检索结果-内蒙古大学图书馆

作者： Kim, Min-Jung Oh, Tae-Hyun Kweon, In So Robotics and Computer Vision Laboratory KAIST Korea Republic of

ISBN: (纸本)9781479957514

Since commercial light field cameras became available, the light field camera has aroused much interest from computer vision and image processing communities due to its versatile functions. Most of its special features are based on an estimated depth map, so reliable depth estimation is a crucial step. However, estimating depth on real light field cameras is a challenging problem due to noise and short baselines among sub-aperture images. We propose a depth map estimation method for light field cameras by exploiting correspondence and focus cues. We aggregate costs among all the sub-aperture images on cost volume to alleviate noise effects. With efficiency of the cost volume, cost-aware depth estimation is quickly achieved by discrete-continuous optimization. In addition, we analyze each property of correspondence and focus cues and utilize them to select reliable anchor points. A well reconstructed initial depth map from the anchors is shown to enhance convergence. We show our method outperforms the state-of-the-art methods by validating it on real datasets acquired with a Lytro camera. © 2014 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Flight performance assessment of land surveying trajectories for multiple UAV platforms

Flight performance assessment of land surveying trajectories...

引用

Workshop on Research, Education and Development of Unmanned Aerial Systems (RED-UAS)

作者： Andres Mora Sai Vemprala Adrian Carrio Srikanth Saripalli School of Earth and Space Exploration Arizona State University Tempe AZ USA Computer Vision Group Centre for Automation and Robotics CSIC-UPM Spain

Crop monitoring of large areas using unmanned aerial vehicles (UAV) is a process that involves multiple trade-offs. For a particular location a multicopter may be more suitable than a fixed-wing due to landscape, altitude, or weather conditions. In other cases the opposite may also be true and the best solution considering additional factors such as available energy and the time it takes to sample the area of interest. In this paper we evaluate the energy consumption, the total distance traveled, and the total time it takes for two unmanned aerial platforms, a fixed-wing and a multicopter to traverse different trajectories. We evaluate the performance of these two platforms using two trajectories: lawnmower and spiral. These trajectories guarantee a 60% both in overlap and sidelap. We analyze the trade-offs between traversing a given trajectory with both platforms and the impact of using a lawnmower instead of a spiral pattern in the context of precision agriculture applications.

关键词： Trajectory Vehicles Spirals Cameras DC motors Agriculture Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Traffic Light Detection: A Learning Algorithm and Evaluations on Challenging Dataset

Traffic Light Detection: A Learning Algorithm and Evaluation...

引用

International Conference on Intelligent Transportation

作者： Mark Philip Philipsen Morten Bornø Jensen Andreas Møgelmose Thomas B. Moeslund Mohan M. Trivedi UC San Diego Computer Vision and Robotics Research Laboratory La Jolla CA USA Visual Analysis of People Laboratory Aalborg University Aalborg Denmark

Traffic light recognition (TLR) is an integral part of any intelligent vehicle, which must function in the existing infrastructure. Pedestrian and sign detection have recently seen great improvements due to the introduction of learning based detectors using integral channel features. A similar push have not yet been seen for the detection sub-problem of TLR, where detection is dominated by methods based on heuristic models. Evaluation of existing systems is currently limited primarily to small local datasets. In order to provide a common basis for comparing future TLR research an extensive public database is collected based on footage from US roads. The database consists of both test and training data, totaling 46,418 frames and 112,971 annotated traffic lights, captured in continuous sequences under a varying light and weather conditions. The learning based detector achieves an AUC of 0.4 and 0.32 for day sequence 1 and 2, respectively, which is more than an order of magnitude better than the two heuristic model-based detectors.

关键词： Detectors Image color analysis Feature extraction Databases computer vision Intelligent vehicles Roads

来源：评论

学校读者我要写书评

暂无评论

Team-based workshop to engage young students in engineering and science: Building and driving a ROV (R2B2). Two special editions in India

Team-based workshop to engage young students in engineering ...

