Building a sonar map in a specular environment using a singlemobile sensor

The physical properties of acoustic sensors are exploited to obtain information about the environment for sonar map building. A theoretical formulation for interpreting the sensor databases on the physical principles of acoustic propagation and reflection is presented. A characterization of the sonar scan that allows the differentiation of planes, corners, and edges in a specular environment is described. A single sensor mounted on an autonomous vehicle in a laboratory verifies the technique. The implications for sonar map building and the limitations of differentiating elements with one sensor are discussed     

Differentiating walls from corners using the amplitude of ultrasonic echoes

This paper analyzes the use of ultrasonic echo amplitudes to evaluate the characteristics of the detected surfaces (such as distinguishing between walls and corners). The shape and surface characteristics of the environment, such as roughness or absorption coefficient, as well as the distance and the angle of incidence, have high influence on the amplitude of the echoes. As a consequence, the amplitude of the received echoes has received little attention from robotic researchers. Instead, time-of-flight (ToF) has been used as the main source of information of the environment. It is also well known that the shape of the echoes of a corner is the same as that of a wall [IEEE Trans. Pattern Anal. Mach. Intell. (PAMI), 12 (1990) 560]. Several authors have proposed special multi-transducer configurations to avoid this problem. This paper studies the amplitude of received echoes and presents a simple model to predict the shape and amplitude of echoes received from different materials in environments composed of walls and corners. Using this model, and analysing the amplitude of the echoes it is possible to distinguish between walls and corners in a single scan of a single ultrasonic transducer pair. The parameters of the model were obtained from tests performed on different materials and surfaces. The last section of the paper shows the experimental results of the wall–corner classifications obtained in real tests during the walk of a mobile robot. The results suggest that the method proposed can be of great interest for map building in robotics.     

基于低成本超声传感器的无线传感网生存环境地图构建研究

移动传感器网络节点在监测环境过程中,采集到大量有误差的环境地图数据,导致构建的传感器网络生存环境地图质量低、实时性差.针对以上问题,提出了一种适用于低成本、轻数据量、多网络节点的基于超声传感器组的环境地图构建算法.首先对超声波测量数据进行高斯滤波处理,其次利用处理后的数据进行单一网络节点所属区域地图的构建,再次提取单一节点地图的点特征,并进行匹配,进而得到融合后的全局地图,最终实现传感器网络节点生存环境地图的构建.进一步通过优化子图拼接顺序,降低了构图数据与实际环境数据的误差,提高了传感器网络节点生存环境的地图质量.     

二值图像中拐点的实时检测算法

鉴于数字图像中的拐点通常成为重要的信息载体,因此准确、稳定和实时地检测出拐点便成为拐点检测算法面临的主要问题,针对该问题,提出了一种新的二值图像中拐点的实时检测算法。该算法与传统基于边界链码的拐点检测算法不同,其是首先构建像素的k(k>8)邻域,并将图像中物体的边界表示为k邻域链码;然后根据曲率定义的差分形式计算各边界点处的曲率;最后通过检测曲率直方图的局部峰值精确定位出拐点,并利用拐角内部像素的颜色统计信息迅速判断出拐点的凸凹性.为验证该算法的效果,给出了该算法与4种已有算法的对比实验.结果表明,该算法不仅稳定性、准确性较高,而且算法简单,实时性强,并适合于嵌入式计算环境。     

Classification of reflectors with an ultrasonic sensor for mobile robot applications

This paper describes a sensor model made up of four ultrasonic transducers able to classify reflectors (wall, edge or corner) in specular environments. The main goal has been to effect the classification from a single reading cycle: emission of ultrasounds and reception of echoes (measuring only times of flight—TOFs). Working from the four TOFs obtained after a single emission of ultrasounds (thereby facilitating its practical implementation in a mobile robot, when readings are taken while the robot is moving), an algorithm has been proposed for discriminating between edge and plane type reflectors. The configuration of the four transducers enabled dependent discriminating functions to be determined directly from the quadratic terms of the TOFs, without the need for previous geometric transformations. Special attention was given to the effect of the separation between the sensor transducers and the reading-associated noise. Finally, some considerations have been pointed out about the possibility of two transducers emitting, so allowing discrimination between walls and corners.     

