检索结果-内蒙古大学图书馆

International Conference on pattern recognition

作者： Keechul Jung Kwang In Kim T. Kurata M. Kourogi JungHyun Han Pattern Recognition and Image Processing Laboratory Michigan State University USA Artificial Intelligence Laboratory KAIST South Korea National Institute for Advanced Industrial Science and Technology Japan School of Electrical and Computer Engineering Sung Kyun Kwan University South Korea

ISBN: (纸本)076951695X

We propose a text scanner which detects wide text strings in a sequence of scene images. For scene text detection, we use a multiple-CAMShift algorithm on a text probability image produced by a multi-layer perceptron. To provide enhanced resolution of the extracted text images, we perform the text detection process after generating a mosaic image in a fast and robust image registration method.

关键词： image sequences Layout image registration Cameras Parameter estimation Videos Pixel image processing Robustness Optical character recognition software

来源：评论

学校读者我要写书评

暂无评论

Automatic Docking Design of Flange Pipe Based on Spatial Information

Automatic Docking Design of Flange Pipe Based on Spatial Inf...

引用

International Conference on Information Science and Control Engineering (ICISCE)

作者： Xingxun Li Xiuhua Zhang Jinmeng Wu Jian Huang Pianpian Chen Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan China Hubei Engineering Research Center of Video Image and HD Projection Wuhan Institute of Technology Wuhan China

With the development of ship industry, pipeline system has been more and more widely used. However, the pipeline site space is narrow. Mechanical and electrical equipments are of all kinds. The pipeline cable is densely distributed. All problems mentioned above seriously affects the pipeline construction. In order to solve the problem of pipeline docking, the method of making model and comprehensive lofting is usually adopted. However, this method is technically backward. The operation is inconvenient due to the narrow onsite space. The required period is long. With low information utilization and accuracy, the method of making model and comprehensive lofting has a great influence on the development cycle and design quality. In order to solve these problems, this paper presents a design method and system of flange pipe docking. A binocular camera is used to obtain the image of the pipe joint. The center position of the flange surface and array holes on the flange surface are extracted from the image, which is bias of subsequent work. First, the path of the intermediate connecting pipe is calculated. Then, according to the pipe standards of intermediate connection pipe and production specification of enterprise, the model of intermediate connecting pipe is automatically generated by using secondary development technology of CAD. In this paper, the binocular vision technology is combined with pipeline docking design, which significantly improves the utilization rate of field space information and design efficiency, and solves the problems of inconvenient operation and safety risk of traditional profiling method.

关键词： Industries Solid modeling Design methodology Pipelines Production Flanges Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Rephrasing the Reference for Non-Autoregressive Machine Translation

arXiv

引用

arXiv 2022年

作者： Shao, Chenze Zhang, Jinchao Zhou, Jie Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Pattern Recognition Center WeChat AI Tencent Inc China

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when the NAT output is closer to other translations. In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. As we train NAT based on the rephraser output rather than the reference sentence, the rephraser output should fit well with the NAT output and not deviate too far from the reference, which can be quantified as reward functions and optimized by reinforcement learning. Experiments on major WMT benchmarks and NAT baselines show that our approach consistently improves the translation quality of NAT. Specifically, our best variant achieves comparable performance to the autoregressive Transformer, while being 14.7 times more efficient in inference. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

The method of image restoration in the environments of dust

The method of image restoration in the environments of dust

引用

IEEE International Conference on Mechatronics and Automation

作者： Yuanyu Wang Yuanzong Li Tianxu Zhang Department of Computer Fundamental Education TaiYuan University of Technology TaiYuan China College of Mechanical Engineering TaiYuan University of Technology TaiYuan China Institute for Pattern Recognition and A.I State Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology WuHan China

In order to solve the problem of image degradation caused by dust environments, an image degradation model considering multiple scattering factors caused by dust was first established using the first-order multiple scattering method. Then, a dark channel prior principle was applied to present an image restoration algorithm based on the image degradation model. Finally, a particle swarm optimization algorithm was applied to optimize the atmospheric light and the exposure parameters. This optimization algorithm was established according to the criterion of the image evaluation based on kirsch operator with dual threshold. By using the method an optimistic result of image restoration was obtained. The experimental results have shown that the method not only enhanced luminance and contrast, but also discovered more detail edges information. The method provided a foundation for target recognition in the dust environments.

