Search

Copyright of Zhejiang Electric Power is the property of Zhejiang Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Railway Standard Design is the property of Railway Standard Design Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Geodesy & Geodynamics (1671-5942) is the property of Editorial Board Journal of Geodesy & Geodynamics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Electrical wiring diagrams， which represent the positions of electrical equipment and describe their wiring and cabling methods， need to be converted into XML for smart grid system scheduling and management. This conversion process is known as vectorization. To address the inefficiencies and time-consuming nature of manual vectorization， this paper proposes a solution for vectorizing electrical wiring diagrams. First， the paper introduces an attention mechanism-enhanced YOLOv3 method for precise recognition and localization of graphic elements in electrical wiring diagrams. Next， it proposes a text region detection algorithm based on multi-scale feature extraction to locate electrical text annotation areas on the diagrams， and uses a CRNN model to recognize their content. Finally， the paper presents a vectorization strategy based on template matching， which analyzes the relationships between electrical elements on the diagrams at the graphic element group level. This method has been practically deployed and can efficiently and accurately complete the vectorization of electrical wiring diagrams， meeting the application needs of power systems.

In view of the problems such as slow processing speed and low accuracy of condition monitoring technology for electrical equipment at this stage, an online status monitoring method of electrical equipment based on the multi change point detection technology and template matching strategy is proposed. Based on the buffer model and the sliding window model, this method uses the TSTKS (Ternary Search Tree and Kolmogorov - Smirnov) algorithm to form the feature vector of the window dimension and the buffer dimension. The running state matching and status switching time positioning of the electrical equipment are realized by template matching of the two dimensions. Simulation experiments results of the household refrigerator show that the proposed method has the advantages of fast detection speed and high accuracy, and can provide a reference for the state monitoring field of electrical equipment. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Geodesy & Geodynamics (1671-5942) is the property of Editorial Board Journal of Geodesy & Geodynamics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Packaging & Food Machinery is the property of Packaging & Food Machinery Magazine and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Zhengzhou University: Engineering Science is the property of Editorial Office of Journal of Zhengzhou University: Engineering Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Donghua University (Natural Science Edition) is the property of Journal of Donghua University (Natural Science) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Real-time speed measurement is a vital issue to assist truck weighing at the entrance of expressway when a truck passes through a scale.Binocular vision technology technically has the advantages of low cost,easy deployment and high stability,which qualify it a potential for prospective application.The key point for binocular vision based speed measurement is displacement-measuring of a target,which is subject to accurate target matching in multiple frames.This paper presents an alignment algorithm on region matching based on spatial location and a calculation method for spatial displacement based on template ma-tching.Specifically,relative spatial location of a wheel is introduced to restrain its matching area,which effectively reduces the mismatching on similar wheels; template matching is derived to track the key points of a wheel for spatial displacement between multiple frames.The practical traffic video data taken at an expressway entrance is applied to experiments.The results show that,compared with other binocular vision based speed measurement methods,our method declines the RMSE of the speed measurement results by 20%～40%,and it more suitable for the real scene when vehicles pass the speed measurement point at the entrance of expressway at a relatively high speed(10~20 km/h).

Traditional data analysis techniques have some problems in processing large-scale medical data detection, such as high time consumption and weak anti-jamming ability. In order to solve these problems, this study presents a fast detection and analysis method for abnormal state of time series data which uses template matching and membership degree analysis techniques. This method uses TSTKS algorithm and sliding window theory to realize rapid detection of multiple mutation points in time series data, extract continuous multi-window fluctuation characteristics, construct a normalized fluctuation vector of time series data, and perform abnormal state detection and analysis on large-scale disease signals. Simulation data and EEG signal analysis show that this method is a relatively fast and accurate method for big data analysis and detection. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Under the influence of scale, occlusion and other factors, the speed and precision of the face detection algorithm are not matched at the same time, and the detection performance is poor. The neural network detector algorithm incorporating the idea of template matching is adopted to solve this deficiency. A face detection algorithm for dual-shot neural network matching is proposed. Thus, an improved method for matching the detection speed and precision is obtained. Firstly, constructing a face template framework and setting a certain threshold according to the five-feature position relation. Secondly, according to the robustness of the constructed template and anchor strategy to different scales of face, extracting and labeling the face area in the sample data in the feature enhancement module layer of the DSFD (dual shot face detector). Finally, matching the correction between the extracted and marked face area and the constructed template. The experimental results on face data sets, such as Face Detection Data Set and Benchmark, FDDB and WIDER FACE indicate that the improved algorithm ensures the accuracy while improving the detection speed, and its advantage is more obvious than that of several similar algorithms.