角点测度在月球表面多光谱图像融合中的应用

根据Harris角点检测原理,提出角点测度的概念,并以角点测度响应值作为高频图像融合系数的选择依据,进而提出基于图像冗余小波域的角点测度重要中心系数算法。算法首先利用冗余小波变换把多光谱图像分解成小波平面和相似平面,然后利用角点测度响应函数来估计小波平面的角点测度,用基于角点测度响应值的重要中心系数融合规则融合小波平面。对相似平面则采取加权平均的融合规则,最后通过冗余小波逆变换得到融合图像。在实验中,用Clementine月球表面多光谱数据和SPOT5多光谱数据验证了算法的有效性,并和其他方法做了比较,除了基于视觉的主观比较以外,还引入了标准差、熵、清晰度和相关系数等客观评价指标对融合结果进行评价,结果表明,算法有效地保持了原图像的细节特征,如边缘、角点等。     

Feature extraction method for a robot map using neural networks

Many map-building algorithms using ultrasonic sensors have been developed for mobile robot applications. In indoor environments, the ultrasonic sensor system gives some uncertain data. To compensate for this effect, a new feature extraction method using neural networks is proposed. A new, effective representation of the target is defined, and the reflection wave data patterns are learnt using neural networks. As a consequence, the targets are classified as planes, corners, or edges, which all frequently occur in indoor environments. We constructed our own robot system for the experiments which were carried out to show the performance. This work was presented in part at the 7th International Symposium on Artificial Life and Robotics, Oita, Japan, January 16–18, 2002     

Using PCA in time-of-flight vectors for reflector recognition and 3-D localization

This paper presents a reflector recognition and localization technique in three-dimensional (3-D) environments, using only times-of-flight (TOFs) data obtained from ultrasonic transducers. The recognition and localization technique is based on the principal component analysis applied to the TOF vectors originating from a sensor that contains two emitting transducers and several receivers. The two emitters simultaneously transmit two coded pulses that are detected later on and discriminated by the receivers, after being reflected in the environment. The proposed technique allows for the possibility of not only recognizing the reflectors, but also estimating approximately its localization referred to the sensor. This technique has been tested with three types of reflectors in 3-D environments: planes, edges, and corners. The achieved results are very satisfactory for reflectors located in the range 50-350 cm.     

基于角点采样的多目标跟踪方法

为了跟踪互遮挡的多个目标,提出了一种基于角点采样的多目标跟踪方法。该方法以遮挡发生前的各目标区域中的Harris角点信息为样本,在遮挡发生情况下,采取K近邻分类器对目标区域中提取的角点信息进行分类,以有效区分遮挡在一起的多个目标。在角点特征提取过程中,还提出了双阈值Harris角点检测算法,用于自适应、准确地提取运动区域中角点信息。实验结果表明,该方法能有效区分遮挡在一起,且没有分裂之前的多个目标。     

基于多尺度Harris角点SAM的医学图像配准算法

为满足医学图像配准对多分辨率,高配准率,低时耗率的高要求,提出了一种新颖的基于多尺度Harris角点方根-算术均值距离（SAM）的配准算法。该算法通过对图像进行小波多尺度积边缘检测和多尺度Harris角点检测,首先得到了估计变换参数;然后利用角点间的SAM作为相似性测度函数来获得最佳匹配点对,并通过最小二乘得到最终配准参数。实验表明,算法可实现含噪声图像以及不同分辨率的多模医学图像的配准,由于算法只对角点匹配,无须最优搜索,从而不仅大大减少了计算量,而且避免了陷入局部极值的情况。最后,通过3类实验验证了算法的可行性和鲁棒性。     

多特征复合的角点提取方法

提出了一种利用图象灰度特征和边界轮廓点特征相复合的角点检测方法；首先在SUSAN特征检测原则基础上，提出了基于图象灰度特征的快速自适应特征检测方法，用以提取不同图象对比度下目标轮廓上的初角点，利用边沿元对这些包含了部分边缘点的初角点沿边绝缘方向跟踪排序后，再由根据图象边缘特征检测的边界方向变化情况来确定角点位置，同时剔除由于图象数字化而导致的虚假角点，这种方法克服了单一特征提取角点所带来的弊病，提高了角点检测的精度，抗噪能力强，运算量较小，适于实时实现。     

近邻传播聚类优化的角点检测改进算法

针对传统Harris角点检测算法和目前一些改进算法应用在图像拼接时,仍然可能存在只可在单一尺度上检测、角点位置不准确、伪检和对噪声敏感致使检测率不高等缺点,提出一种基于AP聚类角点提取优化的双边滤波（BF）角点检测改进算法。该算法在对图像进行双边滤波和多尺度角点检测的基础上,采用一种新型的聚类算法--近邻传播聚类算法（AP聚类算法）,对候选角点提取真实角点的效率进行优化,并对角点算子进行改进。实验是在VS2010+OpenCV平台实现的。结果表明提出的改进算法不仅提高了角点提取效率,而且更加精确地检测图像角点,具有更好的效果,更强的实用性。     