关键词： image edge detection image restoration Degradation Atmospheric modeling Optical scattering Optical imaging

来源：评论

学校读者我要写书评

暂无评论

NLFA: A Non Local Fusion Alignment Module for Multi-Scale Feature in Object Detection 3rd

NLFA: A Non Local Fusion Alignment Module for Multi-Scale Fe...

引用

3rd International Symposium on Automation, Mechanical and Design Engineering, SAMDE 2022

作者： Xue, Honghui Ma, Jinshan Cai, Zheyi Fu, Junfang Guo, Feng Weng, Wei Dong, Yunxin Zhang, Zhenchang College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou China Fujian Zhongke Zhongxin Intelligent Technology Co. Ltd Fuzhou China Fujian Newland Auto-ID Tech. Co. Ltd Fuzhou China Department of Computer and Information Engineering Xiamen University of Technology Xiamen China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen China

ISBN: (纸本)9783031400698

Recently, in order to pursue better detection results, more convolutional layers and deeper networks are a direction pursued by everyone. However, more and more down-sampling convolution or up-sampling operations generate feature maps of different scales, which makes it difficult to avoid the loss of detailed information of the image, and the distribution of different scales features will be misaligned. In particular, the loss and dislocation of the target boundary information will affect the features learned by the model and reduce the accuracy. This paper proposes a feature alignment method based on non-local idea, and designed two modules—Non Local Align Module (NLA) and Channel Fusion Augment Module (CFA). At the same time, the neighborhood calculation algorithm is also designed for it, which strengthens the binding force on the calculation of boundary information. These two modules can be easily embedded into the current mainstream object detection network to improve the detection effect of the model. Compared to the previous model, the network using our NLA module and CFA module achieves better results than the original model. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ship detection in polarimetric SAR based on support vector machine

引用

Research Journal of Applied Sciences, Engineering and Technology 2012年第16期4卷 2844-2850页

作者： Su, Xuwu Yang, Guangyou Sang, Hongshi State Key Laboratory for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China School of Mechanical Engineering Hubei University of Science and Technology Wuhan 430068 China

A Support Vector Machine (SVM) based method for ship detection in Polarimetric SAR (POLSAR) is proposed in this study. Because of similarities of ship and man-made structures on land in scattering mechanisms, land and sea are first segmented by SVM according to polarimetric features and texture features;The SVM-based Recursive Feature Elimination (RFE-SVM) approach is adopted to improve the performance of the segmentation algorithm. Then ship targets are extracted from sea by SVM classifier;Threshold-based rules and SVM-based rules are established for discriminating ship from non-ship target at last. The experiments are carried out on POLSAR data from Radarsat-2. For the available SAR images, the average accuracy of ship detection is over 95%. © Maxwell Scientific Organization, 2012.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

New intra prediction mode for interlaced video in AVS

引用

Gaojishu Tongxin/Chinese High Technology Letters 2007年第3期17卷 221-225页

作者： Chen, Liang Tan, Yihua Tian, Jinwen State Key Laboratory of Education Ministry for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

The technologies of intra prediction and MBAFF were introduced, and a new intra prediction mode based on the characteristics of spatial distribution in interlaced video was proposed. The spatial correlation of five luma intra prediction modes in AVS-P2 and the new mode were analyzed. From the analysis result, it can be concluded that the new mode can exploit the spatial correlation better and predict the samples more precisely than the existed ones. The experimental results showed that the average gain in peak signal to noise ratio was above 0.12dB and the average reduction in bit-rate was above 1.77%, so the proposed mode is an effective prediction mode for improvement of coding performance.

