检索结果-内蒙古大学图书馆

Rough Surface Wear Analysis Using Image Processing Techniques

IFAC-PapersOnLine 2016年第31期49卷 7-12页

作者： Takimoto, Rogério Yugo de Sales Guerra Tsuzuki, Marcos Ueda, Edson Kenji Sato, André Kubagawa de Castro Martins, Thiago Cousseau, Tiago Tanaka, Deniol Sinatora, Amilton Escola Politécnica da Universidade de São Paulo Mechatronics and Mechanical Systems Engineering Department Computational Geometry Laboratory São Paulo Brazil Escola Politécnica da Universidade de São Paulo Mechatronics and Mechanical Systems Engineering Department Surface Phenomema Laboratory São Paulo Brazil United States

Due to the great interest of the automotive industry to quickly and systematically evaluate low wear quantities a new approach based on image processing is presented. By comparing the captured rough surface point cloud using optical interferometry before and after wear, the proposed algorithm was able to estimate the amount of volume wear and mass loss. The proposed algorithm has two main steps. In the first step, the 3D point clouds obtained before and after wear are mapped to 2D images, and conventional edge detection algorithms are applied. Keypoints are determined using the SIFT algorithm on both images (before and after the wear), followed by the use of the ransac algorithm to create a good 2D registration between both 2D images. In the second step an enhanced ICP algorithm is used to perform a 3D registration. The main advantage of this method is the visualization of the wear geometry provided by the wear topography. The proposed algorithm was tested and the results are presented. © 2016

关键词： Edge detection Automotive industry Image processing Image registration Optical data processing Surface measurement 3D registration Edge detection algorithms Image processing technique Optical interferometry Point cloud registration ransac algorithm SIFT SIFT algorithms

来源：评论

学校读者我要写书评

暂无评论

Grey wolf assisted SIFT for improving copy move image forgery detection

引用

EVOLUTIONARY INTELLIGENCE 2022年第2期15卷 1097-1108页

作者： Devi, Moka Uma Babu, Uppu Ravi Acharya Nagarjuna Univ Guntur 522510 Andhra Pradesh India DRK Eng Coll & Technol Hyderabad 500043 India

Copy-move forgery is a general widespread type of digital image forgery, where a segment of an image is attached into a new portion of the similar image to hide or replicate the parts which are called forgered image. The forgered image appears original, as the objective region in spite of being forged, has attained the fundamental qualities of the similar image itself. The capability of the copy-move forgery detection (CMFD) technique is lacked due to some post-processing functions, like JPEG compression scaling, or rotation, etc. Therefore, this paper intends to develop a CMFD using Scale-invariant feature transform (SIFT), best-fin-first algorithm (BBF) and RANdom SAmple Consensus (ransac) directed by grey wolf optimization (GWO) algorithm. Initially, the keypoints are selected using SIFT principle, and BBF algorithm identifies the matched keypoints using keypoint threshold. Further, SIFT feature descriptor is determined, and the final extracted paired keypoints are given to ransac algorithm to remove all the mismatched keypoints. In this CMFD model, the parameters such as parameters keypoint threshold, maximum distance of inliers in ransac and distance threshold in SIFT features are optimized using GWO. The foremost purpose of this research work is maximizing the number of paired keypoints. Hence the proposed model is termed as GWO-based parameter optimization for CMFD (GWPO-CMD). The proposed model is compared over several other meta-heuristic-based keypoint threshold selections and proves its efficiency through diverse analysis.

关键词： Copy-move forgery detection SIFT features Keypoint threshold Best-bin-first GWO algorithm ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

Fast Positioning Method of Truck Compartment Based on Plane Segmentation

IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION

引用

IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION 2022年 6卷 774-778页

作者： Zou, Wenye Shen, Dayong Cao, Puzhen Lin, Chengyang Zhu, Jiangtian Changsha Univ Sci & Technol Sch Elect & Informat Engn Changsha 410114 Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410003 Peoples R China Changsha Ruxin Intelligent Technol Co Ltd Minist Sci & Technol Changsha 410013 Peoples R China

To improve the loading efficiency and shorten the loading time, a method based on LIDAR point cloud segmentation for fast positioning of trucks is proposed for the scenario of level-push automatic loading, in which the truck position and attitude are random. The point cloud data are collected by LIDAR and pre-processed by traditional methods in the order of straight pass filtering, voxel filtering, and plane segmentation. Four planar regions are segmented using the region growth algorithm, and then planar fitting is performed for each of these four regions, which requires a large number of iterations and complex calculations by the traditional planar segmentation method. Focusing on these drawbacks this paper first uses the region growing algorithm to cluster and group the matching points, then combines the least squares and ransac algorithms for plane fitting optimization to calculate the intercept of each plane, and finally uses these intercept values to perform spatial geometry calculations to obtain the exact position and locus of the carriage. Experiments show that the method reduces the number of iterations and improves the computational efficiency compared with the traditional ransac algorithm, thus improving the efficiency and accuracy of the plane fitting algorithm.

