检索结果-南通市图书馆

Image analyses for video-based remote structure vibration monitoring system

在线全文

cnki会议

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2016年第1期10卷 12-21页

作者： Yang YANG Xiong (Bill) YU Department of Electrical Engineering and Computer Science Case Western Reserve University 10900 Euclid Avenue Bingham203d Cleveland OH 44106-7201 USA Department of Civil Engineering Case Western Reserve University 10900 Euclid Avenue Bingham 210 Cleveland OH 44106-7201 USA

Video-based vibration measurement is a cost-effective way for remote monitoring the health conditions of transportation and other civil structures, especially for situations where accessibility is restricted and does not allow installation of conventional monitoring devices. Besides, video-based system is global measurement. The technical basis of video-based remote vibration measurement system is digital image analysis. Comparison of the images allow the field of motion to be accurately delineated. Such information is important to understand the structure behaviors including the motion and strain distribution. This paper presents system and analyses to monitor the vibration velocity and displacement field. The performance is demonstrated on a testbed of model building. Three different methods （i.e., frame difference method, particle image velocimetry, and optical Flow Method） are utilized to analyze the image sequences to extract the feature of motion. The Performance is validated using accelerometer data. The results indicate that all three methods can estimate the velocity field of the model building, although the results can be affected by factors such as background noise and environmental interference. Optical flow method achieved the best performance among these three methods studied. With further refinement of system hardware and image processing software, it will be developed into a remote video based monitoring system for structural health monitoring of transportation infrastructure to assist the diagnoses of its health conditions.

关键词： structure health monitoring velocity estimation frame difference PIV optical-flow method

Camera-based Basketball Scoring Detection Using Convolutional Neural Network

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2021年第2期18卷 266-276页

作者： Xu-Bo Fu Shao-Long Yue De-Yun Pan Department of Public Physical and Art Education Zhejiang UniversityHangzhou 310058China North China Electric Power University Beijing 102206China

Recently,deep learning methods have been applied in many real scenarios with the development of convolutional neural networks(CNNs).In this paper,we introduce a camera-based basketball scoring detection(BSD)method with CNN based object detection and frame difference-based motion *** the proposed BSD method,the videos of the basketball court are taken as ***,the real-time object detection,i.e.,you only look once(YOLO)model,is implemented to locate the position of the basketball ***,the motion detection based on frame difference is utilized to detect whether there is any object motion in the area of the hoop to determine the basketball scoring *** proposed BSD method runs in real-time with satisfactory basketball scoring detection *** experiments on the collected real scenario basketball court videos show the accuracy of the proposed BSD ***,several intelligent basketball analysis systems based on the proposed method have been installed at multiple basketball courts in Beijing,and they provide good performance.

关键词： Computer vision convolutional neural network(CCN) frame difference motion detection object detection real-time system

Efficient Approach for Face Detection in Video Surveillance

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2003年第4期20卷 52-55页

作者：宋红石峰 Department of Computer Science and Engineering Beijing Institute of Technology Beijing 100081 China Department of Computer Science and Engineering Beijing Institute of Technology Beijing 100081 Chinaecurity access control systems and automatic video surveillance systems are becoming increasingly important recently and detecting human faces is one of the indispensable processes. In this paper an approach is presented to detect faces in video surveillance. Firstly both the skin-color and motion components are applied to extract skin-like regions. The skin-color segmentation algorithm is based on the BPNN (back-error-propagation neural network) and the motion component is obtained with frame difference algorithm. Secondly the image is clustered into separated face candidates by using the region growing technique. Finally the face candidates are further verified by the rule-based algorithm. Experiment results demonstrate that both the accuracy and processing speed are very promising and the approach can be applied for the practical use.

Security access control systems and automatic video surveillance systems are becoming increasingly important recently,and detecting human faces is one of the indispensable *** this paper,an approach is presented to detect faces in video ***,both the skin-color and motion components are applied to extract skin-like *** skin-color segmentation algorithm is based on the BPNN (back-error-propagation neural network) and the motion component is obtained with frame difference ***,the image is clustered into separated face candidates by using the region growing ***,the face candidates are further verified by the rule-based *** results demonstrate that both the accuracy and processing speed are very promising and the approach can be applied for the practical use.

