KEYWORDS: Kinematics, 3D modeling, Numerical analysis, Cameras, 3D image processing, 3D image reconstruction, Optical engineering, Filtering (signal processing), Reconstruction algorithms, RGB color model
We propose a real-time pose estimation method that addresses the weaknesses of the numerical inverse kinematics method. Using conventional inverse kinematics based on the numerical method requires many iterations; moreover, a singularity in the Jacobian matrix as well as a local minimum problem can occur. To solve these problems, we propose an inverse kinematics method combined with an unscented Kalman filter (UKF) to recover intermediate joint information. Because the numerical inverse kinematics method optimizes a state, the solution can often converge to the local minimum and require many iterations. We use several sigma points for analysis to find the optimum state by using an unscented transform. The improved method using a UKF converges faster than the numerical inverse kinematics method for the global minimum of the existing inverse kinematics. We use 2-D image processes to extract body areas from the input images, and a 3-D reconstruction algorithm is used to estimate the 3-D positions of the extracted human body area. Using the improved method, we generate intermediate joints for each body part and the results show that the proposed method reduces the computational complexity and increases the accuracy of estimation compared to conventional numerical inverse kinematics.
A keyframe selection algorithm is the process of selecting the essential image for 3-D reconstruction from among many uncalibrated images. Camera autocalibration between images is also essential for 3-D reconstruction. This paper proposes a keyframe selection algorithm that selects the best image to reduce reprojection error. The camera projection matrix in the selected keyframe arises from a full camera autocalibration process. From the camera projection matrix, which is assumed exact, the algorithm calculates the fundamental matrix using algebraic derivation. By this process, false matching is eliminated and finally a 3-D data set is obtained. In our experimental results, the proposed algorithm needs less time than other algorithms; it also has fewer errors in the reconstructed 3-D data. The fundamental matrix that is gained from algebraic derivation takes less time than other algorithms, and it has same average error as the others.
Fundamental-matrix and key-frame selection constitute one of the most important techniques for full 3-D reconstruction of objects from turntable sequences. This paper proposes the new methods for these selection problems in 3-D reconstruction from uncalibrated sequences taken with a turntable and the Fotonovo camera system. Also, we propose a projection-matrix refinement for accurate full 3-D reconstruction. Our approach utilizes single-axis motion. To evaluate the fundamental matrix, camera calibration and 3-D registration are generally needed. Our main contribution is a method for robustly determining the corresponding points between two images, and for accurately filling gaps in a sparse object so as to make surface reconstruction tractable. We do not need all frames, but only few pairs of images (key frames). The key-frame selection has the advantage in camera pose estimation and 3-D scene reconstruction of reducing the computational costs. Experimental results on real image sequences demonstrate accurate object reconstructions and robustness of the proposed methods.