Vision-based force measurement

This paper demonstrates a method to visually measure the force distribution applied to a linearly elastic object using the contour data in an image. The force measurement is accomplished by making use of the result from linear elasticity that the displacement field of the contour of a linearly elastic object is sufficient to completely recover the force distribution applied to the object. This result leads naturally to a deformable template matching approach where the template is deformed according to the governing equations of linear elasticity. An energy minimization method is used to match the template to the contour data in the image. This technique of visually measuring forces we refer to as vision-based force measurement (VBFM). VBFM has the potential to increase the robustness and reliability of micromanipulation and biomanipulation tasks where force sensing is essential for success. The effectiveness of VBFM is demonstrated for both a microcantilever beam and a microgripper. A sensor resolution of less than +/-3 nN for the microcantilever and +/-3 mN for the microgripper was achieved using VBFM. Performance optimizations for the energy minimization problem are also discussed that make this algorithm feasible for real-time applications.     

Vision-based vehicle guidance

This implementation of lane and obstacle detection for an autonomous, self-guided vehicle succeeds by tailoring vision and computational techniques to an affordable SIMD architecture. The authors use a geometrical transform called inverse perspective mapping (IPM). Using a priori knowledge of both the scene and the acquisition device, the IPM technique allows one to remove the perspective effect and produce a new image in which the information content is homogeneously distributed among all pixels. In the remapped image, the amount of information carried by each pixel no longer depends on the pixel's position, making the SIMD approach practical     

An enhanced force and contact position sensor for micro-manipulations

In micro-manipulations, force sensing devices play an important role in the control and the assembly of micro-objects. To protect these micro-objects from damage, we must have the ability to detect the value of the minute amount of interactive force (about a few μN) upon contact between the tip and the object. To detect this micro-force, we need an optimized design of force sensor to increase the strain values at the positions we place sensing components. Stress concentration can effectively amplify the strain values measured by the force sensors. This paper investigates the effect that the notches have on increasing the strain values at the positions we attach the sensing elements. In addition, the optimal design with a flexible structure improves the sensitivity of the sensor. An algorithm that can calculate both contact force and contact position on the sensor tip is also mentioned. Besides, an optimal location of strain gauges will ensure the accuracy and stability of the measurement. Finally, analysis and experiment are done to verify the proposed idea. Recommended by Editorial Board member Dong Hwan Kim under the direction of Editor Jae-Bok Song. This research was supported by the Ministry of Knowledge Economy and Korean Industrial Technology Foundation through the Human Resource Training Project for Strategic Technology. Tri Cong Phung received the B.S. degree in Mechanical Engineering from the HCM University of Technology, Vietnam in 2004 and the M.S. degree in Mechanical Engineering from Sungkyunkwan University in 2007. He is currently working toward a Ph.D. degree in Intelligent Robotics and Mechatronic System Laboratory (IRMS Lab), Mechanical Engineering from Sungkyunkwan University. His research interests include dexterous manipulation and touch sensors. Seung Hwa Ha received the B.S. degree in Korean University of Technology and Education, Korea in 2004. He received the M.S. degree in Mechanical Engineering from Sungkyunkwan University in 2008. He is currently working in Samsung Electronic Co. Ltd. His research interests are about strain gauge and high precision control. Yong Seok Ihn received the B.S. degree in School of Mechanical Engineering from the Sungkyunkwan University, Korea in 2006. He received the M.S. degree in Mechanical Engineering from the Sungkyunkwan University, in 2008. He is currently working toward a Ph. D. degree in the Computer Aided Modeling & Simulation Laboratory (CAMAS Lab), School of Mechanical Engineering at the Sungkyunkwan University in Korea. His research interests are precision mechatronics, dynamic system modeling, and control. Byung June Choi received the B.S. degree in School of Mechanical Engineering from the Sungkyunkwan University, Korea in 2002. He received the M.S. degree in Mechanical Engineer-ing from the Sungkyunkwan University, in 2005. He is currently working toward a Ph.D. degree in the Intelligent Robotics and Mechatronic System Laboratory (IRMS Lab), School of Mechanical Engineering at the Sungkyunkwan University in Korea. His research interests are mechanisms design, multi-robot system control, cooperation, path planning and task allocation algorithm. Sang Moo Lee was born in Seoul, Korea and educated in Seoul. He received the Ph.D. degree from the Seoul National University in Korea, in 1999. He is currently a Principal Researcher of Division for Applied Robot Technology at Korean Institute of Industrial Technology. His research interests include high-precision robot control, motion field network, and location system in outdoor environment for robots. Ja Choon Koo is an Associate Professor of School of Mechanical Engineering in Sungkyunkwan University in Korea. His major researches are in the field of design, analysis, and control of dynamics systems, especially micro precision mechatronic systems and energy transducers. He was an Advisory Engineer for IBM, San Jose, California, USA and a Staff Engineer for SISA, San Jose, CA, USA. He received the Ph.D. and M.S. degrees from the University of Texas at Austin and the B.S. from Hanyang University, Seoul, Korea. Hyouk Ryeol Choi received the B.S. degree from Seoul National University, Seoul, Korea, in 1984, the M.S. degree from Korea Advanced Institute of Science and Technology (KAIST), Daejon, Korea, in 1986, and the Ph.D. degree from Pohang University of Science and Technology (POSTECH), Pohang, Korea, in 1994, all in Mechanical Engineering. From 1986 to 1989, he was an Associate Engineer at LG Electronics Central Research Laboratory, Seoul. From 1993 to 1995, he was at Kyoto University, Kyoto, Japan, as a Grantee of scholarship from the Japanese Educational Ministry. From 2000 to 2001, he visited Advanced Institute of Industrial Science Technology (AIST), Tsukuba, Japan, as a Japan Society for the Promotion of Sciences (JSPS) Fellow. Since 1995, he has been with Sungkyunkwan University, Suwon, Korea, where he is currently a Professor in the School of Mechanical Engineering. He is an Associate Editor of the Journal of Intelligent Service Robotics and International Journal of Control, Automation and Systems (IJCAS), and IEEE Transactions on Robotics. His current research interests include dexterous mechanism, field application of robots, and artificial muscle actuators.     

