检索结果-内蒙古大学图书馆

International conference on Unmanned systems and Artificial Intelligence

作者： Xiaoping Huang Xinru Li Zelin Hu Institute of Intelligent Machine Chinese Academy of Sciences University of Science and Technology of China Hefei China Institute of Intelligent Machine Chinese Academy of Sciences Hefei China

ISBN: (数字)9781728158594

ISBN: (纸本)9781728158600

Body condition score (BCS) is an important parameter to measure cow energy reserve for feeding management. Currently, measuring BCS mainly relies on veterinary experts or skilled scorers by observing and touching animals, which is time consuming and costly, especially on large-scale farms. In this study, a method of image processing and deep learning is employed to estimate cow BCS. Firstly, the network cameras were used to capture the back view images of the cows, resulting in 5470 images that constituted the sample data set, in which the key body parts (tail, pins and rump) of the cow were labeled manually. Secondly, Faster Region-Convolutional Neural Networks (Faster R-CNN) method was used to position and classify the cow tail images which were correlated to the value of BCS. Compared with other deep learning algorithms like the Single Shot multibox Detector (SSD), Faster R-CNN had a slightly higher accuracy. Specifically, the detection accuracy for cow tails was 84%, and the BCS classification had an average accuracy 70%. The low BCS classification rate was mainly due to the insufficient image data in this study for cows with certain ranges of BCS.

关键词： body condition score tail detection Faster R-CNN deep learning image processing dairy cows BCS1L gene cows image processing Machine Learning dairy cattle Body Composition Tail Data sampling

来源：评论

学校读者我要写书评

暂无评论

Remote-Monitoring Smoke Detection System

Remote-Monitoring Smoke Detection System

引用

IEEE Eurasia conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)

作者： Tian-Syung Lan Kai-Chi Chuang I-Hsiung Chang Lie-Ping Zhang Department of Information Management Yu Da University Miaoli County Taiwan Republic of China College of Mechanical and Control Engineering Guilin University of Technology Guilin Guangxi China Department of Early Childhood Education To Ko University Chiayi County Taiwan Republic of China

This study designed a smoke detection system that employs an omnidirectional camera to remotely monitor fire disaster sites. images are transmitted through Wi-Fi to the control center, which then provides accurate real-time information to firefighters. This reduces the time required for fire suppression and provides additional time for personnel evacuation.

关键词： Fires Cameras Real-time systems Optical flow Classification algorithms Clustering algorithms image processing

来源：评论

学校读者我要写书评

暂无评论

Reaction-diffusion algorithm designed for image edge detection and its performance evaluation 12

Reaction-diffusion algorithm designed for image edge detecti...

引用

12th International conference on Interfaces and Human Computer Interaction 2018, 11th International conference on Game and Entertainment Technologies 2018 and 12th International conference on Computer Graphics, visualization, Computer vision and image processing 2018, part of the Multi conference on Computer Science and Information systems 2018, MCCSIS 2018

作者： Nomura, Atsushi Okada, Koichi Mizukami, Yoshiki Faculty of Education Yamaguchi University Yoshida 1677-1 Yamaguchi753-8513 Japan Center for the Promotion of Higher Education Yamaguchi University Yoshida 1677-1 Yamaguchi753-8511 Japan Graduate School of Science and Technology for Innovation Yamaguchi University Tokiwadai 2-16-1 Ube755-8611 Japan

ISBN: (纸本)9789898533791

The present paper proposes image edge detection algorithm utilizing a reaction-diffusion network. The network consists of two-dimensionally coupled FitzHugh-Nagumo type neurons, whose behavior is described by a set of time-evolving partial differential equations. The neurons’ non-linearity and their interconnection give the image edges through an iterative computation. The proposed algorithm differs from its previously-proposed one (Nomura et al., 2016) on the pre-processing for initializing the neurons’ state and the post-processing for thinning edges. The performance of the proposed algorithm is discussed with three image data-sets and two error measures, in comparison with performance of two other algorithms including Canny’s edge detection method. © 2018.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Self-Optimizing image processing Algorithm for Safety Critical systems

Self-Optimizing Image Processing Algorithm for Safety Critic...

引用

IEEE SoutheastCon conference

作者： Cronin, Stephen Butka, Brian Embry Riddle Aeronaut Univ ECSEE Dept Daytona Beach FL 32114 USA

ISBN: (纸本)9781538661338

image processing has made many strides in the past few years in terms of accuracy and robustness. However, these advances have often times come at the cost of being understandable by humans and as a result difficult to validate the outputs. In this work we propose a genetic algorithm designed to optimize image processing while maintaining a human understandable output. The algorithm bases itself on fundamental functions of image processing and works with them to optimize the detection of objects in the frame while minimizing spurious noise. Optimization of results comes in two primary ways, through the varying the arrangement of function calls as well as through tuning the parameters used in the calls themselves. Results and conclusions drawn through the implementation of the algorithm will be discussed along with a comparison of other current state of the art algorithms.