Objectives：Target tracking has been widely used in pedestrian tracking, automatic driving, target monitoring and other fields. The existing tracking methods in single camera have limited tracking range and relatively slow. The existing person re ‐identification methods rely on the pedestrian detection to establish image database, and all the methods may miss detection or lead to false detection. Therefore, in order to meet the needs of pedestrian tracking in large ‐scale scenes, a continuous pedestrian tracking method for vertical mounted camera is studied, which has better tracking robustness and faster speed. Methods: For tracking in a single camera, a discriminative correlation filter with detection and spatial reliability (DSR ‐ DCF) was proposed. Firstly, the Gaussian mixture model was used to eliminate the background, and the minimum circumscribed rectangle of the target was extracted to select the tracking target. Then, 32 dimensional histogram of oriented gradient (HOG) feature and 1 dimensional grayscale feature are used as pedestrian feature description, and spatial reliability and detection reliability are applied to correlation filter to realize pedestrian tracking in single camera. In the process of tracking pedestrians across cameras, according to the imaging characteristics of pedestrians in the vertical mounted camera, the speeded up robust features (SURF) algorithm was used to match the features of overlapping areas. The homography matrix between adjacent shots was calculated according to the matching feature points to determine the best search area of tracking target in the adjacent camera. Finally, taking the pedestrian obtained by Gaussian mixture model background elimination in the search area and template pedestrian as input, and using the sum of absolute difference(SAD) as the matching measure, the real‐time cross‐lens continuous tracking of pedestrian was realized through template matching. Results: Scene simulation and tracking experiments were carried out with four cameras with a resolution of 1 920×1 080 pixels. The success rate was tested by online object tracking benchmark (OTB), and compared with kernelized correlation filters (KCF), discriminative correlation gilter with channel and spatial reliability (CSR ‐ DCF) and other methods. The results show that the background elimination of Gaussian mixture model can extract all pedestrians, and there is no missing or false detection. When tracking across cameras, the best search range is 5 times of the initial tracking window size. In continuous tracking, the average speed of the proposed method can reach 21.8 frames/ s, and the tracking success rate is better, especially in the case of illumination change, deformation, complex background and occlusion. Conclusions: The single camera tracking method DSR ‐ DCF, combined with search area restriction and template matching, can realize the continuous pedestrian tracking across camera. The tracking speed and success rate can meet the real ‐ time requirements, and the tracking speed is better than 21 frames/s. [ABSTRACT FROM AUTHOR]

Copyright of Journal Of Sichuan University (Natural Sciences Division) / Sichuan Daxue Xuebao-Ziran Kexueban is the property of Editorial Department of Journal of Sichuan University Natural Science Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Food & Machinery is the property of Food & Machinery Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Light Industry Machinery is the property of Light Industry Machinery Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The traditional capacitor appearance defect detection adopts manual detection, which has low efficiency, high error rate and high cost. In order to overcome the shortcomings of manual detection and improve the automation of capacitor production, a machine vision based capacitor defect detection system is designed. Firstly, the image is collected, pre-processed, and matched to the capacitor area. Then the threshold segmentation is used to detect the defects of the overflow and epoxy surface pores. The template matching is used to detect the characters and the shell damage defects. Finally, to meet the testing requirements of different standards，the Blob analysis is used to extract the defect features and set the threshold parameters. According to the experimental results of the prototype, the detection system greatly improves the detection efficiency and accuracy.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper proposes a target tracking algorithm based on mean shift and template matching. The algorithm is divided into three stages:prediction, template matching, target positioning, and template updating. In the prediction stage, combined with the target position obtained from the previous frame tracking, the target position is predicted using the mean shift method, and the template matching search gate is defined with the predicted position as the center and the corresponding size as the coverage area. At the template matching stage, using fast template matching algorithm, the target template and search gate are quickly matched from coarse to fine, and the matching degree between matching result and target template is calculated. If the matching degree is greater than the given threshold, the fast template matching will be performed and the result will be used as the tracking result of the current frame image. Otherwise, the target position predicted by the mean shift algorithm is used as the tracking results of the current frame image. Finally, the template updating process is controlled by the tracking results of the current frame to update the target template, and the stable tracking of the target is finally completed. At the same time, the algorithm improves the robust of tracking by combining the advantages of color and edge features to the insensitivity of rotation and deformation. The method has fast calculation speed and high accuracy, it can meet real-time requirements.

