Abstract not found

Abstract. In recent years, 6 Degrees Of Freedom (DOF) Pose Estimation and 3D Mapping is becoming more important not only in the robotics community for applications such as robot navigation but also in computer vision for the registration of large surfaces such as buildings and statues. In both situations, the robot/camera position and orientation must be estimated in order to be used for further alignment of the 3D map/surface. Although the techniques differ slightly depending on the application, both communities tend to solve similar problems by means of different approaches. This article is a guide for any scientist interested in the field since the surveyed techniques have been compared pointing out their pros and cons and their potential applications. 1

In this paper, we designed and implemented a method which can register and integrate range images obtained from different view points for building complete 3D object models. This method contains three major parts: (1) registration of range images and estimation of the parameters of rigid-body transformations, (2) integration of redundant surface patches and generation of triangulated mesh surface models, and (3) reduction of triangular mesh and texture mapping. We developed the RANSACbased DARCES technique to estimate the parameters of the rigid-body transformations between two partially-overlapping range images without requiring initial estimates. Then, we used a circular-ICP procedure to reduce the global registration error. We also used the consensus surface algorithm combined with the marching cube method to generate triangular meshes. Finally, by texture blending and mapping, we can then reconstruct a virtual 3D model containing both geometrical and texture information. Keywords:...

This paper presents a method for fitting a digital line (resp. plane) to a given set of points in a 2D (resp. 3D) image in the presence of outliers. One of the most widely used methods is Random Sample Consensus (RANSAC). However it is also known that RANSAC has a drawback: as maximum iteration number must be set, the solution may not be optimal. To overcome this problem, we present a new method that uses a digital geometric model for lines and planes in a discrete space. Such a digital model allows us to efficiently examine all possible consensus sets, which guarantees the solution optimality and exactness. 1.

Abstract: Problem statement: Multiple cameras are employed for surveillance of larger environment. In such a case there is a need to maintain overlap in the adjacent cameras for correct object registration. Overlap may get disturbed by natural or manual factors. This study proposed an automatic camera pan correction by determining the area of overlap from multi-view images. Approach: A closed loop system which used feature extraction using SIFT, feature matching using descriptor ratio method and Mean Absolute Error (MAE) over Gaussian scale space, followed by overlap estimation is implemented for restoring the camera position. Results: The proposed method was experimented with the datasets acquired in the environment where surveillance involves two cameras. The matched points of the two images were used to calculate the overlap percentage. The overlap percentage estimated by the surveillance server was communicated to the pan controller to re-orient the camera to its original position. Conclusion: The proposed algorithm identified the robust and distinctive features that are invariant to translation, rotation and scaling. These features help in the accurate estimation of overlap percentage, which is further used to automatically correct the pan of the camera.

Abstract not found

Abstract not found

Abstract not found

In this paper, we introduce a novel approach for global registration of partially overlapping point clouds. The approach identifies feature points of matching objects based on surface-approximating polynomials and finds an initial transformation depending on these polynomials. We compute an extended set of rotationally-invariant features for polynomials. In contrast to purely feature-based approaches, we do not only compute transformations based on the invariant properties of polynomials, but actually transform the polynomials into a common coordinate system and compare the transformed coefficients. This results in an improved correspondence analysis of local surfaces. Hence, using transformed polynomials, we gain more discriminating information about different structures. Therefore, the approach can handle partial scans of different objects simultaneously. Each partial scan is assigned to one of the objects and registered accordingly. Moreover, the approach is robust against noise and can process real data.

Abstract — We propose a novel method to enhance a family of ICP(iterative closest point) algorithms by updating velocity. Even though ICP algorithms play a dominant role in a model based tracking, it is difficult to avoid an accumulated tracking error during a continuous motion. It is because that typical ICP algorithms assumes that each of the point in one scan are measured simultaneously while most of the available rangefinders measure each point sequentially. Hence conventional ICP algorithms are prone to be erroneous under a fast motion and an accumulated error during the motion cannot be ignored in many cases. In our approach, we estimate a velocity of a rangefinder numerically over ICP iterations. As a result, distortion of a scan due to the motion can be compensated using estimated velocity. In addition, outliers are effectively rejected during the iteration of velocity update, which means that more accurate and robust motion is trackable. Also we verify a performance and an accuracy of our method by demonstrating simulation and real-world experiment results. I.