检索结果-内蒙古大学图书馆

IEEE Visual Communications and image processing (VCIP)

作者： Cheng Lyu Xiao Deng Shizun Wang Ming Wu Chuang Zhang Pattern Recognition and Intelligent Systems Lab. Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665475938

Detecting objects in the aerial-view scene is challenging for the objects usually have small scales relative to the image, making it hard to achieve high accuracy in full-image detection. Slice detection tries to overcome this by cutting the full image into slices before detecting them, but objects are sparsely distributed and usually clustered in local areas, a large number of background areas without objects can be ignored to improve detection efficiency. In this paper, we present PickDet, a framework for efficient and effective object detection in the aerial-view scene, which only chooses slices containing objects to conduct detection. The key components of PickDet include a lightweight convolutional network (PickNet), a screening strategy (SoftPick), and fine-tuned detectors. Given slices of aerial-view images, PickNet first outputs the probability of object existence. Then SoftPick conducts a double-threshold screening strategy to pick the slices which contain objects. Finally, all picked slices are fed into the detector in parallel and full-image detection is used as an auxiliary mean. Compared with previous methods, PickDet achieves higher accuracy and more efficiency in the aerial-view scene. We evaluate PickDet on Visdrone and Oiltank datasets, experiments show that PickDet can result in up to 28.0% AP improvement compared to full-image detection, and can result in up to 2.9% AP increase and up to 5 times inference speedup compared to slice detection.

关键词： Fault tolerance Visual communication image processing Fault tolerant systems Detectors Object detection

来源：评论

学校读者我要写书评

暂无评论

An Effective Automatic Recognition Approach of Chinese Herbal Medicine by Micro image processing

An Effective Automatic Recognition Approach of Chinese Herba...

引用

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Guangyao Pang Zhenming Yu Honglin Pan Chengwen Xie Ping Gong Xiaoying Zhu Zizhen Peng Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology Wuzhou University Wuzhou China

The identification of traditional Chinese medicine is the key to control the quality of traditional Chinese medicine and ensure the safety and effectiveness of clinical medication. Compared with the physical and chemical identification methods with expensive equipment and complex operation, microscopic image identification of traditional Chinese medicine is an effective method with low cost. However, this method still has a high learning cost and identification errors due to staff fatigue. Therefore, this paper designs an effective automatic recognition approach of Chinese herbal medicine by micro image processing. The core of this method is the introduction of transfer learning and data enhancement methods, which effectively alleviates the problem of insufficient number of microscopic image data samples in the microscopic recognition of traditional Chinese medicine, and realizes the automatic recognition of traditional Chinese medicine. We construct a library of microscopic recognition features of Chinese herbal medicine, and designe evaluation experiments on this basis. The results show that the recognition performance of our method is better than that of SSD method, especially the F1 value is increased by 7.25 %.

关键词： Deep learning image recognition Costs Microscopy Transfer learning Ubiquitous computing Raw materials

来源：评论

学校读者我要写书评

暂无评论

HCGrid: a convolution-based gridding framework for radio astronomy in hybrid computing environments

引用

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 2021年第2期501卷 2734-2744页

作者： Wang, Hao Yu, Ce Zhang, Bo Xiao, Jian Luo, Qi Tianjin Univ Coll Intelligence & Comp 135 Yaguan RoodHaihe Educ Pk Tianjin 300350 Peoples R China Chinese Acad Sci Natl Astron Observ 20 Datun Rd Beijing 100012 Peoples R China Chinese Acad Sci Natl Astron Observ CAS Key Lab FAST 20 Datun Rd Beijing 100012 Peoples R China