关键词： Automatic vehicle loading LIDAR ransac algorithm planar segmentation

来源：评论

学校读者我要写书评

暂无评论

Automated detection of boundary line in paddy field using MobileV2-UNet and ransac

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2022年 194卷 106697-106697页

作者： He, Yong Zhang, Xiya Zhang, Zeqing Fang, Hui Zhejiang Univ Coll Biosyst Engn & Food Sci 866 Yuhangtang Rd Hangzhou 310058 Peoples R China Zhejiang Univ Huzhou Inst Hangzhou Peoples R China Zhejiang Univ Huanan Ind Technol Res Inst Guangzhou 510530 Peoples R China

The detection of boundary lines in farmlands is critical for precision agriculture and automatic navigation. This study proposed a novel method for automatic detection of boundary lines in paddy fields based on images acquired from a vision system. These images were collected from different environmental conditions with wheel marks, shadows, weeds, and uneven illumination in paddy fields. To alleviate the effect of this environmental noise on the detection of boundary lines, the proposed method was designed with the required robustness, which included two sequentially linked phases: farmland area segmentation and boundary line detection. For the segmentation of the farmland area, this study proposed an effective deep learning model, called MobileV2-UNet, which used modified inverted residual blocks and the dilated convolution to achieve the accurate segmentation of the farmland area and nonfarmland area. For the detection of farmland boundary lines, a multiboundary detection method based on the frame correlation and random sample consensus (ransac) algorithm was applied to detect the side boundary and end boundary, which could provide critical information for agricultural machinery steering. Results showed that the mean intersection over union (mIoU) for area segmentation reached 0.908, and the average angular and vertical errors for boundary line detection were 0.865 degrees and 0.021, respectively. Moreover, the processing speed reached 8 frames per second, which could meet the real-time work demands of agricultural machinery.

关键词： Visual navigation Semantic segmentation Boundary line detection ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

Bridge Surface Damage Image Stitching Method Based on SURF algorithm 20

Bridge Surface Damage Image Stitching Method Based on SURF A...

引用

20th COTA International Conference of Transportation Professionals (CICTP) - Advanced Transportation, Enhanced Connection

作者： Da, Xingyu Wang, Xiali Yu, Xin Wang, Lihong Changan Univ Sch Informat Engn Xian 710064 Peoples R China

ISBN: (数字)9780784482933

ISBN: (纸本)9780784482933

With rapid road and bridge development, image-based crack detection technology has become important in current research. For large bridges, obtaining high-precision panoramic images is difficult. Therefore, image-stitching technology with mutual overlap rate producing high-definition images is crucial. In this paper, a low-overlap image mosaic method based on SURF was proposed, which calculates feature points of collected images with low overlap rate by SURF algorithm, then improves Harris operator to enhance angular point adaptability, followed by rough matching through 2 - NN, using ransac (Random Sample Consensus Random sampling uniformity) algorithm. eliminating wrong matching points to conduct accurate matching, and finally using multi-band fusion to solve excessive incoherence in joint-line and process image matching. The results show that image mosaics based on SURF have higher matching accuracy, adaptability, and robustness in the case of low overlap rate, which lays a foundation for further crack detection and has strong application value.

关键词： Image mosaic SURF algorithm ransac algorithm Multi-band fusion

来源：评论

学校读者我要写书评

暂无评论

Salient Object Detection in Video Streams

Salient Object Detection in Video Streams

引用

10th International Symposium on Electronics and Telecommunications (ISETC)

作者： Tapu, Ruxandra Mocanu, Bogdan Tapu, Ermina Univ Politehn Bucuresti Dept Telecommun Fac ETTI Bucharest Romania Univ Politehn Bucuresti Fac Aerosp Engn Dept Descript Geometry & Engn Graph Bucharest Romania

ISBN: (纸本)9781467311762

In this paper we propose a complete framework for automatic detection and tracking of salient objects in video streams. The video flow is firstly segmented into shots based on scale space filtering graph partition method. For each detected shot the associated static summary is developed using a leap keyframe extraction method. Based on the representative images we introduce next a combined spatial and temporal video attention model that is able to recognize both interesting objects and actions in image sequences. The approach extends the state-of-the-art image region based contrast saliency with a temporal attention model. Different types of motion presented in the current shot are determined using a set of homographic transforms, estimated by recursively applying the ransac algorithm on the interest point correspondence. Finally, a decision is taken based on the combined information from both saliency maps. The experimental results validate the proposed framework and demonstrate that our approach is suitable for various types of videos and is robust to noise and low resolution.