Vision-based sparse topological mapping

Most of the existing appearance-based topological mapping algorithms produce dense topological maps in which each image stands as a node in the topological graph. Sparser maps can be built by representing groups of visually similar images of a sequence as nodes of a topological graph. In this paper, we present a sparse/hierarchical topological mapping framework which uses Image Sequence Partitioning (ISP) to group visually similar images of a sequence as nodes which are then connected on the occurrence of loop closures to form a topological graph. An indexing data structure called Hierarchical Inverted File (HIF) is proposed to store the sparse maps so as to perform loop closure at the two different resolutions of the map namely the node level and image level. TFIDF weighting is combined with spatial and frequency constraints on the detected features for improved loop closure robustness. Our approach is compared with two other existing sparse mapping approaches which use ISP. Sparsity, efficiency and accuracy of the resulting maps are evaluated and compared to that of the other two techniques on publicly available outdoor omni-directional image sequences.     

Vision-based robotic convoy driving

This article describes a method for vision-based autonomous convoy driving in which a robotic vehicle autonomously pursues another vehicle. Pursuit is achieved by visually tracking a target mounted on the back of the pursued vehicle. Visual tracking must be robust, since a failure leads to catastrophic results. To make our system as reliable as possible, uncertainty is accounted for in each measurement and propagated through all computations. We use a best linear unbiased estimate (BLUE) of the target's position in each separate image, and a polynomial least-mean-square fit (LMSF) to estimate the target's motion. Robust autonomous convoy driving has been demonstrated in the presence of various lighting conditions, shadowing, other vehicles, turns at intersections, curves, and hills. A continuous, autonomous, convoy drive of over 33 km (20 miles) was successful, at speeds averaging between 50 and 75km/h (30–45 miles/h).     