基于B样条的改进型Harris角点检测算法

在研究Harris角点检测算法时发现由于该算法采用高斯低通滤波进行平滑,因而对一些图像进行角点提取时,存在角点信息丢失和位置偏移等现象,而B样条函数可以收敛于高斯函数,并具有良好的逼近能力和紧支性等一些优秀的性质,从而基于B样条函数提出了一种改进的Harris角点提取方法.实验表明,该方法对提取角点非常有效.     

Self-localization and obstacle avoidance for a mobile robot

This article presents a fast self-localization method based on ZigBee wireless sensor network and laser sensor, an obstacle avoidance algorithm based on ultrasonic sensors for a mobile robot. The positioning system and positioning theory of ZigBee which can obtain a rough global localization of the mobile robot are introduced. To realize accurate local positioning, a laser sensor is used to extract the features from environment, then the environmental features and global reference map can be matched. From the matched environmental features, the position and orientation of the mobile robot can be obtained. To enable the mobile robot to avoid obstacle in real-time, a heuristic fuzzy neural network is developed by using heuristic fuzzy rules and the Kohonen clustering network. The experiment results show the effectiveness of the proposed method.     

一种自动检测棋盘角点的新算法

提出了一种自动获取棋盘角点的新算法。该方法采用由粗到精的多层次检测策略，通过综合使用Radon变换、Harris算子以及Forstner算子，能够快速准确地提取出图像中的棋盘点。与传统方法相比，该算法具有两个明显的优点：无须人工干预，能够自动确定角点位置；定位精度高，角点的平均位置偏差在0.1个像素以内。     

基于图像角点特征的第二代水印算法研究

提出了一种新颖的基于图像角点特征的第2代水印算法。该方法首先将水印图像进行置乱预处理,其次对载体图像进行小波3级提升,然后利用第2步的结果和多尺度曲率积角点检测（MSP）方法,提取出图像最低频成分中的角点,最后在角点位置对应的所有高频系数中嵌入水印。检测时,在这些系数上做水印嵌入的逆运算,并用事先得到的密钥反变换出水印。实验结果表明,所提出的水印算法较第1代数字水印算法不仅在运行速度上大大提高,而且在抵抗旋转、放缩、平移、裁剪等几何攻击方面的鲁棒性也有显著提高。     

Concurrent Map Building and Behavior Learning for Navigation in Unknown Environments

In this paper, we report a robust and low-cost navigation algorithm for an unknown environment based on integration of a grid-based map building algorithm with behavior learning. The study focuses on mobile robots that utilize ultrasonic sensors as their prime interface with the outside world. The proposed algorithm takes into account environmental information to augment the readings from the low angular accuracy sonar measurements for behavior learning. The environmental information is obtained by an online grid-based map learning design that is concurrently operating with the behavior learning algorithm. The proposed algorithm is implemented and tested on an in-house-built mobile robot, and its performance is verified through online navigation in an indoor environment.     

基于USAN的改进的角点检测算法

提出了一种基于USAN的改进的角点检测算法。该算法在原有SUSAN算法的基础上做了如下改进：使用一个3×3的方形预检测窗口对图像的像素进行预检测，在精确检测角点前剔除掉大部分的背景点、边界点及脉冲噪声点，提高了算法的效率；根据图像不同区域对比度不同的特性，采用根据对比度自动调节核心点与其邻域像素的灰度差值门限的方法，使所检测出的角点分布均匀；利用基于USAN定义的角点所应具有的特征(角的边缘及USAN的连续性)来剔除伪角点，降低了角点虚报和漏检的发生率。仿真实验证明了该文所提出的算法具有抗噪能力强、运算量小的特点，适于实时实现。     

Harris角点检测的优化算法

针对Harris角点检测算法中提取出较多的伪角点和计算量大的问题,提出了一种基于Harris角点检测的改进算法. 为抑制Harris角点检测中的伪角点数目并且提高算法的效率,首先加入预筛选得到候选角点,在计算水平和垂直方向梯度时,对于梯度较小的像素点进行预处理,在进行非极大值抑制时采用自适应阈值,提高算法自适应性,最后利用USAN对角点进行进一步选择. 实验结果表明,改进的Harris角点检测算法不仅提高了检测精度和效率,而且对噪声具有一定的鲁棒性.