Mobile Robot Navigation Using Sonar and Range Measurements from Uncalibrated Cameras

A novel, simple and efficient method for vision based range measurements with uncalibrated cameras is presented. Required parameters are the image size, the relative distance between two different image frames of the same scene and the field of view of the camera(s). Range measurements acquired using ultrasonic sensors and a vision system have been used to navigate a mobile robot around known colored obstacles in an indoor environment. Both sonar sensors and cameras are activated and they operate simultaneously in parallel to obtain range measurements from common search areas located in the front of the mobile robot. Experimental results using a parallel stereoscopic, rotated and monocular vision system with uncalibrated cameras confirm that the maximum computational error (as well as the normalized root mean square error) of range measurements using the vision system for obstacles lying at a distance of 27–800 cm from the robot, is smaller compared to other similar, even more advanced and state-of-the-art existing approaches, reported in Rajagopalan (IEEE Trans. Pattern Anal. Mach. Intell., 28(11): 1521–1525, 2004), Mudenagudi and Chaudhuri (Proceedings of IEEE International Conference on Computer Vision, 1: 483–488, 1999), Umeda and Takahashi (Proceedings of IEEE ICRA, pp. 3215–3220, April 2000), Jiang and Weymouth (Proceedings of IEEE CVPR, pp. 250–255, June 1989), Lai, Fu, and Chang (IEEE Trans. Pattern Anal. Mach. Intell., 14(4):405–411, 1992), Malis and Rives (Proceedings of IEEE ICRA, pp. 1056–1061, 2003), Derrouich, Izumida, and Shiiya (IEEE Annual Conference on IECON, 3: 2191–2196, Nov. 2002).     

环境特征提取在移动机器人导航中的应用

针对移动机器人在未知结构化环境中导航的需要,采用2D激光雷达作为主要传感器,对诸如墙壁、拐角、出口等这些典型的环境特征分别设计了一套有效的特征提取算法,并在该算法的基础上提出了基于特征点的移动机器人导航策略.该策略不需要里程计等其他一些内部传感器的信息,并且也不依赖具体的环境表述模型,从激光雷达扫描一次所得的数据中即可提取出环境特征,从而来指引机器人导航,实现起来快速可靠.应用到移动机器人MORCS-1上进行实验,取得了满意的结果,算法的实时性与鲁棒性得到了验证.     

基于移动应用的智能配网调度视频及图像感知系统设计

为解决目前配网调度中无法直观掌握网络运行以及操作流程等问题,提出了基于移动应用的配网调度视频作业以及调度图像感知方法.首先分析了调度业务对实时可视化的需求,然后分析了移动应用技术和图像感知技术的原理和智能配网调度的形式和业务.设计了基于移动应用的配网调度视频作业平台的系统构架和功能构架,详细说明了移动应用模块的内容和组...     

Robot Navigation Based on Discrimination of Artificial Fields: Application to Robot Formations

In the preceding paper, a method for mobile robot navigation control based on discrimination of multiple artificial fields was introduced. In this second paper, the method is extended to robot formations. Experimental demonstrations are presented taking examples of four types of formations. The experiments cover formation initialization, maneuvering, obstacle avoidance and formation switching.     

Representation of High Resolution Images from Low Sampled Fourier Data: Applications to Dynamic MRI

In this work we propose the use of B-spline functions for the parametric representation of high resolution images from low sampled data in the Fourier domain. Traditionally, exponential basis functions are employed in this situation, but they produce artifacts and amplify the noise on the data. We present the method in an algorithmic form and carefully consider the problem of solving the ill-conditioned linear system arising from the method by an efficient regularization method. Two applications of the proposed method to dynamic Magnetic Resonance images are considered. Dynamic Magnetic Resonance acquires a time series of images of the same slice of the body; in order to fasten the acquisition, the data are low sampled in the Fourier space. Numerical experiments have been performed both on simulated and real Magnetic Resonance data. They show that the B-splines reduce the artifacts and the noise in the representation of high resolution Magnetic Resonance images from low sampled data. This work was supported by the Italian MIUR project Inverse Problems in Medical Imaging 2004–2006 (grant no 2004015818). Germana Landi received the BS degree in Mathematics from the University of Bologna in 1997 and the Ph.D. degree in Computational Mathematics from the University of Padova in 2000. She is currently a postdoctoral researcher in Numerical Analysis at the Department of Mathematics of the University of Bologna. Her research interests include medical imaging and inverse ill-posed problems. Elena Loli Piccolomini received the BS degree in Mathematics from the University of Bologna in 1988. She is an associate professor in Numerical Analysis at the Department of Mathematics of the University of Bologna. Her research interests include numerical methods for the regularization of discrete ill-posed problems with application to medical imaging (MR, TAC, SPECT, PET).     

Plan Execution Based on Active Perception: Adding Hints to Plans

In this paper we present a complete control architecture for a mobile robot which enables it to achieve a set of proposed goals with a high degree of autonomy and to react to the changing environment in real time. Autonomy and robustness are achieved through careful selection and incremental implementation of a set of basic Motor-Behaviors that interpret the sensor readings (sonar, vision and odometric sensors) and actuate the motors. The plan is provided by a user, and is expressed as a sequence of goals and a series of hints on how to achieve them. These hints are based on the user's knowledge of the environment and of the robot's behavioral and perceptual abilities. A new set of behaviors, called Conductor-Behaviors, which inspect and modify Motor-Behaviors' attributes, have been introduced in order to link the robot's Motor-Behaviors to the user's plan. Finally, a canonical set of symbols, attached to the Motor-Behaviors, serves as well grounded symbols that the user can utilize to express the plans. We also report experimental results with a real robot that demonstrate how plans expressed as goals and hints to achieve them improve the robot's performance.     