Vision-based clad height measurement

The laser deposition process is useful for part creation, repair, and hard facing. To maintain consistent clad height in the presence of process uncertainties measurement and control is required. This work presents a vision-based clad height measurement technique that utilizes a CCD camera and a line laser to measure the complete clad profile. Unique line detection and spur trimming algorithms are presented that extract measurement data efficiently. The effectiveness of the measurement approach is validated through examples.     

一种基于视觉的道路检测算法

计算机视觉导航使移动机器人可以工作于复杂环境中,而道路检测是其中的关键环节。针对道路的多样性和环境因素的影响,提出了一种稳健的道路检测算法。依据道路特征把图像分为3组区域：路、非路和不确定区域,然后对难以判断的不确定区域使用假设检验的策略,依据道路的形状、路宽和面积信息综合判断,把不确定区域合并到路或者非路区域,从而快速准确地检测出道路。该算法已经在移动机器人-ATRV上测试和使用。     

基于视觉的目标定位技术的研究进展

基于视觉的目标定位是目前计算机视觉领域的研究热点。就现阶段基于视觉的定位技术进行了综述,着重介绍了基于单目视觉定位、基于双目视觉定位和基于全景视觉定位3类定位技术的研究现状,并分析了各自的优缺点。最后就基于视觉定位方法的发展趋势做了简要分析,以期为以后基于视觉定位问题的研究提供参考。     

基于视觉密码的物联网身份认证技术研究

随着物联网＂十二五＂规划的发布,物联网这个新型产业走进人们的日常生活中,同时物联网所带来的安全问题也引起广泛关注。该文通过对物联网架构中感知层所存在安全漏洞的分析,结合视觉密码可验证身份的性质,给出了具体的视觉密码身份认证方案。     

Vision-based multi-UAV position estimation

This paper describes a method for vision-based unmanned aerial vehicle (UAV) motion estimation from multiple planar homographies. The paper also describes the determination of the relative displacement between different UAVs employing techniques for blob feature extraction and matching. It then presents and shows experimental results of the application of the proposed technique to multi-UAV detection of forest fires.     

Vision-based entrance detection in outdoor scenes

Doors are a significant object for the visually impaired and robots to enter and exit buildings. Although the accuracy of door detection is reported high in indoor scenes, it has become a difficult problem in outdoor scenes in computer vision. The reason may lie in the fact that such properties of a simple ordinary door such as handles, corners, and the gap between the door and the ground may not be visible due to the great variety of doors in outdoor environments. In this paper, we present a vision-based method for detecting building entrances in outdoor images. After extracting the lines and deleting the extra ones, regions between the vertical lines are specified and the features including height, width, location, color, texture and the number of lines inside the regions are obtained. Finally, some additional knowledge such as door existence at the bottom of the image, a reasonable height and width of a door, the difference between color and texture of the doors and those of the neighboring regions, and numerous lines on doors is used to decide on door detection. The method was tested on the eTRIMS dataset, door images from the ImageNet dataset, and our own dataset including doors of houses, apartments, and stores leading to acceptable results. The obtained results show that our approach outperforms comparable state-of-the-art approaches.     

基于单目视觉的车辆检测算法研究

本文在全面总结现有的国内外前方行驶车辆的视觉检测算法的基础上,利用由于光照因素使得前方车辆在图像内形成的底部阴影这一先验知识,建立了基于车辆阴影区域检测的前方障碍物视觉检测算法。     

面向视觉交互的室内肤色建模研究

肤色检测是视觉交互技术中的重要环节.本文通过分析室内光照条件下的肤色分布特性,提出了基于Ada-boost的肤色建模技术,实现了肤色建模过程与颜色空间选择的有机结合,所构建的特征空间具有良好的类别区分性,弥补了传统方法仅能针对特定颜色空间进行肤色建模的不足.多种肤色建模方法性能比较实验表明:本文所提出的方法能更好地满足视觉交互对识别率和实时性的要求.     