Gridding operation, which is to map non-uniform data samples on to a uniformly distributed grid, is one of the key steps in radio astronomical data reduction process. One of the main bottlenecks of gridding is the poor computing performance, and a typical solution for such performance issue is the implementation of multicore CPU platforms. Although such a method could usually achieve good results, in many cases, the performance of gridding is still restricted to an extent due to the limitations of CPU, since the main workload of gridding is a combination of a large number of single instruction, multidata stream operations, which is more suitable for GPU, rather than CPU implementations. To meet the challenge of massive data gridding for the modern large single-dish radio telescopes, e.g. the Five-hundred-meter Aperture Spherical radio Telescope, inspired by existing multicore CPU gridding algorithms such as Cygrid, here we present an easy-to-install, high-performance, and open-source convolutional gridding framework, HCGrid, in CPU-GPU heterogeneous platforms. It optimizes data search by employing multithreading on CPU, and accelerates the convolution process by utilizing massive parallelization of GPU. In order to make HCGrid a more adaptive solution, we also propose the strategies of thread organization and coarsening, as well as optimal parameter settings under various GPU architectures. A thorough analysis of computing time and performance gain with several GPU parallel optimization strategies show that it can lead to excellent performance in hybrid computing environments.

关键词： methods: data analysis techniques: image processing software: public release

来源：评论

学校读者我要写书评

暂无评论

Displacement detection method of QR code reference object based on computer vision 18

Displacement detection method of QR code reference object ba...

引用

18th IEEE Int Symp on parallel and distributed Proc with Applicat (ISPA) / 10th IEEE Int Conf on Big Data and Cloud Comp (BDCloud) / IEEE Int Symp on Social Comp and Networking (SocialCom) / IEEE Int Conf on Sustainable Comp and Commun (SustainCom)

作者： Yang, Qiuhui Ji, Xiaoyu Liang, Yanyan Wuzhou Univ Guangxi Coll & Univ Key Lab Image Proc & Intellig Wuzhou Peoples R China Wuzhou Univ Sch Data Sci & Software Engn Wuzhuo Peoples R China Macau Univ Sci & Technol Fac Informat Technol Macau Peoples R China Beijing Inst Technol Zhuhai Peoples R China

ISBN: (纸本)9781665414852

In order to realize the concrete quality monitoring, the displacement detection method based on computer vision is adopted by adding the identification label to the concrete specimen The traditional camera calibration methods often need to make standard checkerboard to calculate the camera parameters. If users use different mobile phones to shoot the same scene, it is impossible to calibrate each mobile camera in advance. Therefore, aiming at the problem that the traditional camera calibration method can't meet the needs of some application scenarios, this paper proposes a method to calibrate the camera by extracting a small number of feature points in the image. Experimental data show that the method can calibrate the camera accurately, and then calculate the reference moving distance according to the basic principle of computer vision, and it has good flexibility.

关键词： Displacement detection camera calibration feature point identification label

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 Challenge on Perceptual image Quality Assessment

NTIRE 2021 Challenge on Perceptual Image Quality Assessment

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gu, Jinjin Cai, Haoming Dong, Chao Ren, Jimmy S. Qiao, Yu Gu, Shuhang Timofte, Radu Cheon, Manri Yoon, Sungjun Kang, Byungyeon Kangg Lee, Junwoo Zhang, Qing Guo, Haiyang Bin, Yi Hou, Yuqing Luo, Hengliang Guo, Jingyu Wang, Zirui Wang, Hai Yang, Wenming Bai, Qingyan Shi, Shuwei Xia, Weihao Cao, Mingdeng Wang, Jiahao Chen, Yifan Yang, Yujiu Li, Yang Zhang, Tao Feng, Longtao Liao, Yiting Li, Junlin Thong, William Pereira, Jose Costa Leonardis, Ales McDonagh, Steven Xu, Kele Yang, Lehan Cai, Hengxing Sun, Pengfei Ayyoubzadeh, Seyed Mehdi Royat, Ali Fezza, Sid Ahmed Hammou, Dounia Hamidouche, Wassim Ahn, Sewoong Yoon, Gwangjin Tsubota, Koki Akutsu, Hiroaki Aizawa, Kiyoharu Univ Sydney Sch Elect & Informat Engn Sydney NSW Australia Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China SenseTime Res Hong Kong Peoples R China OPPO Res Zurich Switzerland Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland LG Elect Seoul South Korea Meituan Grp Beijing Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China Tsinghua Univ Shenzhen Int Grad Sch Dept Elect Engn Beijing Peoples R China Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Beijing Peoples R China Tsinghua Univ Dept Automat Beijing Peoples R China Peking Univ Beijing Peoples R China Bytedance Inc Beijing Peoples R China Huawei Noahs Ark Lab Shenzhen Peoples R China Key Lab Parallel & Distributed Proc Sydney NSW Australia Univ Sydney Sydney NSW Australia 4Paradigm Inc Beijing Peoples R China Univ Zurich Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland McMaster Univ ECE Dept Hamilton ON Canada Sharif Univ Technol EE Dept Tehran Iran Natl Inst Telecommun & ICT Oran Algeria Univ Rennes INSA Rennes CNRS IETRUMR 6164 Rennes France SI Analyt Mainz Germany Univ Tokyo Tokyo Japan Hitachi Ltd Tokyo Japan

