual servo-control even in the presence of severe c...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006