引用

OCEANS - Europe

作者： Xavier Cuff Miquel Villanueva Andres El-Fakdi Natalia Hurtós Eduard Muntaner Jordi Freixenet Joan Massich Josep Quintana Narcis Palomeras Anna Bosch Anna Renart Universitat de Girona Girona Catalunya ES Computer Vision and Robotics Group (VICOROB) and UdiGital.Edu Research Group from University of Girona Spain

This work reports the experience gathered along 6 years in developing a team-based project activity to promote engineering programs among secondary school students. The aim of the activity is to increase the interest of students for science and technology in general, but also to promote engineering skills, capabilities and values, leading to attract more secondary school students to enrolment for engineering programs. Simple theoretical concepts related to physics and engineering are illustrated through hands-on experimentation. To achieve this goal, the students build a remotely operated underwater robot in a workshop. The robot is built using low-cost materials and the students customize their own design over the different phases of the workshop. Once the activity is completed, every team understands that with teamwork, effort and a good working strategy, every problem can be overcome. This paper explains in detail the structure and operation of the workshop and introduces a first initiative towards the internationalization of the project, which was carried out in two schools for underprivileged children in South India. Through this initiative in India, the workshop takes a step forward, and in addition to promoting science and technology, it also adds a new dimension of education for global citizenship to the project.

关键词： Conferences Robots Vehicles DC motors Underwater vehicles Buoyancy Buildings

来源：评论

学校读者我要写书评

暂无评论

Physiological signals in driving scenario: How heart rate and skin conductance reveal different aspects of driver's cognitive load

Physiological signals in driving scenario: How heart rate an...

引用

International Conference on Physiological Computing Systems, PhyCS 2014

作者： Dang, Thi-Hai-Ha Tapus, Adriana Computer Vision and Robotics Lab. ENSTA-Paris Palaiseau France

ISBN: (纸本)9789897580062

Driver's cognitive load has always been associated with the driver's heart rate activity and his/her skin conductance activity. However, what aspects of cognitive load that these signals relate to have never been clearly studied. This paper presents our preliminary results about the relationship between the different physiological signals (heart rate and skin conductance) and the driver's cognitive load. Via one experiment with simulated car driving environment and one experiment in real flying environment, our data suggests that subjects' heart rate relates to the number of events to be processed by the human driver while the skin conductance relates to the novelty of the driving task. Given the small population involved in these experiments, tests on more subjects are planned and reported in the future. Copyright © 2014 SCITEPRESS - Science and Technology Publications. All rights reserved.

关键词： Automobile drivers

来源：评论

学校读者我要写书评

暂无评论

Day and night-time drive analysis using stereo vision for naturalistic driving studies

Day and night-time drive analysis using stereo vision for na...

引用

IEEE Symposium on Intelligent Vehicle

作者： Mark P. Philipsen Morten B. Jensen Ravi K. Satzoda Mohan M. Trivedi Andreas Møgelmose Thomas B. Moeslund Computer Vision and Robotics Research Laboratory La Jolla CA USA Visual Analysis of People Laboratory Aalborg University Aal-borg Denmark Aalborg Universitet Aalborg DK

In order to understand dangerous situations in the driving environment, naturalistic driving studies (NDS) are conducted by collecting and analyzing data from sensors looking inside and outside of the car. Manually processing the overwhelming amounts of data that are generated in such studies is very comprehensive. We propose a method for automatic data reduction for NDS based on stereo vision vehicle detection and tracking during day- and nighttime. The developed system can automatically register five NDS events, mainly related to intersections, from an existing NDS dictionary. We propose a new drive event which takes advantage of the extra dimension provided by stereo vision. In total, six drive events are selected on the basis of them being problematic to detect automatically using conventional monocular computer vision approaches. The proposed system is evaluated on day-and nighttime data, resulting in drive analysis report. The proposed system reach an overall precision of 0.78 and an overall recall of 0.72.

关键词： Vehicles Stereo vision Roads Three-dimensional displays Noise Vehicle detection Vehicle crash testing

来源：评论

学校读者我要写书评

暂无评论

Underwater robot-object contact perception using machine learning on force/torque sensor feedback

Underwater robot-object contact perception using machine lea...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Nawid Jamali Petar Kormushev Arnau C. Viñas Marc Carreras Darwin G. Caldwell iCub Facility Istituto Italiano di Tecnologia via Morego 30 Genova Italy Department of Advanced Robotics Istituto Italiano di Tecnologia via Morego. 30 Genova Italy Computer Vision and Robotics Group (VICOROB) University of Girona Girona Spain

