检索结果-内蒙古大学图书馆

Detection and tracking of returns in sector-scan sonar image sequences

IEE PROCEEDINGS-RADAR SONAR AND NAVIGATION 1996年第3期143卷 157-162页

作者： Chantler, MJ Lane, DM Dai, D Williams, N Department of Computing and Electrical Engineering Heriot-Watt University Edinburgh United Kingdom

The authors report the development of algorithms for the detection and tracking of object returns in noisy sector-scan sonar image sequences. Static objects are first removed using spatial and frequency domain filtering. The optical flow of the resulting images (containing only dynamic returns) is calculated. Significant dynamic returns are detected and segmented using adaptive thresholding. The average optical flow of each significant return is used by a tracking algorithm both to constrain search window radii and to derive a similarity measure. A tree of possible tracks is maintained in which the cumulative similarity measure is used to identify the most likely tracks and to prune out the least likely object sequences. The results of experiments using real scan sequences are presented to show the utility of the proposed tracking system.

关键词： detection algorithm tracking tree sonar image processing tracking algorithm adaptive thresholding object identification

来源：评论

学校读者我要写书评

暂无评论

Fusion of Radar and IRST Sensor Measurements for 3D Target tracking using Extended Kalman Filter

引用

DEFENCE SCIENCE JOURNAL 2009年第2期59卷 175-182页

作者： Naidu, V. P. S. Natl Aerosp Labs Bangalore 17 Karnataka India

tracking algorithms for IRST and radar are implemented and their performance is checked with simulated data. Detailed mathematical expressions given Could be useful for implementation. Performance evaluation metrics have been presented to check the tracking algorithm performance. Two fusion schemes have been presented and their performances evaluated with simulated data. It is concluded that both fusion schemes performed alike with the second fusion scheme giving slightly better results. From the results, it is also concluded that fusion of IRST and radar would improve the tracking performance and reduce the positional uncertainty compared to individual trackers.

关键词： IRST sensor measurements 3-D target tracking Kalman filter tracking algorithm performance evaluation fusion schemes target tracking

来源：评论

学校读者我要写书评

暂无评论

A Perceptually Adaptive Long-Term tracking Method for the Complete Occlusion and Disappearance of a Target

引用

COGNITIVE COMPUTATION 2023年第6期15卷 2120-2131页

作者： Chen, Lu Li, Gun Zhao, Kunqi Zhang, Guiping Zhu, Xingyu Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu 611731 Peoples R China Zhongxing Telecommun Equipment Corp Shenzhen 518057 Peoples R China

In recent years, tracking algorithms based on correlation filtering have been widely considered because of their high real-time performance. However, most of these algorithms do not consider the reliability of tracking results;thus, model drift is often a challenge in long-term target tracking. Moreover, the target is significantly occluded or disappears in long-term target tracking, hence the need for research to address such complexities. This paper proposes a long-term tracking framework comprising a tracking and re-detection module. The tracking module is based on the efficient convolution operator target-tracking algorithm (ECO) (Danelljan et al. in Proc IEEE Conf Comput Vis Pattern Recognit, 1). To redetect a lost target, a tracking uncertainty estimation method is developed that evaluates the tracking results of each image. Furthermore, an adaptive model-updating method is proposed, which can reduce the number of model updates and improve the robustness of the tracking algorithm. The model is inspired by long and short-term memory pool mechanisms of the brain, applying both mechanisms to the traditional tracking algorithm to improve long-term tracking. The memory model is effectively integrated into a brain-inspired visual long-term tracker through mutual learning and inspiration from computer and biological vision. In addition, the brain-inspired visual model can be made bio-cognitive on a small hardware platform with limited computing power. Central processing unit (CPU)-based experiments using two data sets, UAV20L (Mueller et al. in Eur Conf Comput Vision, 2) and UAV123 (Wu et al. in Proc IEEE Conf Comput Vis Pattern Recognit, 3), confirmed that the proposed method runs faster than 30fps. Furthermore, the long-term tracking test using the UAV20L data set showed that the proposed method performs better than any other method by 39%. Compared with conventional tracking methods, the proposed method has better performance in terms of coverage rate and position

关键词： Long-term target tracking tracking algorithm Uncertainty estimation method Adaptive model-updating method

来源：评论

学校读者我要写书评

暂无评论

Path-tracking simulation and field tests for an auto-guidance tillage tractor for a paddy field

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2015年 112卷 161-171页

作者： Han, Xiong Zhe Kim, Hak Jin Kim, Joon Yong Yi, Sang Yup Moon, Hee Chang Kim, Jung Hun Kim, Young Joo Seoul Natl Univ Dept Biosyst & Biomat Engn Seoul South Korea Seoul Natl Univ Res Inst Agr & Life Sci Seoul South Korea SimLab Co Ltd Seoul South Korea Unmanned Solut Co Ltd Seoul South Korea Tongyang Moolsan Co Ltd R&D Inst Gongju South Korea Korea Inst Ind Technol Environm Mat & Components Ctr Jeonju South Korea