ISBN: (纸本)9781665448994

This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing technology, perceptual image processing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a new challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challenges, the training and testing datasets in this challenge include the outputs of perceptual image processing algorithms and the corresponding subjective scores. Thus they can be used to develop and evaluate IQA methods on GAN-based distortions. The challenge has 270 registered participants in total. In the final testing stage, 13 participating teams submitted their models and fact sheets. Almost all of them have achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.

关键词： image quality Training Visualization Conferences Generative adversarial networks Distortion Market research

来源：评论

学校读者我要写书评

暂无评论

Prediction of the Cyanobacteria Coverage in Time-series images based on Convolutional Neural Network 21

Prediction of the Cyanobacteria Coverage in Time-series Imag...

引用

4th International Conference on Control and Computer Vision, ICCCV 2021

作者： Ye, Xiangyu Lai, Zhiquan Li, Dongsheng National Key Laboratory of Parallel and Distributed Processing Computer College National University of Defense Technology China

ISBN: (纸本)9781450390477

In recent years, the problem of lake eutrophication has become increasingly severe. The monitoring and control of cyanobacteria in lakes are of great significance. The information obtained by existing monitoring methods is relatively lagging, and it is impossible to monitor the sudden outbreak of cyanobacteria in time. Getting cyanobacteria information directly through camera images is a breakthrough. In this paper, after analyzing the characteristics of time series cyanobacteria images, we propose a block prediction scheme based on the CNN model. Experiments show that this method can quickly calculate the coverage of cyanobacteria in the monitoring image in a short time. It can also effectively distinguish cyanobacteria-rich water areas, which significantly facilitates water quality monitoring and cyanobacteria management. We can draw a chart of the changes in the coverage of cyanobacteria by analyzing multi-day time-series images. The chart helps us conduct a short-term water quality analysis to better deal with the outbreak of cyanobacteria. © 2021 ACM.

关键词： Lakes

来源：评论

学校读者我要写书评

暂无评论

Analyzing Search Techniques for Autotuning image-based GPU Kernels: The Impact of Sample Sizes

Analyzing Search Techniques for Autotuning Image-based GPU K...

引用

IEEE International Symposium on parallel and distributed processing Workshops and Phd Forum (IPDPSW)

作者： Jacob O Tø rring Anne C. Elster Department of Computer Science Norwegian University of Science and Technology (NTNU) Trondheim Norway

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

Modern computing systems are increasingly more complex, with their multicore CPUs and GPUs accelerators changing yearly, if not more often. It thus has become very challenging to write programs that efficiently use the associated complex memory systems and take advantage of the available parallelism. Autotuning addresses this by optimizing parameterized code to the targeted hardware by searching for the optimal set of parameters. Empirical autotuning has therefore gained interest during the past decades. While new autotuning algorithms are regularly presented and published, we will show why comparing these autotuning algorithms is a deceptively difficult task. In this paper, we describe our empirical study of state-of-the-art search techniques for autotuning by comparing them on a range of sample sizes, benchmarks and architectures. We optimize 6 tunable parameters with a search-space size of over 2 million. The algorithms studied include Random Search (RS), Random Forest Regression (RF), Genetic Algorithms (GA), Bayesian Optimization with Gaussian Processes (BO GP) and Bayesian Optimization with Tree-Parzen Estimators (BO TPE). Our results on the imageCL benchmark suite suggest that the ideal autotuning algorithm heavily depends on the sample size. In our study, BO GP and BO TPE outperform the other algorithms in most scenarios with sample sizes from 25 to 100. However, GA usually outperforms the others for sample sizes 200 and beyond. We generally see the most speedup to be gained over RS in the lower range of sample sizes (25–100). However, the algorithms more consistently outperform RS for higher sample sizes (200–400). Hence, no single state-of-the-art algorithm outperforms the rest for all sample sizes. Some suggestions for future work are also included.