关键词： AVS Interlaced video Intra prediction Video coding

来源：评论

学校读者我要写书评

暂无评论

Study on the Method of image Restoration in the Environment of Dust

Study on the Method of Image Restoration in the Environment ...

引用

International Conference on Wireless Communications, Networking and Mobile Computing (WiCom)

作者： Yuanyu Wang Yuanzong Li Tianxu Zhang Department of Computer Fundamental Education Taiyuan University Of Technology Taiyuan China College of Mechanical Engineering Taiyuan University Of Technology Taiyuan China Institute of Pattern Recognition and A.I State Key Laboratory of Image Processing and Intelligent Control HuaZhong University of Science and Technology Wuhan China

In order to solve the problem of image degradation caused by dust environments, an image degradation model considering multiple scattering factors caused by dust was first established using the first-order multiple scattering method. Then, a dark channel prior principle was applied to present an image restoration algorithm based on the image degradation model. Finally, GA optimization algorithm was applied to optimize the atmospheric light and the exposure parameters. This optimization algorithm was established according to the criterion of the image evaluation based on kirsch operator with automatic threshold. By using the method an optimistic result of image restoration was obtained. The experimental results have shown that the method not only enhanced luminance and contrast, but also discovered more detail edges information. The method provided a foundation for target recognition in the dust environments.

关键词： image edge detection image restoration Scattering Degradation Gallium Atmospheric modeling Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Online Lidar-Camera Extrinsic Parameters Self-Checking

SSRN

引用

SSRN 2023年

作者： Wei, Pengjin Yan, Guohang You, Xin Fang, Kun Ma, Tao Yang, Jie Liu, Wei Department of Automation Shanghai Jiao Tong University 800 Dongchuan RD Minhang District China Autonomous Driving Group Shanghai AI Laboratory 129 Longwen RD Xuhui District China Institute of Image Processing and Pattern Recognition China

With the development of neural networks and the increasing popularity of automatic driving, the calibration of the LiDAR and the camera has attracted more and more attention. This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks. In real-world applications, as smart cars roll off the production line, their LiDAR and camera systems are meticulously calibrated, while in the rest of the car life period, the poses of the LiDARs and cameras no longer get continually supervised to ensure the security. To this end, this paper proposes a self-checking algorithm to judge whether the extrinsic parameters are well-calibrated during the car life period by introducing a binary classification network based on the fused information from the camera and the LiDAR. Moreover, since there is no such dataset for the task in this work, we further generate a new dataset branch from the KITTI dataset tailored for the task. Our experiments on the proposed dataset branch demonstrate the performance of our method. To the best of our knowledge, this is the first work to address the significance of continually checking the calibrated extrinsic parameters for autonomous driving. The dataset and code are available at https://***/OpenCalib/LiDAR2camera_self-check © 2023, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Fast Ground Target Detection Method in Infrared image Sequences

Fast Ground Target Detection Method in Infrared Image Sequen...

引用

International Conference on Audio, Language and image processing

作者： Hu Zhu Lizhen Deng Gaihua Wang Gang Zhou Xiaodong Bai National Key Laboratory of Science and Technology on Multi-spectral Information Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology College of Electrical & Electronic Engineering Huazhong University of Science and Technology

ISBN: (纸本)9781467301732

Automatic target detection (ATD) in infrared (IR) imagery is a fundamental and challenging task in computer vision. A fast automatic target detection method in IR image sequence is proposed in this paper. Since the position and scale of target change real-timely, we can predict the target position in real-time image by using the history position of target and flight parameters information of previous and current frames, and then estimate the scale of target depending on flight parameters and imaging parameters for getting the model with the appropriate scale. In order to make the template matching more robust for target rotation, the template matching method based on parametric template vector is used to recognize the position of target. The detection result is identified by using multi-frame integration based on recognition information of history and currant frames. Some experimental results using real-world images with complicated background validate the effectiveness and robustness of the proposed method under rotation and scale variance condition.

关键词： Infrared imaging images Targets flight parameter computer vision real image fast ground infrared imagery automatic target currant Object detection TEMPLATE MATCHING Scale formation

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：