The application of an auto-guided tractor to rice cultivation in Korean paddy fields may be limited by tire slippage and headland turning due to wet soil conditions and the use of small-sized fields < 1 ha. This study examines the development of a computer simulator capable of virtually testing the motion of a tractor based on a look-ahead distance method in a real-time 3D graphic environment. The tractor motion was simulated based on the dynamic model of a vehicle that considered the effects of tire slippage and side force imparted by soil. The validity of the computer simulation was confirmed by a paved road test, thereby providing tracking trajectories similar to those obtained from the road test. However, an oscillation in the steering angle, ranging from -8 to +5 deg., occurred when the tractor traveled on straight paths. This oscillation might be related to the limitations of the electric motor in controlling the tractor's hydraulic steering system due to the non-linear response of the hydraulic actuator to the rotation of the steering wheel by motor torque. In an arable field (90 m x 25 m), the auto-guided tractor followed the predefined path including C-shape headland turning with acceptable tracking, showing RMS lateral errors ranging from 3.8 to 12.8 cm on the straight paths. However, RMS lateral errors obtained on the curved paths increased to 100 cm when the tractor traveled in a wet sub-field with moisture content > 30%, thereby requiring more accurate estimation of sliding parameters. (C) 2015 Elsevier B.V. All rights reserved.

关键词： tracking algorithm Autonomous tractor Kinematic model Computer simulation Tire slippage Paddy field

来源：评论

学校读者我要写书评

暂无评论

Reentry vehicle tracking in a cluttered environment

引用

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE 2010年第2期41卷 213-225页

作者： Liu, Cheng-Yu Chyuan, Chung-Hsing Lee Ming Inst Technol Dept Elect Engn Taipei 24305 Taiwan

Recently, reentry vehicle (RV) tracking has become an important issue because of its high speed and high-elevation angle. The extended Kalman filter (EKF) with input estimation (IE) was developed for an RV tracking in a clear environment. However, radar tracking suffers from clutters in the form of unwanted, unavoidable and unpredictable signal echoes from sea, land and weather. The Hough transform is a well-known technique for identifying a straight line in noisy environments. This technique can be utilised to design a clutter elimination algorithm for clutters censoring. This study presents a novel tracking algorithm by integrating the EKF, IE and clutter elimination algorithm to track the RVs in cluttered environments. To ensure an RV to be tracked continuously, the estimation errors between the predicted and the real trajectories should be within a range cell. Simulation results reveal that the proposed algorithm can provide an acceptable accuracy to maintain the track. Although clutters cannot be totally censored, the effects of resting clutters can be reduced to an acceptable range. The proposed algorithm may thus help radars in achieving continuous tracking. In conclusion, this algorithm deserves further study and application.

关键词： input estimation Hough transform tracking algorithm reentry vehicle trajectory estimation tracking state estimation parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Exploring dynamics in living cells by tracking single particles

引用

CELL BIOCHEMISTRY AND BIOPHYSICS 2007年第1期48卷 1-15页

作者： Levi, Valeria Gratton, Enrico Univ Calif Irvine Rockwell Engn Ctr 204 Lab Fluorescence Dynam Irvine CA 92697 USA Univ Buenos Aires Dept Fis Lab Electron Cuant RA-1428 Buenos Aires DF Argentina

In the last years, significant advances in microscopy techniques and the introduction of a novel technology to label living cells with genetically encoded fluorescent proteins revolutionized the field of Cell Biology. Our understanding on cell dynamics built from snapshots on fixed specimens has evolved thanks to our actual capability to monitor in real time the evolution of processes in living cells. Among these new tools, single particle tracking techniques were developed to observe and follow individual particles. Hence, we are starting to unravel the mechanisms driving the motion of a wide variety of cellular components ranging from organelles to protein molecules by following their way through the cell. In this review, we introduce the single particle tracking technology to new users. We briefly describe the instrumentation and explain some of the algorithms commonly used to locate and track particles. Also, we present some common tools used to analyze trajectories and illustrate with some examples the applications of single particle tracking to study dynamics in living cells.