During the detection of laser spot center, in order to improve the calculation efficiency under the premise of ensuring the location accuracy of the spot center, an improved template matching algorithm was used for theoretical analysis and experimental verification. The results show that: In the case of no exposure, the average calculation time of the adaptive region of interest (ROI) is 897s, while the average calculation time of the traditional template matching algorithm is 3388s. In the presence of exposure, the average calculation time of the adaptive ROI is 921 s, and the average calculation time of the traditional template matching algorithm is 3389s. The improved adaptive algorithm has achieved excellent performance in the experimental test of laser spot positioning, which shows that it can improve the calculation efficiency under the premise of ensuring accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

When extracting the skeleton of the crack image, the existing algorithms usually had problems such as the missing information of the skeleton body after the refinement, and the burr removal effect decreased rapidly with the increase of the image size. Aiming at the above problems, this algorithm proposed a crack matching algorithm for template matching and high adaptive burr removal. Firstly, it improved the Rosenfeld refinement algorithm by combining template matching to preserve the skeleton structure. Then proposed a high adaptive burr removal algorithm. The ratio of the number of branch pixels to the number of target pixel points of the refined skeleton image was used as the criterion to effectively adapt to the crack image of different target pixel density and scale. The experimental results show that the algorithm can effectively realize the single pixel width skeleton and remove the redundant skeleton burrs as much as possible, which has certain feasibility and superiority. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to reduce the detection of false positive m月SSeS and improve the matching rate of the double V1e41 lump， a method of double templates matching to detect the suspicious lesions area has been proposed. paper then， uses the susplelOUS leslOns In the CC-V1eW area t0 1(lentlfy the matChlng bar area In the MLO-mew firstly. This fend }t uses double Sech-template to detect lumps，the areas of high correlation coefficient will be suspicious }eS1l1nS }3.re}3.. After deleting the false positive regions，it fuse the different size template results based shape and area. information. This Finally， paper m月tc卜. it is realized that the m月SS matching which have by measuring the similarity based On rules of mutual selects 100 pairs The experimental of images been confirmed to carry out the experiments of suspicious lesions mass matching in results show that ninety pairs of images have been achieved double-view comparing with the gray-scale layering algorithm.

The defect detection of date code relies mainly upon manual inspection. Due to the high complexity of time and the low accuracy, the existing algorithms for detecting the defect of codes can not obtain a wide range of applications in industry.For such a situation, this paper proposed an algorithm named PRICP based on iterative registration. This algorithm first abstracted the date code as a point feature, and then registered the template and feature points to achieve the purpose of detecting the defect. Machine learning as an upgrade auxiliary function, it improved its accuracy, robustness and defect classification ability. This algorithm successfully applied to the inspection of the date code of Tsingtao. The operation results demonstrate that the algorithm insensitive to constraint conditions, background and noise is superior to the traditional method in terms of robustness and efficiency, can detect the defect of information codes of multiple connected domains fastly and be directly applied to other visual field. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problem of slow object recognition and low working accuracy of mobile manipulators, the object recognition and positioning algorithm and the robot operation accuracy improvement method were studied. Based on hardware such as omnidirectional mobile platform, industrial robot and monocular camera, a mobile manipulators system was constructed. The monocular visual template matching methods were summarized, and the feature point matching algorithm based on random tree classification was used to quickly and accurately identify and locate the objects. Camera calibration and robot hand-eye calibration was completed. The relationship between hand-eye pose and grab pose was analyzed. A compensation method for the correction of the hand-eye pose was proposed to reduce the working error. Finally, the grab/place experiment of the mobile manipulator was performed. The research results indicate that using the methods proposed above the objects are quickly and accurately identified and the working error is effectively reduced so that high working accuracy is achieved. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In view of problem that it is easy to produce interference between objects with the similar colors while using traditional Camshift algorithm for drill tracking, a drill counting method based on improved Camshift algorithm was proposed. Improved Camshift algorithm was used to capture drill targets real timely, and then drill counting was realized by setting anchor and determining time interval. The improved Camshift algorithm uses template matching method to locate tracking target, intelligently selects appropriate method to extract color histogram, meanwhile introduces particle filters to get exact location of the tracking target in the next frame by combining texture features through certain mechanisms. Experimental results show that the improved algorithm solves the interference problem of similar colors, and is still able to accurately track the target in conditions of partial cover, consequently achieves accurate drill counting.

