检索结果-内蒙古大学图书馆

Reliability verification-based convolutional neural networks for object tracking

IET IMAGE PROCESSING 2019年第1期13卷 175-185页

作者： Hu, Xiaopeng Li, Jingting Yang, Yan Wang, Fan Dalian Univ Technol Sch Comp Sci & Technol 2 Linggong Rd Ganjingzi Dist Dalian Peoples R China Liaoning Normal Univ Sch Comp & Informat Technol 850 Huanghe Rd Shahekou Dist Dalian Peoples R China

The authors propose a tracking algorithm based on the reliability analysis of the convolutional neural network to avoid drift. In general, most tracking algorithms implemented with the deep network consist of a single network;they obtain the tracking results according to the confidence and perform updates with the samples, which are collected based on the previous target state. However, this kind of algorithm relies heavily on the accuracy of tracking results, and slight deviations can lead to improperly labelled training samples and degrade the network. Therefore, they design a verification network to guarantee the reliability of the tracking network by correcting the results and it can be connected to a tracking network by sharing convolutional layers. The reliability verification network estimates the accuracy of the results of the tracking network and discards ambiguous results to avoid accumulating errors. Specifically, the verification network can distinguish the target from the confused candidates more precisely because of the optimised training data. The training samples of the verification network consist of characteristics and labels, and they are optimised by feature selection and label enhancement, respectively. The experimental results illustrate the outstanding performance compared with several state-of-the-art methods on the challenging video sequences.

关键词： object tracking learning (artificial intelligence) feedforward neural nets reliability feature selection tracking network reliability verification-based convolutional neural networks object tracking tracking algorithm reliability analysis deep network single network improperly labelled training samples feature selection label enhancement convolutional layers

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Rivers and Associated Precipitation over France and Western Europe: 1980-2020 Climatology and Case Study

引用

ATMOSPHERE 2021年第8期12卷 1075-1075页

作者： Doiteau, Benjamin Dournaux, Meredith Montoux, Nadege Baray, Jean-Luc Univ Clermont Auvergne CNRS Lab Meteorol Phys UMR 6016 F-63178 Aubiere France Univ Clermont Auvergne CNRS Observ Phys Globe Clermont Ferrand UAR 833 F-63178 Aubiere France

Atmospheric rivers are important atmospheric features implicated in the global water vapor budget, the cloud distribution, and the associated precipitation. The ARiD (Atmospheric River Detector) code has been developed to automatically detect atmospheric rivers from water vapor flux and has been applied to the ECMWF ERA5 archive over the period 1980-2020 above the Atlantic Ocean and Europe. A case study of an atmospheric river formed in the East Atlantic on August 2014 that reached France has been detailed using ECMWF ERA5 reanalysis, ground based observation data, and satellite products such as DARDAR, AIRS, GPCP, and GOES. This atmospheric river event presents a strong interaction with an intense upper tropospheric jet stream, which induced stratosphere-troposphere exchanges by tropopause fold. A 1980-2020 climatology of atmospheric rivers over Europe has been presented. The west of France, Iberian Peninsula, and British Islands are the most impacted regions by atmospheric rivers with an occurrence of up to four days per month during the October-April period. Up to 40% of the precipitation observed on the west European coast can be linked to the presence of ARs. No significant trend in the occurrence of the phenomena was found over 1980-2020.

关键词： atmospheric river water vapor precipitation upper tropospheric jet-stream stratosphere-troposphere exchange tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

A Selectable Imaging Spectrum Vehicle Recognition Method based on Spectral Feature 2

A Selectable Imaging Spectrum Vehicle Recognition Method bas...

引用

2nd Target Recognition and Artificial Intelligence Summit Forum

作者： Zhu, Xiao-qiang Li, Zi-jian Zhao, Wei-hong Li, Jiao-yang Liang, Hao-wen Li, Xi-ying Cai, Zhi-gang Wang, Jia-hui Sun Yat Sen Univ Sch Phys State Key Lab Optoelect Mat & Technol Guangzhou Guangdong Peoples R China Sun Yat Sen Univ Sch Engn Guangdong Prov Key Lab Intelligent Transportat Sy Guangzhou 510006 Guangdong Peoples R China Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou 510006 Guangdong Peoples R China

ISBN: (纸本)9781510636323

Vehicle recognition is a key issue of intelligent transportation systems. For traditional color-based vehicle recognition methods, an important problem is that color information of vehicle is susceptible on lumination variation, which will inevitably reduce the recognition accuracy. Another is that there are contrastive interfering vehicles with similar color in same exposure environment, which could result in misrecognition of target vehicle. This paper presents a novel technique for recognizing target vehicle in different lumination scenarios via spectral feature. This method consists of three parts, ambient light spectrum calibration, vehicle spectral reflectivity detection and vehicle recognition. And an prototype system named Selectable Imaging Spectrum Detection System (SISDS), has been setup by this spectral feature-based method. A new combination algorithm is proposed for the detection part which contains the deep learning model YOLOv3 and the discriminant tracking algorithm KCF. Also, a CNN model is designed for improving the recognition accuracy through transforming the spectral data into two-dimension matrix. The experimental results of the SISDS clearly demonstrate that the spectral feature-based method overcomes the shortcomings of the traditional color-based method, and it can not only distinguish the vehicles of different colors in the case of overexposure, but also can recognize the target vehicle from the same color interference vehicles under various lumination, the recognition accuracy is up to 96.4%. Compared with colorbased method, the spectral feature-based method has great lamination robustness, and high recognition accuracy.

关键词： spectrum detection vehicle detection tracking algorithm convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

ARM-based Behavior tracking and Identification System for Group-housed Pigs

引用

RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING 2019年第6期12卷 554-565页

作者： Liu, Xingqiao Xuan, Jun Hussain, Fida Chong, Chen Li, Pengyu Jiangsu Univ Sch Elect & Informat Engn 301 Xuefu Rd Zhenjiang Jiangsu Peoples R China Nanjing Agr Univ Natl Engn & Technol Ctr Informat Agr Nanjing Jiangsu Peoples R China Yancheng Inst Technol Coll Elect Engn Yancheng Jiangsu Peoples R China

Background: A smart monitoring system is essential to improve the quality of pig farming. A real-time monitoring system provides growth, health and food information of pigs while the manual monitoring method is inefficient and produces stress on pigs, and the direct contact between human and pig body increases diseases. Methods: In this paper, an ARM-based embedded platform and image recognition algorithms are proposed to monitor the abnormality of pigs. The proposed approach provides complete information on in-house pigs throughout the day such as eating, drinking, and excretion behaviors. The system records in detail each pig's time to eat and drink, and the amount of food and water intake. Results: The experimental results show that the accuracy of the proposed method is about 85%, and the effect of the technique has a significant advantage over traditional behavior detection methods. Conclusion: Therefore, the ARM-based behavior recognition algorithm has certain reference significance for the fine group aquaculture industry. The proposed approach can be used for a central monitoring system.

关键词： Embedded system image recognition tracking algorithm pig behavior fine breeding behavior recognition

来源：评论

学校读者我要写书评

暂无评论

Issues On Infrared Dim Small Target Detection And tracking

Issues On Infrared Dim Small Target Detection And Tracking

引用

International Conference on Smart Grid and Electrical Automation (ICSGEA)

作者： Eysa, Raziye Hamdulla, Askar Xinjiang Univ Informat Sci & Engn Shi Urumqi 830046 Peoples R China

ISBN: (纸本)9781728144634

Infrared dim small target detection has always been one of the difficulties in the field of infrared image processing. Due to the long imaging distance, targets usually occupy a few pixels in images, and lack of textural information. Besides, there is usually low contrast between the small targets and backgrounds in infrared images, the small targets are easily immersed in complex backgrounds, also raise the difficulty. Infrared dim small target detection and tracking technology is of great significance and high value in military and civilian applications and has broad application prospects. This paper focuses on the typical algorithm principles and characteristics of infrared dim small target detection and tracking technology. On this basis, the research status and development trend of infrared dim small target detection and tracking technology are predicted.

关键词： Dim and Small Infrared Target Target detection tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

tracking of Objects on Images: a General Approach

Tracking of Objects on Images: a General Approach

引用

Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)

作者： Zilinberg, A. Y. Korneev, Y. A. St Petersburg State Univ Aerosp Instrumentat St Petersburg Russia

The article describes the approach to the construction of algorithms for tracking objects on the video image. Details are commented on the implementation of the procedure for associating traces of marks on adjacent fr... 详细信息

ISBN: (纸本)9781728122885

关键词： pattern recognition image analysis tracking algorithm

来源：评论

学校读者我要写书评

暂无评论

Multiple-Joint Pedestrian tracking Using Periodic Models

引用

SENSORS 2020年第23期20卷 6917页

作者： Dolatabadi, Marzieh Elfring, Jos van de Molengraft, Rene Univ Eindhoven Dept Mech Engn Control Syst Technol Grp NL-5600 MB Eindhoven Netherlands