Autonomous manipulation of objects requires reliable information on robot-object contact state. Underwater environments can adversely affect sensing modalities such as vision, making them unreliable. In this paper we investigate underwater robot-object contact perception between an autonomous underwater vehicle and a T-bar valve using a force/torque sensor and the robot's proprioceptive information. We present an approach in which machine learning is used to learn a classifier for different contact states, namely, a contact aligned with the central axis of the valve, an edge contact and no contact. To distinguish between different contact states, the robot performs an exploratory behavior that produces distinct patterns in the force/torque sensor. The sensor output forms a multidimensional time-series. A probabilistic clustering algorithm is used to analyze the time-series. The algorithm dissects the multidimensional time-series into clusters, producing a one-dimensional sequence of symbols. The symbols are used to train a hidden Markov model, which is subsequently used to predict novel contact conditions. We show that the learned classifier can successfully distinguish the three contact states with an accuracy of 72% ± 12 %.

关键词： Robot sensing systems Grippers Valves Force Torque Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Motion-oriented attention for a social gaze robot behavior 6

Motion-oriented attention for a social gaze robot behavior

引用

6th International Conference on Social robotics, ICSR 2014

作者： Sorostinean, Mihaela Ferland, François Dang, Thi-Hai-Ha Tapus, Adriana Computer Vision and Robotics Lab Computer Science and System Engineering Department ENSTA-ParisTech Palaiseau France

ISBN: (纸本)9783319119724

Various studies have shown that human visual attention is generally attracted by motion in the field of view. In order to embody this kind of social behavior in a robot, its gaze should focus on key points in its environment, such as objects or humans moving. In this paper, we have developed a social natural attention system and we explore the perception of people while interacting with a robot in three different situations: one where the robot has a totally random gaze behavior, one where its gaze is fixed on the person in the interaction, and one where its gaze behavior adapts to the motion-based environmental context. We conducted an online survey and an on-site experiment with the Meka robot so as to evaluate people’s perception towards these three types of gaze. Our results show that motion-oriented gaze can help to make the robot more engaging and more natural to people. © Springer International Publishing Switzerland 2014.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Facial landmark localization and feature extraction for therapeutic face exercise classification

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2014年 458卷 179-194页

作者： Lanz, Cornelia Olgay, Birant Sibel Denzler, Joachim Gross, Horst-Michael Neuroinformatics and Cognitive Robotics Lab Ilmenau University of Technology Ilmenau Germany Computer Vision Group Friedrich Schiller University Jena Jena Germany

ISBN: (纸本)9783662449103

In this work, we examine landmark localization and feature extraction approaches for the unexplored topic of therapeutic facial exercise recognition. Our goal is to automatically discriminate nine therapeutic exercises that have been determined in cooperation with speech therapists. We use colour, 2.5D and 3D image data that was recorded using Microsoft’s Kinect. Our features comprise statistical descriptors of the face surface curvature as well as characteristic profiles that are derived from face landmarks. For the nine facial exercises, we yield an average recognition accuracy of about 91% in conjunction with manually labeled landmarks. Additionally, we introduce a combined method for automatic landmark localization and compare the results to landmark positions obtained from Active Appearance Model fitting as well as manual labeling. The combined localization method exhibits increased robustness in comparison to AAMs. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A real-time webcam based Eye Ball Tracking System using MATLAB

A real-time webcam based Eye Ball Tracking System using MATL...

引用

International Symposium for Design and Technology of Electronics Packages (SIITME)

作者： Osama Mazhar Taimoor Ali Shah Muhammad Ahmed Khan Sameed Tehami Computer Vision and Robotics University of Burgundy Burgundy France Electrical Engineering & Information Technology Technische Hochschule Ingolstadt Ingolstadt Germany Biomedical Engineering NED University of Engineering & Technology Karachi Pakistan

Eye Ball Tracking System is a device which is intended to assist patients that cannot perform any voluntary tasks related to daily life. Patients who only can control their eyes can still communicate with the real-world using the assistive devices like one proposed in this paper. This device provides a human computer interface in order to take decisions based on their eye movement. A real time data stream is captured via webcam that transfers data serially to MATLAB. Then a sequential image processing scheme segments the iris of the eye and calculates the centroid, thereby generating control signal with the help of a reference axis. The control signals are then used to manipulate the position of a motorized platform via USB-microcontroller interface.

关键词： Image processing MATLAB Gaze tracking Webcams Microcontrollers Real-time systems computers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：