Aiming at the shortcomings of complicated algorithm and low accuracy of the existing algorithm of textile yarn tube color sorting,based on machine vision, a color sorting algorithm for spinning tubes is proposed. The target image captured by CCD color camera is performed color shift correction, filtering and other operations.The various yarn tube color information obtained is saved as template,and then the detected image and template are matched by improved color difference method. Experimental results show that the algorithm is simple and reliable, effectively improving the accuracy of image color recognition, and keeping the margin of error below 5%.It has good portability and can be used for the sorting of textile yarn tubes of different colors. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Ａｉｍｉｎｇ ａｔ ｔｈｅ ｐｒｏｂｌｅｍｓ ｏｆ ｄｅｆｅｃｔｓ ｉｎ ＰＥＴ ｂｏｔｔｌｅ ｃａｐｐｉｎｇ ｐｒｏｄｕｃｔｉｏｎ ｌｉｎｅ, ａ ｄｅｔｅｃｔｉｏｎ ａｌｇｏｒｉｔｈｍ ｂａｓｅｄ ｏｎ ｍａｃｈｉｎｅ ｖｉｓｉｏｎ ｔｅｃｈｎｏｌｏｇｙｗａｓ ｐｒｏｐｏｓｅｄ. Ｆｉｒｓｔｌｙ, ｔｈｅ ｈａｒｄｗａｒｅ ｐｌａｔｆｏｒｍ ｏｆ ｔｈｅ ｓｙｓｔｅｍ ｗａｓ ｂｕｉｌｔ, ｓｏ ｔｈａｔ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ｄｉｆｆｉｃｕｌｔｉｅｓ ｗｅｒｅ ａｎａｌｙｚｅｄ. Ｔｈｅ ｔｅｍｐｌａｔｅ ｍａｔｃｈｉｎｇ ａｌｇｏｒｉｔｈｍ ｗａｓ ｉｎｔｒｏｄｕｃｅｄ ｔｏ ｄｅｔｅｃｔ ｔｈｅ ｐｒｅｓｅｎｃｅ ｏｒ ａｂｓｅｎｃｅ ｏｆ ｔｈｅ ｃａｐ, ａｎｄ ｔｈｅ ｒｅｇｉｏｎｓ ｏｆ ｔｈｅ ｅｍｂｒｙｏ ｒｉｎｇ ａｎｄ ｕｐｐｅｒ ｅｄｇｅ ｏｆ ｔｈｅ ｃａｐ ｗｅｒｅ ｐｏｓｉｔｉｏｎｅｄ ｆｒｏｍ ｔｈｅ ｍａｔｃｈｉｎｇ ｒｅｓｕｌｔｓ. Ｔｈｅｎ, ｔｈｅ Ｈａｒｒｉｓ ｃｏｒｎｅｒ ｄｅｔｅｃｔｉｏｎ ａｌｇｏｒｉｔｈｍ ｗａｓ ｕｓｅｄ ｔｏ ｆｉｔ ｔｈｅ ｓｔｒａｉｇｈｔ ｌｉｎｅ ｏｆ ｔｈｅ ｅｍｂｒｙｏ ｒｉｎｇ. Ｆｕｒｔｈｅｒ￣ｍｏｒｅ, ｔｈｅ Ｃａｎｎｙ ａｌｇｏｒｉｔｈｍ ａｎｄ ｔｈｅ ｌｅａｓｔ ｓｑｕａｒｅｓ ａｌｇｏｒｉｔｈｍ ｗｅｒｅ ｕｓｅｄ ｔｏ ｆｉｔ ｔｈｅ ｓｔｒａｉｇｈｔ ｌｉｎｅ ｏｆ ｕｐｐｅｒ ｅｄｇｅ ｏｆ ｔｈｅ ｃａｐ. Ｆｉｎａｌｌｙ, ｂｙ ｃａｌｃｕｌａｔｉｎｇ ｔｈｅ ａｎｇｌｅ ａｎｄ ｄｉｓｔａｎｃｅ ｂｅｔｗｅｅｎ ｔｈｅ ｌｉｎｅ ｏｆ ｕｐｐｅｒ ｅｄｇｅ ｏｆ ｔｈｅ ｃａｐ ａｎｄ ｔｈｅ ｒｅｆｅｒｅｎｃｅ ｌｉｎｅ, ｔｈｅ ｄｅｆｅｃｔｓ ｏｆ ｉｎｃｌｉｎｅｄ ｃａｐ ａｎｄ ｈｉｇｈ ｃａｐ ｗｅｒｅ ｃａｔｅｇｏｒｉｚｅｄ. Ｔｈｅ ｒｅｓｕｌｔｓ ｉｎｄｉｃａｔｅ ｔｈａｔ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ａｌｇｏｒｉｔｈｍ ｈａｓ ｇｒｅａｔ ｄｅｔｅｃｔｉｏｎ ｒｅｓｕｌｔ ａｎｄ ｅｆｆｉｃｉｅｎｔ ｒｅａｌ￣ｔｉｍｅ ｐｒｏｃｅｓｓｉｎｇ ｅｆｆｉｃｉｅｎｃｙ, ｗｉｔｈ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ａｃｃｕｒａｃｙ ｕｐ ｔｏ ９９％, ｔｈｅ ｄｅｔｅｃｔｉｏｎ ｅｆｆｉｃｉｅｎｃｙ ｉｓ ｌｅｓｓ ｔｈａｎ １００ｍｓ. [ABSTRACT FROM AUTHOR]

Ａｉｍｉｎｇ ａｔ ｉｍｐｒｏｖｉｎｇ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ｓｐｅｅｄ ｏｆ ｂｏｔｔｌｅ ｃａｐ ｐｒｉｎｔｅｄ ｃｏｄｅ ｒｅｃｏｇｎｉｔｉｏｎ ｉｎ ｐｒｉｎｔｉｎｇ ｉｎｄｕｓｔｒｙꎬ ａｎ ｉｍｐｒｏｖｅｄ ｔｅｍｐｌａｔｅ ｍａｔｃｈｉｎｇ ａｌｇｏｒｉｔｈｍ ｂａｓｅｄ ｏｎ Ｍａｔｌａｂ ｉｍａｇｅ ｉｎｔｅｇｒａｌ ｗａｓ ｐｒｏｐｏｓｅｄ ｔｈｒｏｕｇｈ ｔｈｅ ｓｔｕｄｙ ｏｆ ｉｍａｇｅ ｉｎｔｅｇｒａｌ ａｌｇｏｒｉｔｈｍ ａｎｄ ｔｈｅ ｉｍｐｒｏｖｅｍｅｎｔ ｏｆ ｃｏｒｒｅｌａｔｉｏｎ ｃｏｅｆ￣ ｆｉｃｉｅｎｔ ｃａｌｃｕｌａｔｉｏｎ ｆｏｒｍｕｌａ ｉｎ ｔｅｍｐｌａｔｅ ｍａｔｃｈｉｎｇ. Ａｎ ｅｘｐｅｒｉｍｅｎｔａｌ ｍｅｔｈｏｄ ｗａｓ ｄｅｓｉｇｎｅｄ ｔｏ ａｃｑｕｉｒｅ ｔｈｅ ｉｍａｇｅ ｓｉｇｎａｌ ｔｈｒｏｕｇｈ ｔｈｅ ＣＣＤ ｉｎｄｕｓｔｒｉ￣ ａｌ ｃａｍｅｒａꎬ ｔｏ ｐｒｏｃｅｓｓ ｔｈｅ ｉｍａｇｅ ｉｎｔｅｇｒａｌ ｐｒｏｃｅｓｓｉｎｇ ａｎｄ ｆｏｕｒ ｃｈｅｃｋ ｖａｌｕｅｓ. Ｔｈｅ ｐｉｘｅｌｓ ｉｎ ｔｈｅ ｔａｒｇｅｔ ａｒｅａ ｗａｓ ｄｅｔｅｒｍｉｎｅｄ ｑｕｉｃｋｌｙ ｔｏ ｏｂｔａｉｎ ｔｈｅ ｃｏｒｒｅｌａｔｉｏｎ ｃｏｅｆｆｉｃｉｅｎｔｓ. Ｔｈｅ ｆｅａｓｉｂｉｌｉｔｙ ｏｆ ｔｈｅ ａｌｇｏｒｉｔｈｍ ｗａｓ ｖｅｒｉｆｉｅｄ ｂｙ Ｍａｔｌａｂ ｓｏｆｔｗａｒｅ ｐｒｏｇｒａｍｍｉｎｇ ｔｅｓｔ ａｎｄ ｔｈｅ ｍｅｍｏｒｙ ｒｅａｄｉｎｇ ｏｖｅｒｈｅａｄ ｏｆ ｔｈｅ ｏｒｉｇｉｎａｌ ｔｅｍｐｌａｔｅ ｍａｔｃｈｉｎｇ ａｌｇｏｒｉｔｈｍ ｗａｓ ｇｒｅａｔｌｙ ｒｅｄｕｃｅｄ. Ｔｈｅ ｒｅｓｕｌｔｓ ｉｎｄｉｃａｔｅ ｔｈａｔꎬ ｉｎ ｔｅｒｍｓ ｏｆ ｄｅｔｅｃｔｉｏｎ ｓｐｅｅｄꎬ ｔｈｅ ｉｍｐｒｏｖｅｄ ｍａｔｃｈｉｎｇ ａｌｇｏｒｉｔｈｍ ｃａｎ ｉｎｃｒｅａｓｅ ｓｐｅｅｄ ｕｐ ｍｏｒｅ ｔｈａｎ ２０％ ｃｏｍｐａｒｅｄ ｗｉｔｈ ｔｈｅ ｔｒａｄｉｔｉｏｎａｌ ｍａｔｃｈｉｎｇ ａｌｇｏｒｉｔｈｍ. [ABSTRACT FROM AUTHOR]

