scholarly journals Global localization and relative pose estimation based on scale-invariant features

Author(s):  
J. Kosecka ◽  
Xiaolong Yang
10.5772/5682 ◽  
2007 ◽  
Vol 4 (3) ◽  
pp. 36 ◽  
Author(s):  
Shi Chao-xia ◽  
Hong Bing-rong ◽  
Wang Yan-qing

Efficient exploration of unknown environments is a fundamental problem in mobile robotics. We propose a novel topological map whose nodes are represented with the range finder's free beams together with the visual scale-invariant features. The topological map enables teams of robots to efficiently explore environments from different, unknown locations without knowing their initial poses, relative poses and global poses in a certain world reference frame. The experiments of map merging and coordinated exploration demonstrate the proposed map is not only easy for merging, but also convenient for robust and efficient explorations in unknown environments.


Author(s):  
CHENGGUANG ZHU ◽  
zhongpai Gao ◽  
Jiankang Zhao ◽  
Haihui Long ◽  
Chuanqi Liu

Abstract The relative pose estimation of a space noncooperative target is an attractive yet challenging task due to the complexity of the target background and illumination, and the lack of a priori knowledge. Unfortunately, these negative factors have a grave impact on the estimation accuracy and the robustness of filter algorithms. In response, this paper proposes a novel filter algorithm to estimate the relative pose to improve the robustness based on a stereovision system. First, to obtain a coarse relative pose, the weighted total least squares (WTLS) algorithm is adopted to estimate the relative pose based on several feature points. The resulting relative pose is fed into the subsequent filter scheme as observation quantities. Second, the classic Bayes filter is exploited to estimate the relative state except for moment-of-inertia ratios. Additionally, the one-step prediction results are used as feedback for WTLS initialization. The proposed algorithm successfully eliminates the dependency on continuous tracking of several fixed points. Finally, comparison experiments demonstrate that the proposed algorithm presents a better performance in terms of robustness and convergence time.


2015 ◽  
Vol 112 (29) ◽  
pp. E3950-E3958 ◽  
Author(s):  
Dongsung Huh ◽  
Terrence J. Sejnowski

In a planar free-hand drawing of an ellipse, the speed of movement is proportional to the −1/3 power of the local curvature, which is widely thought to hold for general curved shapes. We investigated this phenomenon for general curved hand movements by analyzing an optimal control model that maximizes a smoothness cost and exhibits the −1/3 power for ellipses. For the analysis, we introduced a new representation for curved movements based on a moving reference frame and a dimensionless angle coordinate that revealed scale-invariant features of curved movements. The analysis confirmed the power law for drawing ellipses but also predicted a spectrum of power laws with exponents ranging between 0 and −2/3 for simple movements that can be characterized by a single angular frequency. Moreover, it predicted mixtures of power laws for more complex, multifrequency movements that were confirmed with human drawing experiments. The speed profiles of arbitrary doodling movements that exhibit broadband curvature profiles were accurately predicted as well. These findings have implications for motor planning and predict that movements only depend on one radian of angle coordinate in the past and only need to be planned one radian ahead.


Author(s):  
Mohini Gawande

The increasing popularity of Social Networks makes change the way people interact. These interactions produce a huge amount of data and it opens the door to new strategies and marketing analysis. According to Instagram and Tumblr, an average of 80 and 59 million photos respectively are published every day, and those pictures contain several implicit or explicit brand logos. Image recognition is one of the most important fields of image processing and computer vision. The CNNs are a very effective class of neural networks that is highly effective at the task of image classifying, object detection and other computer vision problems.in recent years, several scale- invariant features have been proposed in literature, this paper analyzes the usage of Speeded Up Robust Features (SURF) as local descriptors, and as we will see, they are not only scale-invariant features, but they also offer the advantage of being computed very efficiently. Furthermore, a fundamental matrix estimation method based on the RANSAC is applied.


2018 ◽  
Vol 3 (4) ◽  
pp. 2770-2777 ◽  
Author(s):  
Lucas Teixeira ◽  
Fabiola Maffra ◽  
Marco Moos ◽  
Margarita Chli

Sign in / Sign up

Export Citation Format

Share Document