关键词： single particle tracking dynamics trajectory intracellular motion tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Robustness tracking of Maneuvering Target for Bionic Robot

引用

INTERNATIONAL JOURNAL OF SECURITY AND ITS APPLICATIONS 2015年第12期9卷 67-75页

作者： Wang Peng Wu Jian Zhang Yuan Li Jixiang Zhang Peng Harbin Univ Sci & Technol Sch Mech & Power Engn Harbin Peoples R China Harbin Univ Sci & Technol Coll Automat Harbin Peoples R China

In order to improve vision tracking quality of the bionic robot, the new automatic tracking algorithm system is proposed in this paper. Base on design of FPGA image acquisition system, the scene noise is removed by adaptive wiener filtering. Aiming at the problem of ROI region extraction in the scene, the seed pixel is selected with background subtraction, orderly, the neighborhood point is judged, the label of the primary selection seed is calibrated. The scene image segmentation algorithm is proposed based on snake model. The matching process is to find the maximum optimization process of the similar function, and the gradient drop method is adopted in mean shift algorithm. Extended kalman filtering is used to realize the robustness state estimation and prediction of the target tracking system. The results given by tracing experiment indicate that the proposed detailed algorithm is effective for partial loss of maneuvering target.

关键词： maneuvering target tracking algorithm mean shift extended kalman filtering

来源：评论

学校读者我要写书评

暂无评论

High Dynamics and Precision Optical Measurement Using a Position Sensitive Detector (PSD) in Reflection-Mode: Application to 2D Object tracking over a Smart Surface

引用

SENSORS 2012年第12期12卷 16771-16784页

作者： Ivan, Ioan Alexandru Ardeleanu, Mihaita Nicolae Laurent, Guillaume J. Univ Valahia Targoviste FIE & FIMMR B Dul Unirii 18-20 Targoviste 130082 Romania FEMTO ST Inst UMR CNRS 6174 UFC ENSMMUTBMDpt AS2M F-25000 Besancon France

When related to a single and good contrast object or a laser spot, position sensing, or sensitive, detectors (PSDs) have a series of advantages over the classical camera sensors, including a good positioning accuracy for a fast response time and very simple signal conditioning circuits. To test the performance of this kind of sensor for microrobotics, we have made a comparative analysis between a precise but slow video camera and a custom-made fast PSD system applied to the tracking of a diffuse-reflectivity object transported by a pneumatic microconveyor called Smart-Surface. Until now, the fast system dynamics prevented the full control of the smart surface by visual servoing, unless using a very expensive high frame rate camera. We have built and tested a custom and low cost PSD-based embedded circuit, optically connected with a camera to a single objective by means of a beam splitter. A stroboscopic light source enhanced the resolution. The obtained results showed a good linearity and a fast (over 500 frames per second) response time which will enable future closed-loop control by using PSD.

关键词： microrobotics optics optomechatronics sensing PSD position sensitive detector smart-surface tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

A Framework of Automatic Clustering and tracking for Time-Variant Multipath Components

引用

IEEE COMMUNICATIONS LETTERS 2017年第4期21卷 953-956页

作者： Wang, Qi Ai, Bo He, Ruisi Guan, Ke Li, Yan Zhong, Zhangdui Shi, Guowei Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China China Acad Telecommun Res Beijing 100083 Peoples R China

A framework of automatic clustering and tracking algorithm is proposed for the multipath components (MPCs) in time-variant radio channels. The algorithm is based on the channel dynamics in time domain and is able to reflect the birth and death behaviors of MPCs naturally. The proposed algorithm is validated by a ray-tracer and the spatial channel model extension simulations. Compared with other existing clustering algorithms, the proposed framework is able to cluster the timevarying MPCs and track the clusters with high accuracy and low complexity.

关键词： Clustering algorithm tracking algorithm time-variant channels

来源：评论

学校读者我要写书评

暂无评论

ombined tracking Strategy Based on Unscented Kalman Filter for Global Positioning System L2C CM/CL Signal

引用

DEFENCE SCIENCE JOURNAL 2015年第5期65卷 395-402页

作者： Zhu, Xuefen Shen, Fei Chen, Jianfeng Yang, Yang Yang, Dongrui Chen, Xiyuan Southeast Univ Sch Instrument Sci & Engn Minist Educ Key Lab Microinertial Instrument & Adv Nav Techno Nanjing 210096 Jiangsu Peoples R China Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Peoples R China

In a global positioning system receiver, the tracking algorithm plays a dominant role since the code delay and Doppler frequency shift need to be accurately estimated as well as their variation over time need to be continuously updated. Combine unscented Kalman filter (UKF) with CM/CL signal to improve the signal tracking precision is proposed. It allow weighting assignment between CM code and CL code incoming signal, masked by a mass of noise, and to describe a UKF tracking loop aiming at decreasing numerical errors. UKF here involves state and measuring equations which calculate absolute offsets to adjust initial code and carrier phase then dramatically decrease the tracking error. In particular, the algorithm is implemented in both open space and jammed environment to highlight the advantages of tracking approach, by comparing single code and combined code, UKF and EKF tracking loop. It proves that signal tracking based on UKF, with low energy dissipation as well as high precision, is particularly appealing for a software receiver implementation.

关键词： global positioning system GPS receiver tracking algorithm unscented Kalman filter CM/CL signal weighting assignment

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：