关键词： Salient map temporal attention model homography transform ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

FAST OBJECT RE-DETECTION AND LOCALIZATION IN VIDEO FOR SPATIO-TEMPORAL FRAGMENT CREATION

FAST OBJECT RE-DETECTION AND LOCALIZATION IN VIDEO FOR SPATI...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Apostolidis, Evlampios Mezaris, Vasileios Kompatsiaris, Ioannis Ctr Res & Technol Hellas Inst Informat Technol Thermi 57001 Greece

ISBN: (纸本)9781479916030

This paper presents a method for the detection and localization of instances of user-specified objects within a video or a collection of videos. The proposed method is based on the extraction and matching of SURF descriptors in video frames and further incorporates a number of improvements so as to enhance both the detection accuracy and the time efficiency of the process. Specifically, (a) GPU-based processing is introduced for specific parts of the object re-detection pipeline, (b) a new video-structure-based sampling technique is employed for limiting the number of frames that need to be processed and (c) improved robustness to scale variations is achieved by generating and employing additional instances of the object of interest based on the one originally provided by the user. The experimental results show that the algorithm achieves high levels of detection accuracy while the overall needed processing time makes the algorithm suitable for quick instance-based labeling of video and the creation of object-based spatio-temporal fragments.

关键词： Object Re-detection SURF descriptors ransac algorithm Shot Segmentation GPU processing

来源：评论

学校读者我要写书评

暂无评论

An Image Registration Method Based on Improved SIFT algorithm 7

An Image Registration Method Based on Improved SIFT Algorith...

引用

7th International Conference on Advanced Communication and Networking (ACN)

作者： Meng, Qingsong Lv, Zhihui Harbin Univ Sci & Technol Sch Automat Harbin Peoples R China

ISBN: (纸本)9781467379557

The purpose of this paper is to eliminate the mismatch points of image registration. Analyzing the SIFT algorithm and finding mismatch source, according to the source to develop solutions to eliminate the error matching points. And compared with the traditional SIFT registration results. In this paper, firstly do initial matching with SIFT algorithm, then use the feature of key points in spatial domain to eliminate the error matching, Finally, using ransac algorithm to do the final debugging. Experimental results show that the improved SIFT algorithm can better eliminate mismatch points.

关键词： image registration sift algorithm several-for-one matching ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

FAST AUTOMATED SEGMENTATION OF FEMORAL HEADS IN FLUOROSCOPIC X-RAY IMAGES

FAST AUTOMATED SEGMENTATION OF FEMORAL HEADS IN FLUOROSCOPIC...

引用

8th IEEE International Symposium on Biomedical Imaging (ISBI) - From Nano to Macro

作者： Wang, Lei Kohnen, Michael Friman, Ola Hahn, Horst K. Fraunhofer MEVIS Inst Med Image Comp Bremen Germany Stryker Leibinger GmbH & Co KG Freiburg Germany

ISBN: (纸本)9781424441280

In fluoroscopic tracking for fractured femur bone fixation, a precise identification of the femoral head provides valuable guidance for positioning the implant instruments such as nails and screws. Noise, occlusions and weak edges challenge the task of automatically segmenting the femoral head. In this paper, a fast and fully automated method to precisely delineate the femoral head in fluoroscopic X-ray images is presented. The proposed method comprises two stages: First, a candidate circle detection stage using a set of curved Gabor filters and a Gabor-based Hough transform is applied to estimate a few candidate circles approximating the femoral head. Second, a fine circle determination stage extracts the target circle from the candidates by analyzing the anatomical features of the femoral head and its spatial relation to the acetabulum. The validity and robustness of the method were tested on a set of 1184 fluoroscopic images from different vendors.

关键词： Femoral head segmentation Gabor filter Hough transform ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

Bolt looseness detection algorithm based on 2D color space extraction and 3D depth measurement 17

Bolt looseness detection algorithm based on 2D color space e...

引用

17th Conference on Industrial Electronics and Applications (ICIEA)

作者： Yang, Ran Guan, Ziling Lu, Jiang Zhao, Yijing Southwest Jiaotong Univ Sch Elect Engn Chengdu Peoples R China

ISBN: (纸本)9781665409841

This project mainly uses 2D and 3D image processing technology, and develops fault detection algorithm accordingly. The research object we focused on is bolt. In reality, as for the images processing, the shooting environment is complex with different shooting angles, and the change of light in the environment will change the RGB value of the same point. Target detection based on model training is used in the processing. The bolt fault detection is based on the anti-loose line detection model based on two-dimensional image processing. In order to reduce Error detection rate, the color threshold dictionary is introduced to get the optimal threshold, and the bolt depth detection model based on three-dimensional point cloud processing is introduced to jointly complete the fault detection of target faults.

关键词： labellmg YOLO-V4 Object Detection CIoU Loss mean Average Precision Edge detection Mathematical morphology color threshold dictionary point cloud library ransac algorithm

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：