关键词： face detection skin-color segmentation BPNN frame difference region growing

Automatic Segmentation of Moving Objects in Video Sequences for Indoor and Outdoor Applications

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2003年第4期10卷 76-81页

作者： FALAH E. ALSAQRE Institute of Information Science Beijing Jiaotong University

Computer vision systems have an impressive spread both for their practicalapplication and for theoretical research . The common approach used in such systems consists of agood segmentation of moving objects from video sequences . This paper presents an automaticalgorithm for segmenting and extracting moving objects suitable for indoor and outdoor videoapplications, where the background scene can be captured beforehand . Since edge detection is oftenused to extract accurate boundaries of the image's objects, the first step in our algorithm isaccomplished by combining two edge maps which are detected from the frame difference in twoconsecutive frames and the background subtraction . After removing edge points that belong to thebackground, the resulting moving edge map is fed to the object extraction step . A fundamental taskin this step is to declare the candidates of the moving object, followed by applying morphologicaloperations. The algorithm is implemented on a real video sequence as well as MPEG- 4 sequence andgood segmentation results are achieved.

关键词： frame difference background subtraction moving object segmentation cannyedge detection morphological operation

The Design and Implementation of Fire Smoke Detection System Based on FPGA

在线全文

学校读者我要写书评

暂无评论

The Design and Implementation of Fire Smoke Detection System...

第24届中国控制与决策会议

作者： Li Jinghong, Zou Xiaohui, Wang Lu College of Information Science and Engineering Northeastern University, Shenyang 110819,China

This paper uses modular method to design smoke detection system. On the basis of the requirement analysis, the paper designs and implements all the modules, including image capture module, SDRAM data buffer module, image display module and smoke detection module. Among them the smoke detection module is the core of the system, which decides the performance of the system. Using a synergistic manner through software and hardware, the smoke detection module is realized. First of all, using the algorithm of frame difference, erosion and dilation, it realizes suspected smoke area extraction with hardware description language. This method ensures to process real-time sequential image. And then we detect the suspected smoke areas with smoke dynamic features including smoke area rising feature and smoke regional stability feature. Finally, the paper builds smoke detect module using SOPC Builder, which reads image data captured by CMOS image sensor monitors into SRAM. Based on smoke detect hardware module this paper realizes smoke background fuzzy characteristics based on the 2d discrete wavelet transform in Nios II IDE environment. After a period of debugging and running, the system realizes real-time smoke detection.

关键词： Smoke Detection Smoke Dynamic Features frame difference 2-D Wavelet Transform FPGA

Long Distance Target Detection Based on Multi-sensor Information Fusion

在线全文

cnki会议

学校读者我要写书评

暂无评论

Long Distance Target Detection Based on Multi-sensor Informa...

第十一届中国体视学与图像分析学术会议

作者： Xiong darong , Yang xuan ( College of Information Eng. , Shenzhen Unib. , Shenzhen 518060 ATR National Key Lab. , of Defense Tech. , Shenzhen Unib. , Shenzhen 518060)

Long distance target detection is important in military applications. Multi-sensor provides complementary and redundant information and has advantages for long distance targets detection. In this paper, long distance target detection based on information fusion in visual and thermal infrared image sequences is proposed. The method acquires the moving targets area by frame difference accumulation in two sensor image sequences , and we defined the reliable measurement in the moving target area and got the final moving area using fusion rules. A simple segmentation method extracts the targets in moving area. The detection results are acquired by feature level image fusion. The multi-sensor redundant information enhances the reliability of the detection. The experimental results illustrate that this approach is feasible and robust.

关键词： Visual image sequences Thermal infrared image sequences frame difference Information fusion

Circuit Design of Moving Object Recognition System

在线全文

cnki会议

学校读者我要写书评

暂无评论

Circuit Design of Moving Object Recognition System

第三十九届中国控制会议

作者： Dan Shan Xiaoxu Zhang Wei Lu Department of Electronic Engineering Dalian Neusoft University of Information School of Control Science and Engineering Dalian University of Technology

The traditional moving object recognition and tracking systems are usually based on software environment of PC,so the performance of processing speed, real-time and the size have limitations. In view of this, the circuit design based on Field Programmable Gate Array（FPGA） is proposed, which improves the performance of processing speed and real-time and miniaturization. Aiming at the recognition, tracking and feature point extraction of moving object, 300,000 pixel camera is used for image acquisition, and hardware circuit is used for image processing, including real-time image caching, gray-scale processing, improved bit plane median filtering, segmentation of self-adaptive threshold binarizing, fusing of frame difference and background difference methods for moving object detecting, tracking and feature point extracting. Finally, the recognition results are displayed by HDMI interface displayer. The design takes full advantage of the high-speed and parallel processing ability of FPGA, and combines the high-speed on-chip RAM with the large capacity off-chip SDRAM to realize the processing and storage of video data. After written by Verilog HDL and verified by Modelsim, the physical circuit is implemented in FPGA. This system has the characteristics of strong anti-interference, compact, flexibility, high speed, low power consumption,versatility and scalability, which is suitable for both industrial field and home use.

关键词： frame difference Moving Detection Bit Plane Real-time Low Power Consumption,FPGA