Watershed from propagated markers: An interactive method to morphological object segmentation in image sequences

In this paper, it is introduced an interactive method to object segmentation in image sequences, by combining classical morphological segmentation with motion estimation – the watershed from propagated markers. In this method, the objects are segmented interactively in the first frame and the mask generated by its segmentation provides the markers that will be used to track and segment the object in the next frame. Besides the interactivity, the proposed method has the following important characteristics: generality, rapid response and progressive manual edition. This paper also introduces a new benchmark to do quantitative evaluation of assisted object segmentation methods applied to image sequences. The evaluation is done according to several criteria such as the robustness of segmentation and the easiness to segment the objects through the sequence.     

Controlled Processes: Methods of Investigation and Applications

This paper is a review of results of control theory and the theory of dynamic games over the period of existence of the Cybernetics Institute. Basic results that are widely applied and directions that underlie further investigations are emphasized.     

Mining of Moving Objects from Time-Series Images and its Application to Satellite Weather Imagery

The framework of mining of moving objects from image data sequence is presented. Scenes are first clustered and labeled by using two-stage SOM that is modified to recognize images including similar moving objects as the same cluster, and that well recognizes scenes including prominent objects. After extraction of images which include prominent objects based on clustering result, the position and the shape of objects are approximated by using mixture gaussian model via EM algorithm, providing the adequate or larger number of components. By adopting the average of the data points in the smaller blocks as the initial parameters, the solutions are stabilized and the identification of components among time-series images and the tracking of a specific object become easier.This framework is applied to a four-year (ranging from 1997 to 2000) dataset of cloud images taken by Japanese weather satellite GMS-5 to evaluate its performance. Modified SOM method well classifies scenes which include prominent moving object, and seasonal variation tendency is detected in the cluster ID sequence. The result of object detection via EM algorithm for summer-type images including clear cloud masses such as typhoons shows that this approach well approximate the adequate distribution of cloud masses in many cases. Objects in the very irregular shapes are also well represented as the mixtures of gaussians.The extracted object information, together with the scene clustering result, is expected to offer us a rich source for knowledge discovery of video datasets. This approach is one of the effective ways of mining video images whose characteristics are unknown in advance, and thus applicable to the various type of applications.     

Weakly Constrained Minimization: Application to the Estimation of Images and Signals Involving Constant Regions

We focus on the question of how the shape of a cost-function determines the features manifested by its local (and hence global) minimizers. Our goal is to check the possibility that the local minimizers of an unconstrained cost-function satisfy different subsets of affine constraints dependent on the data, hence the word weak. A typical example is the estimation of images and signals which are constant on some regions. We provide general conditions on cost-functions which ensure that their minimizers can satisfy weak constraints when noisy data range over an open subset. These cost-functions are non-smooth at all points satisfying the weak constraints. In contrast, the local minimizers of smooth cost-functions can almost never satisfy weak constraints. These results, obtained in a general setting, are applied to analyze the minimizers of cost-functions, composed of a data-fidelity term and a regularization term. We thus consider the effect produced by non-smooth regularization, in comparison with smooth regularization. In particular, these results explain the stair-casing effect, well known in total-variation methods. Theoretical results are illustrated using analytical examples and numerical experiments.     

The Contracting Curve Density Algorithm: Fitting Parametric Curve Models to Images Using Local Self-Adapting Separation Criteria

The task of fitting parametric curve models to the boundaries of perceptually meaningful image regions is a key problem in computer vision with numerous applications, such as image segmentation, pose estimation, object tracking, and 3-D reconstruction. In this article, we propose the Contracting Curve Density (CCD) algorithm as a solution to the curve-fitting problem.The CCD algorithm extends the state-of-the-art in two important ways. First, it applies a novel likelihood function for the assessment of a fit between the curve model and the image data. This likelihood function can cope with highly inhomogeneous image regions, because it is formulated in terms of local image statistics. The local image statistics are learned on the fly from the vicinity of the expected curve. They provide therefore locally adapted criteria for separating the adjacent image regions. These local criteria replace often used predefined fixed criteria that rely on homogeneous image regions or specific edge properties. The second contribution is the use of blurred curve models as efficient means for iteratively optimizing the posterior density over possible model parameters. These blurred curve models enable the algorithm to trade-off two conflicting objectives, namely heaving a large area of convergence and achieving high accuracy.We apply the CCD algorithm to several challenging image segmentation and 3-D pose estimation problems. Our experiments with RGB images show that the CCD algorithm achieves a high level of robustness and sub-pixel accuracy even in the presence of severe texture, shading, clutter, partial occlusion, and strong changes of illumination.     

A semi-parametric approach for mixture models: Application to local false discovery rate estimation

A procedure to estimate a two-component mixture model where one component is known is proposed. The unknown part is estimated with a weighted kernel function. The weights are defined in an adaptive way. The convergence to a unique solution of our estimation procedure is proven. The procedure is compared with two classical approaches using simulation. In addition, the results obtained are applied to multiple testing procedure in order to estimate the posterior population probabilities and the local false discovery rate.