检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： El-Melegy, Moumen T. Assiut Univ Dept Elect Engn Assiut 71516 Egypt

ISBN: (纸本)9781424496365

This paper addresses the problem of fitting a functional model to data corrupted with outliers using a multilayered feed-forward neural network (MFNN). Almost all previous efforts to solve this problem have focused on using a training algorithm that minimizes an M-estimator based error criterion. However the robustness gained from M-estimators is still low. Using a training algorithm based on the RANdom SAmple Consensus (ransac) framework improves significantly the robustness of the algorithm. However the algorithm typically requires prolonged period of time before a final solution is reached. In this paper, we propose a new strategy to improve the time performance of the ransac algorithm for training MFNNs. A statistical pre-test based on Wald's sequential probability ratio test (SPRT) is performed on each randomly generated sample to decide whether it deserves to be used for model estimation. The proposed algorithm is evaluated on synthetic data, contaminated with varying degrees of outliers, and have demonstrated faster performance compared to the original ransac algorithm with no significant sacrifice of the robustness.

关键词： Adaptation models Approximation algorithms Computational modeling Data models M-estimator based error criterion Neural networks ransac algorithm Robustness Training learning (artificial intelligence) multilayer perceptrons multilayered feedforward neural network random sample consensus algorithm robust neural network training sequential probability ratio test statistical analysis

来源：评论

学校读者我要写书评

暂无评论

A Sea-Sky Line Detection Method Based on the ransac algorithm in the Background of Infrared Sea-Land-Sky Images

引用

JOURNAL OF RUSSIAN LASER RESEARCH 2021年第3期42卷 318-327页

作者： Song, Hongfei Ren, Hongkai Song, Yansong Chang, Shuai Zhao, Zhennan Changchun Univ Sci & Technol Sch Optoelect Engn Changchun 130022 Jilin Peoples R China Changchun Univ Sci & Technol Key Lab Fundamental Sci Natl Def Aero & Ground La Changchun 130022 Peoples R China

Subgrade sea and sky monitoring equipment requires the accurate detection of threat targets in a given area. Due to the extremely complex sea-land-sky backgrounds, the sea-sky line is often submerged in the background. Therefore, we propose an algorithm for accurately detecting sea-sky lines under a complex sea-land-sky background. Based on the analysis of infrared images with sea-land-sky backgrounds, we segment images using the k-means algorithm. To use the random sampling consistency (ransac) algorithm to fit the sea-sky line better, we divide the images into nonuniform segments and count the row mean-value gradient trough. The experimental results show that the sea-sky line can be detected in 1215 out of 1227 pictures. The test success rate is 99%, and the difference from the actual sea-sky line is less than 3 pixels. The method presented has higher adaptability under a subgrade sea and sky monitoring environment.

关键词： sea– sky line detection ransac algorithm image segmentation nonuniform segmentation

来源：评论

学校读者我要写书评

暂无评论

DETECTION OF RESTORATION WORK BY APPLYING THE ransac algorithm TO THE POINT CLOUD DATA FROM LASER SCANNING: CASE STUDY AT OSTIA 9

DETECTION OF RESTORATION WORK BY APPLYING THE RANSAC ALGORIT...

引用

9th International Workshop on 3D-ARCH 3D Virtual Reconstruction and Visualization of Complex Architectures

作者： Lim, Y. B. Ogawa, T. Hori, Y. Kyushu Univ Fac Human Environment Studies 744 Motoka Fukuoka Japan

In Ostia, the huge range of excavation carried out by Guido Calza under Mussolini (1938-1942), the zone of contiguous city blocks unearthed in those massive campaigns. From 2012, new survey by a Japanese team of standing remains using laser scanners formed the basis for an analysis of building history, and for a reconstruction of the original building. There is a considerable amount of undocumented reconstruction work in the upper part of the structure which has been identified from analysis of the surface of the walls. The seam and the absence of coursing between the original walls and the later restored works sometimes including in the Roman phase, and sometimes modern using original part of the walls, make difficult to identify which part of walls were original and which were restorations or re-use 80 years later from the excavation. In this paper, the case that the seams are invisible, but its existence is known from the photographic record of the progress of the excavations. The detection by applying the ransac algorithm to the point cloud data from laser scanning relies on several cases of invisible seams running on the surfaces. Additionally, this method allows us without any special knowledge and experience to find detailed characteristics on the surface of the walls, such as slight unevenness or weathering parts, to extrapolate the building history.

关键词： Laser scanning ransac algorithm Restoration Roman building Ostia

来源：评论

学校读者我要写书评

暂无评论

A Lane Detection Method Combined Fuzzy Control with ransac algorithm 7

A Lane Detection Method Combined Fuzzy Control with RANSAC A...

引用

7th International Conference on Power Electronics Systems and Applications - Smart Mobility, Power Transfer and Security (PESA)

作者： Xu, Y. Shan, X. Chen, B. Y. Chi, C. Lu, Z. F. Wang, Y. Q. Shenzhen Univ Coll Mechatron & Control Engn Shenzhen 518060 Peoples R China

ISBN: (纸本)9781538613863

The traditional lane detection methods based on the ransac algorithm used to cause many false detection and unable to accurately detect the lanes in complex road environment, because of the existence of interferential noise points in the set of sampling points. Aiming at these issues, this paper presents a new lane detection method combined fuzzy control with ransac algorithm. The first process of the new lane detection method is pretreatment, the purpose of which is to denoise the image preliminarily through filtering and binarization. And then it selects the region of interest (ROI) that contains lanes in the input image and extract the initial boundary candidate points of the lanes in ROI. So far, there are still a lot of irrelevant noise points in the set of lane boundary candidate points. It would analyze the relationship between the interferential noise points and the boundary points of the lane, and then remove the interferential noise points from the set of lane boundary candidate point by using the fuzzy control. After that, fit the lane model by using ransac algorithm in the set of effective lane boundary points. The experiment shows that the method proposed in this paper has high robustness and effectiveness which can accurately detect the lanes in complicated city road.

关键词： Automatic driving for intelligent vehicles Lane detection Fuzzy control ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

An Improved ransac algorithm Based on Similar Structure Constraints

An Improved RANSAC Algorithm Based on Similar Structure Cons...

引用

International Conference on Robots & Intelligent System (ICRIS)

作者： Zhu, Wenqiu Sun, Wenjing Wang, Yexiang Liu, Shaolin Xu, Keke Hunan Univ Technol Sch Comp & Commun Zhuzhou 412007 Peoples R China Key Lab Intelligent Informat Percept & Proc Techn Zhuzhou 412007 Peoples R China

ISBN: (纸本)9781509041558

An improved ransac algorithm based on structural similarity was proposed to improve the speed and accuracy of traditional ransac (Random Sample Consensus) algorithm and to reduce iterations and runtime. Firstly, BRISK (Binary Robust Invariant Scalable Keypoints) algorithm was used to extract and describe feature points. The initial match set is obtained by hamming distance feature matching. Then, mismatches are eliminated by similar structure constraints. Finally, the new match set is taken as the input of ransac to calculate the transformation matrix. The algorithm can obtain the transformation model quickly because it has purified matching points after the initial matching. Experiments show that the number of iterations and runtime of this algorithm are obviously less than the number of iterations and runtime of the traditional algorithm. So the proposed method outperforms traditional ransac (Random Sample Consensus) algorithm significantly both in iterations and speed.

关键词： ransac algorithm feature matching similar structure purified matching points

来源：评论

学校读者我要写书评

暂无评论

Research on Feature Matching Based on Improved ransac algorithm 15th

Research on Feature Matching Based on Improved RANSAC Algori...

引用

15th International Conference on Intelligent Robotics and Applications (ICIRA ) - Smart Robotics for Society

作者： Wang, Xianfeng Wang, Baitong Ding, Zilin Zhao, Tong Northeast Petr Univ Daqing 163000 Peoples R China

ISBN: (纸本)9783031138355;9783031138348

Aiming at the problems that the current ransac (Random Sample Consensus) algorithm has too large randomness and is susceptible to external point interference, which leads to the reduction of matching accuracy, an improved ransac algorithm combining feature matching confidence and grid clustering is proposed. Firstly, rough matching is carried out by the FLANN algorithm, and confidence analysis is carried out on the coarse matching point pairs, then expanding grid clustering around the high confidence point pairs. Multiple local optimal interior points are screened to optimize the global interior points and improve the matching accuracy of feature points. The experimental results show that the improved ransac in this paper increases the existence probability of interior points, avoids too many wrong feature matching affecting the model effect of the homography matrix, and improves the accuracy of feature matching.

关键词： ransac algorithm Grid clustering Confidence analysis

来源：评论

学校读者我要写书评

暂无评论

Initial Performance Improvement for Fuzzy ransac algorithm Based on Weighted Estimation Model 1

Initial Performance Improvement for Fuzzy RANSAC Algorithm B...

引用

1st International Conference on Image Processing and Robotics (ICIP)

作者： Watanabe, Toshihiko Osaka Electrocommun Univ Fac Engn Neyagawa Osaka Japan

ISBN: (纸本)9781728165417

The computer vision involves many modeling problems with preventing noise caused by disturbance and sensing unit conditions. In order to improve computer vision system performance, a robust modeling technique must be developed for essential models in the system. The random sample consensus (ransac) and least median of squares (LMedS) algorithm have been widely applied in such issues. However, the performance deteriorates as the noise ratio increases and the modeling time for algorithms tends to increase in industrial applications. As an effective technique, we proposed a new fuzzy ransac method based on reinforcement learning concept for robust modeling. In this study, we proposed a new technique for the fuzzy ransac in order to improve learning performance in initial learning stage based on weighted modeling technique. Through modeling synthetic nonlinear data and camera homography experiments, the performance of the technique was evaluated. Their results found the proposed technique to be promising for improving modeling performance in initial learning stage.