Vision-based control of near-obstacle flight

This paper presents a novel control strategy, which we call optiPilot, for autonomous flight in the vicinity of obstacles. Most existing autopilots rely on a complete 6-degree-of-freedom state estimation using a GPS and an Inertial Measurement Unit (IMU) and are unable to detect and avoid obstacles. This is a limitation for missions such as surveillance and environment monitoring that may require near-obstacle flight in urban areas or mountainous environments. OptiPilot instead uses optic flow to estimate proximity of obstacles and avoid them. Our approach takes advantage of the fact that, for most platforms in translational flight (as opposed to near-hover flight), the translatory motion is essentially aligned with the aircraft main axis. This property allows us to directly interpret optic flow measurements as proximity indications. We take inspiration from neural and behavioural strategies of flying insects to propose a simple mapping of optic flow measurements into control signals that requires only a lightweight and power-efficient sensor suite and minimal processing power.     

基于视觉的遥操作机器人精密装配系统

针对遥操作精密装配问题,基于视觉伺服,并通过图形图像叠加等方法,加入了有效的人工辅助措施,很好地利用了人类智能,增强了精密作业系统的鲁棒性和可实现性,并最终实现了遥操作精密装配．     

复杂条件下运动物体的视频检测

提出了一种适合于复杂条件下运动物体视频检测的新方法。首先采用改进的点状相关图法检测出可能存在运动物体的区域,然后对可能存在的运动区域二值化并采用形态学算子去除环境噪音和光线的干扰,精确地确定运动物体的轮廓。大量实验验证了该方法的有效性和实用性。     

Vision-based control for mining automation

The mining industry is highly suitable for the application of robotics and automation technology since the work is both arduous and dangerous. Visual servoing is a means of integrating noncontact visual sensing with machine control to augment or replace operator based control. This article describes two of our current mining automation projects in order to demonstrate some, perhaps unusual, applications of visual servoing, and also to illustrate some very real problems with robust computer vision     

Vision-based mobile robots on highways

Intelligent vehicles are mobile robots on highways. They are expected to improve the safety, efficiency and environmental impacts of the current highway traffic systems. Vision systems will play an important role as sensors for the intelligent vehicles. This paper first compares the vision sensors with other sensing methods from an application point of view and then describes two vision systems, one which we have developed and another which we are developing. Two important features are required for the vision systems applied to intelligent vehicles: three-dimensional (3D) measurement capability and real-time operation. We chose a trinocular stereo vision scheme among a number of 3D vision processing methods because it is suitable for real-time operations with dedicated processor architectures. The trinocular stereo algorithm requires a large number of operations, but all the operations are relatively straightforward and, therefore, they are suitable for custom architecture implementation. The system takes three images simultaneously by using three TV cameras installed on a single horizontal line at the front grill of the test car. Vertical edges are extracted from these images and the spatial offsets (or disparities) among the images are calculated for measuring the distances to the objects. The first version was developed and installed in a car for highway testing. Two custom digital processors were developed: one for edge detection and the other for stereo matching. The test results were encouraging and the architectures based on ASIC (Application Specific Integrated Circuits) are 800 and 550 times more efficient, respectively, compared with conventional microprocessors for edge detection and stereo matching. The second version is currently being developed in order to further reduce the silicon area size. It uses hybrid analog/digital circuit technology while the first version uses only digital circuits. We are developing a hybrid analog/digital array processor chip which includes a large number of processing elements. Each processing element includes a digital memory unit, a data flow control switch unit and an analog arithmetic/logic unit. The analog arithmetic/logic unit reduces the silicon area size significantly compared with the digital one. The data flows among multiple processing elements in the array chip in a form of analog voltage. The data flow is controlled by the data flow switches. The digital memory unit controls the set-up of the data flow control switch and arithmetic/logic units.     

Vision-based real estate price estimation

Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow’s estimates.     

Vision-based intelligent control for automated assembly

Development of an automated assembly system requires integration of different engineering modules and coordination of interactions between these modules. This paper presents some of the results of an effort in developing an assembly automation schene for an automated work cell. Integration of the control scheme with the vision module and an on-line trajectory planner is presented. Special characteristics of this automation scheme are dynamic integration of vision and feedback control, real-time operation, uncertainty compensation and error recovery. The hardware required for implementation of this scheme is described. Results of implementing this scheme on a PUMA robot performing a carburetor and gasket mating operation are presented.