Estimating accurate positions of multiple pedestrians is a critical task in robotics and autonomous cars. We propose a tracker based on typical human motion patterns to track multiple pedestrians. This paper assumes that the legs' reflection and extension angles are approximately changing periodically during human motion. A Fourier series is fitted in order to describe the moving, such as describing the position and velocity of the hip, knee, and ankle. Our tracker receives the position of the ankle, knee, and hip as measurements. As a proof of concept, we compare our tracker with state-of-the-art methods. The proposed models have been validated by experimental data, the Human Gait Database (HuGaDB), and the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) tracking benchmark. The results indicate that our tracker is able to estimate the reflection and extension angles with a precision of 90.97%. Moreover, the comparison shows that the tracking precision increases up to 1.3% with the proposed tracker when compared to a constant velocity based tracker.

关键词： tracking algorithm pedestrian– car interaction harmonic motion kinematics estimation joint tracking

来源：评论

学校读者我要写书评

暂无评论

Design of a Low-Power BLE5-Based Wearable Device for tracking Movements of Football Players 16

Design of a Low-Power BLE5-Based Wearable Device for Trackin...

引用

16th International System-on-Chip Design Conference (ISOCC)

作者： Kim, Hyunsung Lim, Juin Hong, Wonbin Park, Joonho Kim, Young-Seok Kim, Mijung Lee, Youngjoo POSTECH Dept Elect Engn Pohang 37673 South Korea Kreemo Pohang 37673 South Korea POSTECH Korea Sport Ind Dev Inst Pohang 37673 South Korea

ISBN: (纸本)9781728124780

This paper presents a prototype wearable device that tracks movements of football players during the match time. To analyze the performance of each player, the proposed device uses the global navigation satellite system (GNSS) assisted by the inertial measurement unit (IMU). Several algorithms are realized on the embedded processor to estimate the amount of speed, total distance covered, and inertia. In addition, the Bluetooth Low Energy (BLE) protocol is used to transfer acquired data from the pitch while reducing the overall power consumption. Experimental results show that the BLE-based wearable device successfully demonstrates the real-time tracking operation, achieving the low-power solution compared to the existing devices.

关键词： BLE tracking algorithm wearable device

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different tracking Approaches on Pre-Fused Data for Automotive Perception System 19

Comparison of Different Tracking Approaches on Pre-Fused Dat...

引用

IEEE Joint 19th International Symposium on Computational Intelligence and Informatics / 7th International Conference on Recent Achievements in Mechatronics, Automation, Computer Sciences and Robotics

作者： Lindenmaier, Laszlo Tihanyi, Viktor Budapest Univ Technol & Econ Fac Transportat Engn & Vehicle Engn Dept Automot Technol Budapest Hungary

ISBN: (纸本)9781728156255

The development of autonomous vehicles requires different sensor types for constructing an accurate local environment model. The evolution of sensor technology is challenging the development of sensor data fusion. Although, the sensors are getting more robust and reliable. However, because of the development of sensors the data fusion should be able to handle diversified sensor clusters. Thus, the high-level sensor fusion algorithms, like track to track method, are getting more important. This paper introduces different tracking approaches, which are intended to support a track-to-track fusion method of an autonomous vehicle in highway situations.

关键词： Autonomous vehicles Automotive perception Sensor Fusion Track-to-track fusion tracking algorithm Data association JIPDA

来源：评论

学校读者我要写书评

暂无评论

Forest Fire Visual tracking with Mean Shift Method and Gaussian Mixture Model

Forest Fire Visual Tracking with Mean Shift Method and Gauss...

引用

International Conference on Smart Innovations in Communications and Computational Sciences (ICSICCS)

作者： Cai, Bo Xiong, Lu Zhao, Jianhui Wuhan Univ Sch Comp Wuhan 430072 Hubei Peoples R China

ISBN: (纸本)9789811089718;9789811089701

Forest fire region from surveillance video is non-rigid object with varying size and shape. It is complex and thus difficult to be tracked automatically. In this paper, a new tracking algorithm is proposed by mean shift method and Gaussian mixture model. Based on moment features of mean shift algorithm, the size adaptive tracking window is employed to reflect size and shape changes of object in real time. Meanwhile, the Gaussian mixture model is utilized to obtain the probability value of belonging to fire region for each pixel. Then, the probability value is used to update the weighting parameter of each pixel in mean shift algorithm, which reduces the weight of non-fire pixels and increases the weight of fire pixels. With these techniques, the mean shift algorithm can converge to forest fire region faster and accurately. The presented algorithm has been tested on real monitoring video clips, and the experimental results prove the efficiency of our new method.

关键词： Non-rigid object tracking algorithm Mean shift method Gaussian mixture model

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：