Ａｉｍｉｎｇ ａｔ ｔｈｅ ｐｒｏｂｌｅｍｓ ｏｆ ｔｈｅ ｒｅｆｌｅｃｔｉｏｎ￣ｌｉｇｈｔ ｉｎｔｅｒｆｅｒｅｎｃｅ ａｎｄ ｔｈｅ ｄｉｆｆｉｃｕｌｔｙ ｏｆ ｄｅｔｅｃｔｉｎｇ ｌａｒｇｅ ｓｉｚｅ ａｌｕｍｉｎｕｍ ａｌｌｏｙ ｐａｒｔｓ ｉｎ ｔｈｅ ｄｉ￣ ｍｅｎｓｉｏｎ ｅｒｒｏｒｓ ｄｅｔｅｃｔｉｏｎ ｐｒｏｃｅｓｓꎬ ｔｈｅ ｍａｃｈｉｎｅ ｖｉｓｉｏｎ ｓｙｓｔｅｍꎬ ｉｍａｇｅ ｓｙｎｔｈｅｓｉｓꎬ ａｎｄ ｉｍａｇｅ ｐｒｏｃｅｓｓｉｎｇ ｗｅｒｅ ｓｔｕｄｉｅｄ. Ｔｈｅｎꎬａｎ ａｕｔｏｍａｔｉｃ ｄｅｔｅｃ￣ ｔｉｏｎ ｍｅｔｈｏｄ ｂａｓｅｄ ｏｎ ｍａｃｈｉｎｅ ｖｉｓｉｏｎ ｓｙｓｔｅｍ ｗａｓ ｐｒｏｐｏｓｅｄ. Ｔｈｅ ｈｉｇｈ ｐｒｅｃｉｓｉｏｎ ｉｍａｇｅｓ ｆｏｒ ｌａｒｇｅ ｓｉｚｅ ｐａｒｔｓ ｗｅｒｅ ｏｂｔａｉｎｅｄ ｂｙ ｕｓｉｎｇ ａ ｃｏａｘｉａｌ ｐａｒａｌｌｅｌ ｌｉｇｈｔ ｓｙｓｔｅｍ ａｎｄ ａ ｔｗｏ￣ａｘｉｓ ｍｏｔｉｏｎ ｐｌａｔｆｏｒｍ. Ｉｎ ｏｒｄｅｒ ｔｏ ｏｂｔａｉｎ ａ ｈｉｇｈｅｒ ｄｅｔｅｃｔｉｏｎ ａｃｃｕｒａｃｙꎬ ｔｈｅ ｌｏｃａｌ ｈｉｇｈ ｐｒｅｃｉｓｉｏｎ ｉｍａｇｅｓ ｗｅｒｅ ｃａｐ￣ ｔｕｒｅｄ ａｎｄ ｔｈｅｎ ｓｐｌｉｃｅｄ ｔｏｇｅｔｈｅｒ ｔｏ ｒｅｂｕｉｌｄ ｔｈｅ ｗｈｏｌｅ ｉｍａｇｅ ｏｆ ｔｈｅ ａｌｕｍｉｎｕｍ ａｌｌｏｙ ｐａｒｔꎬ ｗｈｉｃｈ ａｌｌｏｗｓ ｔｈｉｓ ｍｅｔｈｏｄ ｔｏ ｄｅｔｅｃｔ ｌａｒｇｅ ｓｉｚｅ ｐａｒｔｓ ｗｉｔｈ￣ ｏｕｔ ｓｉｚｅ ｌｉｍｉｔａｔｉｏｎ. Ｔｈｅ ｐｒｅｐｒｏｃｅｓｓ ａｎｄ ｆｅａｔｕｒｅ ｅｘｔｒａｃｔｉｏｎ ｏｆ ｔｈｅ ｏｂｔａｉｎｅｄ ｉｍａｇｅｓ ｗｅｒｅ ｐｅｒｆｏｒｍｅｄ ｂｙ ｖｉｓｕａｌ ｉｎｓｐｅｃｔｉｏｎ ｔｅｃｈｎｏｌｏｇｙ. Ｔｈｅ ｐａｒｔ ｅｄ￣ ｇｅｓ ｗｅｒｅ ｅｘｔｒａｃｔｅｄ ｂｙ ｕｓｉｎｇ Ｃａｎｎｙ ｏｐｅｒａｔｏｒ ｃｏｍｂｉｎｅｄ ｗｉｔｈ ｂｉｌｉｎｅａｒ ｉｎｔｅｒｐｏｌａｔｉｏｎ ｍｅｔｈｏｄꎬ ｗｈｉｃｈ ｃａｎ ｏｂｔａｉｎ ｓｕｂ￣ｐｉｘｅｌ ｐｒｅｃｉｓｉｏｎ ｆｏｒ ｔｈｅ ｐａｒｔ ｅｄ￣ ｇｅｓ. Ｔｈｅ ｄｉｍｅｎｓｉｏｎ ｅｒｒｏｒｓ ｏｆ ａｌｕｍｉｎｕｍ ａｌｌｏｙ ｐａｒｔｓ ｗｅｒｅ ｄｅｔｅｒｍｉｎｅｄ ｂｙ ｍａｔｃｈｉｎｇ ｔｈｅｓｅ ｐｒｏｃｅｓｓｅｄ ｉｍａｇｅｓ ｗｉｔｈ ｔｈｅ ＣＡＤ ｄｒａｗｉｎｇｓ. Ｔｈｅ ｒｅｓｕｌｔｓ ｉｎｄｉｃａｔｅ ｔｈａｔ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ａｃｃｕｒａｃｙ ｉｓ ｈｉｇｈｅｒ ｔｈａｎ ０. ０２ｍｍꎬ ｗｈｉｃｈ ｃａｎ ｍｅｅｔ ｔｈｅ ｒｅｑｕｉｒｅｍｅｎｔ ｏｆ ｔｈｅ ａｕｔｏｍａｔｉｃ ｄｅｔｅｃｔｉｏｎ ｆｏｒ ｔｈｅ ａｌｕｍｉｎｕｍ ａｌｌｏｙ ｐａｒｔ ｍａｎｕｆａｃｔｕｒｅ. [ABSTRACT FROM AUTHOR]

Ａｉｍｉｎｇ ａｔ ｔｈｅ ｐｒｏｂｌｅｍ ｔｈａｔ ａｎ ｉｎｄｕｓｔｒｉａｌ ｒｏｂｏｔ ｈｏｗ ｔｏ ｑｕｉｃｋｌｙ ａｎｄ ａｕｔｏｎｏｍｏｕｓｌｙ ｉｄｅｎｔｉｆｙ ａｎｄ ｃａｐｔｕｒｅ ａ ｓｐｅｃｉｆｉｅｄ ｔａｒｇｅｔ ａｒｔｉｆａｃｔ ｕｎｄｅｒ ｍｕｌｔｉ￣ｔａｒｇｅｔ ｃｏｎｄｉｔｉｏｎｓ, ｍｏｎｏｃｕｌａｒ ｖｉｓｉｏｎ ｗａｓ ａｐｐｌｉｅｄ ｔｏ ｔｈｅ ｄｅｓｉｇｎ ｏｆ ａｎ ｉｎｔｅｌｌｉｇｅｎｔ ｇｒａｓｐｉｎｇ ｓｙｓｔｅｍ ｆｏｒ ｉｎｄｕｓｔｒｉａｌ ｒｏｂｏｔｓ. Ｉｎ ｏｒｄｅｒ ｔｏ ｅｓｔａｂｌｉｓｈ ｔｈｅ ｒｅｌａｔｉｏｎｓｈｉｐ ｂｅｔｗｅｅｎ ｔｈｅ ｖｉｓｕａｌ ｉｍａｇｅ ａｎｄ ｔｈｅ ｗｏｒｋｐｉｅｃｅ ｐｏｓｉｔｉｏｎｉｎｇ ａｎｄ ｇｒａｐｐｉｎｇ, ｔｈｅ ｐａｔｔｅｒｎ ｒｅｃｏｇｎｉｔｉｏｎ, ｄｅｔｅｃｔｉｏｎ ａｎｄ ｌｏｃａｔｉｏｎ ｕｓｉｎｇ ｉｍａｇｅｓ ｗｅｒｅ ｓｔｕｄｉｅｄ, ａｎｄ ａ ｍｏｎｏｃｕｌａｒ ｖｉｓｉｏｎ ｃａｐｔｕｒｅ ｓｙｓｔｅｍ ｂａｓｅｄ ｏｎ ｃｏｎｔｏｕｒ Ｈｕ ｉｎｖａｒｉａｎｔ ｍｏｍｅｎｔｓ ｆａｓｔ ｔｅｍｐｌａｔｅ ｍａｔｃｈｉｎｇ ａｌｇｏｒｉｔｈｍ ｗａｓ ｐｒｏｐｏｓｅｄ. Ｆｉｒｓｔｌｙ, ｔｈｅ ｉｍａｇｅ ｄａｔａ ｃｏｌｌｅｃｔｅｄ ｆｒｏｍ ｔｈｅ ｃａｍｅｒａ ｓｈｏｕｌｄ ｂｅ ｐｒｅｐｒｏｃｅｓｓｅｄ, ｔｈｅｎ ｔｈｅ ｔａｒｇｅｔ ｗａｓ ｉｄｅｎｔｉｆｉｅｄ ｂｙ ｔｈｅ ｔｅｍｐｌａｔｅ ｍａｔｃｈｉｎｇ ｍｅｔｈｏｄ ｂａｓｅｄ ｏｎ ｔｈｅ ｃｏｎｔｏｕｒ Ｈｕ ｉｎｖａｒｉａｎｔ ｍｏｍｅｎｔ, ａｎｄ ｔｈｅ ｐｏｓｉｔｉｏｎ ｏｆ ｔｈｅ ｔａｒｇｅｔ ｗｏｒｋｐｉｅｃｅ ｗａｓ ｏｂｔａｉｎｅｄ ｂｙ ｕｓｉｎｇ ｔｈｅ ｃｏｎｔｏｕｒ ｍｏｍｅｎｔ ａｎｄ ｔｈｅ ｐｒｉｎｃｉｐｌｅ ｏｆ ｓｅｃｏｎｄ￣ｏｒｄｅｒ ｍｏｍｅｎｔ ｏｆ ｉｎｅｒｔｉａ. Ｆｉｎａｌｌｙ, ｔｈｒｏｕｇｈ ｔｈｅ ｅｓｔａｂｌｉｓｈｍｅｎｔ ｏｆ ＳＯＣＫＥＴ ｃｏｍｍｕｎｉｃａｔｉｏｎ, ｔｈｅ ｄｅｓｉｒｅｄ ｐｏｓｅ ｗａｓ ｓｅｎｔ ｔｏ ｔｈｅ ｍａｎｉｐｕｌａｔｏｒ ｃｏｎｔｒｏｌ ｓｙｓｔｅｍ ｔｏ ｇｕｉｄｅ ｔｈｅ ｍａｎｉｐｕｌａｔｏｒ ｔｏ ｇｒａｓｐ. Ｂａｓｅｄ ｏｎ ＶＳ ｓｏｆｔｗａｒｅ ｄｅｖｅｌｏｐｍｅｎｔ ｐｌａｔｆｏｒｍ ａｎｄ ＡＢＢ ｒｏｂｏｔ , ｔｈｅ ｉｎｔｅｌｌｉｇｅｎｔ ｇｒａｓｐｉｎｇ ｓｙｓｔｅｍ ｗａｓ ｂｕｉｌｔ ａｎｄ ｔｅｓｔ. Ｔｈｅ ｒｅｓｕｌｔｓ ｉｎｄｉｃａｔｅ ｔｈａｔ ｔｈｅ ｉｎｄｕｓｔｒｉａｌ ｒｏｂｏｔ ｉｎｔｅｌｌｉｇｅｎｔ ｇｒａｓｐｉｎｇ ｓｙｓｔｅｍ ｂａｓｅｄ ｏｎ ｍｏｎｏｃｕｌａｒ ｖｉｓｉｏｎ ｈａｓ ｌｏｗ ｃｏｓｔ,ｈｉｇｈ ｐｏｓｉｔｉｏｎｉｎｇ ａｃｃｕｒａｃｙ ａｎｄ ｍｅｅｔｓ ｔｈｅ ｎｅｅｄｓ ｏｆ ｉｎｄｕｓｔｒｉａｌ ａｕｔｏｍａｔｉｏｎ ｐｒｏｄｕｃｔｉｏｎ. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To realize the long-term tracking, there are a number of problems such as scale and illumination changes, partial occlusions which need to be addressed. Some existing tracking algorithms can handle these problems hut still have had performance on the real-time of system because of large amount of calculation which make the fast object tracking research become more popular and challenging recently. This paper proposed an improved TLD (tracking-learning-detection) fast object tracking algorithm, which was obtained by making several improvements based on the original TLD algorithm proposed by foreign scholars Zdenek Kalal etc. The improved algorithm explored a method of adjusting image resolution dynamically according to the area ratio between object and whole picture frame which could reduce the number of samples overall and tried to generate samples from the neighboring region of object to narrow detection range. It also replaced the method of template matching in the detection part, using fast template matching algorithm to improve the efficiency of algorithm. The experimental results show that the improved TLD algorithm proposed can handle these problems above ,as a result the computational complexity of algorithm is reduced and the operation speed of system is also improved. This algorithm ensures the accuracy of object tracking and has a good performance on the real-time in video surveillance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper proposes a vector polygon pattern recognition method based on the wavelet descriptor. In order to minimize the amount of calculation we calculate wavelet coefficient matrix of the target and the template polygons. Using this matrix, we calculate the similarity between these two polygons. We can determine through the similarity, whether or not these two polygons can he matched. Due to the nature of the selected wavelet, the comparison can he made by using the coefficients which can reflect the characteristic of polygon, so that the recognition effect is more effective. Experimental results show that the method is efficient and not sensitive to translation, rotation, and zoom transform. [ABSTRACT FROM AUTHOR]