关键词： Radio frequency Multicore processing Memory management Benchmark testing parallel processing Bayes methods Task analysis

来源：评论

学校读者我要写书评

暂无评论

Trustworthy distributed Deep Neural Network Training in an Edge Device Network

Trustworthy Distributed Deep Neural Network Training in an E...

引用

IEEE International Conference on Big Data

作者： Sudipta Saha Shubha Haiying Shen Department of Computer Science University of Virginia USA

ISBN: (纸本)9781665480468

With the increased usage of edge devices having local computation capabilities, deep neural network (DNN) training in a network of edge devices becomes promising. Several recent works have proposed fully edge-based distributed training systems for situations when the communication to cloud is unstable or intermittent. However, such distributed systems become vulnerable when there are untrusted devices that launch data and model poisoning attacks during training, deteriorating the accuracy of the DNN model. To handle this challenge, we propose a Trustworthy distributed system for Machine learning training in an edge device network (TrustMe). TrustMe realizes both data and model parallelisms. It detects the untrusted devices producing illegitimate outputs. Next, it reassigns the training tasks of the untrusted devices to other trusted devices in such a way that the reassignment and the training that is restarted after the reassignment require minimal time. Our container-based emulation and real device experiments demonstrate that TrustMe achieves up to 12% higher accuracy and 45% less training time compared to existing methods in the presence of untrusted devices.

关键词： Training Deep learning image edge detection Neural networks Emulation distributed databases parallel processing

来源：评论

学校读者我要写书评

暂无评论

Task Distribution Method for Index Classification based on Color Segmentation in Remote Sensing 4

Task Distribution Method for Index Classification based on C...

引用

4th International Conference on Advanced Information Technologies, ICAIT 2020

作者： Htun, Yan Naing Aye, Bawin Aung, Aung Higher Education Center Department of Computer Technology Pyin Oo Lwin Myanmar

ISBN: (纸本)9781728183640

Digital processing of remotely sensed image data has been great importance in recent times. This research work discusses task distribution method in parallel image processing and load balancing under the circumstance of multi-Tasks and multi-processors in remote sensing. Task distribution method can speed up computation and improve efficiency and perform larger computations which are not possible on single processor system. The tasks are distributed based on the segmentation of color and the Support Vector Machine (SVM) is used to classify the indices of the input image and intends to design and improve the color segmentation based task distribution method for index classification using machine learning. In the system, the RGB satellite image is used as an input image and the output is the four indices of forest, building, road and land The results of the system are more accurate and less time consumption than non-distributed computing methods. It is implemented in MATLAB platform with parallel computation toolbox because the system can solve computationally and data-intensive tasks using multicore processors and clusters of computer. © 2020 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Communication-efficient decentralised algorithms for seismic tomography with sensor networks

引用

INTERNATIONAL JOURNAL OF parallel EMERGENT AND distributed SYSTEMS 2020年第5期35卷 550-570页

作者： Zhao, Liang Univ South Carolina Upstate Div Math & Comp Sci Spartanburg SC 29303 USA

We consider the decentralised consensus optimisation problem arising from in-situ seismic tomography in large-scale sensor networks. Unlike traditional seismic imaging performed in a centralised location, each node in this setting privately holds an objective function and partial data. The goal of each node is to obtain the optimal solution of the whole seismic image, while communicating only with its immediate neighbours. We present a fast decentralised gradient descent method and prove that this novel method can reach optimal convergence rate ofO(1/k(2))wherekis the number of communication/iteration rounds. A gossip-based asynchronous version is also proposed which is preferable when there is a divergence on the processing speed of the nodes. Extensive numerical experiments on synthetic and real-world sensor network seismic data demonstrate that the proposed algorithms significantly outperform existing methods. [GRAPHICS] .

关键词： Big data decentralised computing in-network processing seismic tomography sensor network

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：