关键词： modeling ransac algorithm fuzzy set reinforcement learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Traffic Bottleneck Reconstruction LIDAR Orthoimages: A ransac algorithm Feature Extraction 3rd

Traffic Bottleneck Reconstruction LIDAR Orthoimages: A RANSA...

引用

3rd International Conference of Reliable Information and Communication Technology (IRICT)

作者： Sakib, Md. Nazmus Rahman, Md. Ashiqur World Univ Bangladesh Plot 13-ARd 5 Dhaka 1205 Bangladesh

ISBN: (纸本)9783319990071;9783319990064

This study attempts a solution for autonomous vehicles to avoid immediate collision due to close proximity between cars. Since LIDAR sensors are widely used for capturing images in autonomous car industry, we depict a scope of using ransac algorithm and linear regression to reconstruct the orthoimages to escape traffic bottleneck as well as avoid collision. It is found that LIDAR sensors can't suggests much detail in close distance, and cameras don't perform well in conditions with low light or glare images. Dataset is collected from KITTI (Karlsruhe Institute of Technology) containing compressed pixels. Significance resultants focus on error reduction followed by feature extraction simulated with MATLAB. The findings excludes large scale of data size to implement and project in T-way testing for determining strength as well as capability of resultants.

关键词： Autonomous vehicle ransac algorithm LIDAR sensor Orthoimage reconstruction Linear regression analysis Traffic bottleneck

来源：评论

学校读者我要写书评

暂无评论

INITIAL PERFORMANCE IMPROVEMENT FOR FUZZY ransac algorithm BASED ON WEIGHTED ESTIMATION MODEL

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2021年第6期17卷 2033-2044页

作者： Watanabe, Toshihiko Osaka Electrocommun Univ Fac Engn 18-8 Hatsucho Neyagawa Osaka 5728530 Japan

The computer vision involves many modeling problems with preventing noise caused by disturbance and sensing unit conditions. In order to improve computer vision system performance, a robust modeling technique must be developed for essential models in the system. The random sample consensus (ransac) and least median of squares (LMedS) algorithm have been widely applied in such issues. However, the performance deteriorates as the noise ratio increases and the modeling time for algorithms tends to increase in industrial applications. As an effective technique, we proposed a new fuzzy ransac method based on reinforcement learning concept for robust modeling. In this study, we proposed a new technique for the fuzzy ransac in order to improve learning performance in initial learning stage based on weighted estimation technique. Through modeling synthetic nonlinear data and camera homography experiments, the performance of the technique was evaluated. Their results found the proposed technique to be promising for improving modeling performance in initial learning stage.

关键词： Robust estimation ransac algorithm Fuzzy system Reinforcement learning Computer vision Camera homograpy

来源：评论

学校读者我要写书评

暂无评论

RANdom sample consensus (ransac) algorithm for enhancing overlapped etched track counting

引用

IET IMAGE PROCESSING 2015年第2期9卷 97-106页

作者： Ghergherehchi, Mitra Kim, Seung Yeol Afarideh, Hossein Kim, Yoon Sang Sungkyunkwan Univ Coll Elect & Elect Engn Suwon South Korea Korea Univ Technol & Educ Sch Comp Sci & Engn Cheonan South Korea Amirkabir Univ Technol Energy Engn & Phys Dept Tehran Iran

In this study, a method to enhance the accuracy of overlapped etched track analysis is proposed. Counting tracks by eye is not an easy task and automated tracks counting systems are attractive key for this problem. This method supplements the deficiencies of the conventional track analysis method. A computer programme named KoreaTech Track Measurement System written in C++, which is the authors' previous method, has been upgraded. In the proposed track analysis method, the track images captured from solid state nuclear track detectors are geometrically analysed and the number of tracks is counted. A damaged etching track shape can be restored on the track image to improve the analysis accuracy. For track restoration, the effective points are differentiated from the damaged track image. The track image is then restored by estimating the radii (small object removal) or their axis (ellipse, circle and non-circle) using the RANdom sample consensus method. Using the restored track image, the track parameters are obtained from the ellipse and then approximated to the contour of the track image to analyse the track image. Then, the total number of tracks including the overlapped tracks is counted. To verify the proposed track analysis method, experiments using actual etching track images are conducted and the results are discussed.

关键词： random processes image enhancement image restoration solid-state nuclear track detectors nuclear engineering computing shape recognition image capture C plus plus language random sample consensus algorithm overlapped etched track counting enhancement automated track counting system KTTMS C plus captured image tracking solid state nuclear track detector SSNTD damaged etching track shape restoration track image restoration radii estimation axis estimation track analysis method 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：