关键词： Genetic Algorithm image processing Safety Critical Computer vision

来源：评论

学校读者我要写书评

暂无评论

Digital image processing systems based on functional-oriented processors with a homogeneous structure

引用

Journal of Physics: conference Series 2020年第1期1680卷

作者： N A Lookin Institute of Engineering Science Ural Branch of RAS 34 Komsomol street Yekaterinburg 620049

Real-time digital image processing as part of mobile systems requires solving the problems of development high-performance specialized processors for intraframe image processing. The graphs of intraframe processing algorithms are analysed and their parameters are evaluated, primarily the degree of parallelism. The architectures of functional-oriented processors based on homogeneous computing environments for ultrafast intraframe processing are described. The results of research and development of microelectronic implementation of such processors are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OpenCL Superpixel Implementation on a General Purpose Multi-core CPU

OpenCL Superpixel Implementation on a General Purpose Multi-...

引用

IEEE International conference on Imaging systems and Techniques (IST)

作者： Haseljic, Hana Cogo, Emir Prazina, Irfan Turcinhodzic, Razija Buza, Emir Akagic, Amila Univ Sarajevo Dept Comp Sci & Informat Fac Elect Engn Sarajevo Bosnia & Herceg

ISBN: (纸本)9781538666289

Multi-, many-core, hybrid processors and parallel programming languages are slowly becoming pervasive in mainstream computing. It is expected that they will affect a large spectrum of systems, from embedded and general-purpose, to high-end computing systems. This architectural change has already challenged programmers to efficiently write an application code that can scale over many cores to utilize its computational power. Moreover, many heterogeneous architectures exist today, hence there was an emergent need for a uniform interface to these architectures. Recently, Khronos Group defined the Open Computing Language (OpenCL) for abstracting the underlying hardware, which enables software developers to write a portable code across different shared-memory architectures. In this paper, we introduce a new parallel implementation of one of the fastest image segmentation algorithms known as Simple Linear Iterative Clustering based on OpenCL. We evaluate the effectiveness of this implementation using only multi-core GPCPU. Our implementation is fully compatible with sequential implementation. When the algorithm is executed sequentially it utilizes only 25% of total computational power of a GPCPU for any image resolution, while its modified algorithm is able to utilize close to 100% for high resolution images. The resulting algorithm is up to 5x faster than its sequential counterpart.

关键词： parallel programming multi-core gpcpu opencl superpixel image segmentation image processing

来源：评论

学校读者我要写书评

暂无评论

Fast Bag-Of-Words Candidate Selection in Content-Based Instance Retrieval systems

Fast Bag-Of-Words Candidate Selection in Content-Based Insta...

引用

IEEE International conference on Big Data (Big Data)

作者： Siedlaczek, Michal Wang, Qi Chen, Yen-Yu Suel, Torsten NYU Tandon Sch Engn Brooklyn NY USA Blippar Inc Mountain View CA USA

ISBN: (纸本)9781538650356

Many content-based image search and instance retrieval systems implement bag-of-visual-words strategies for candidate selection. visual processing of an image results in hundreds of visual words that make up a document, and these words are used to build an inverted index. Query processing then consists of an initial candidate selection phase that queries the inverted index, followed by more complex reranking of the candidates using various image features. The initial phase typically uses disjunctive top-k query processing algorithms originally proposed for searching text collections. Our objective in this paper is to optimize the performance of disjunctive top-k computation for candidate selection in content-based instance retrieval systems. While there has been extensive previous work on optimizing this phase for textual search engines, we are unaware of any published work that studies this problem for instance retrieval, where both index and query data are quite different from the distributions commonly found and exploited in the textual case. Using data from a commercial large-scale instance retrieval system, we address this challenge in three steps. First, we analyze the quantitative properties of index structures and queries in the system, and discuss how they differ from the case of text retrieval. Second, we describe an optimized term-at-a-time retrieval strategy that significantly outperforms baseline term-at-a-time and document-at-a-time strategies, achieving up to 66% speed-up over the most efficient baseline. Finally, we show that due to the different properties of the data, several common safe and unsafe early termination techniques from the literature fail to provide any significant performance benefits.

关键词： inverted index bag-of-visual-words image retrieval candidate selection top-k search cascade ranking

来源：评论

学校读者我要写书评

暂无评论

Realtime 3D Object Detection for Automated Driving Using Stereo vision and Semantic Information

Realtime 3D Object Detection for Automated Driving Using Ste...

引用

International conference on Intelligent Transportation

作者： Hendrik Königshof Niels Ole Salscheider Christoph Stiller FZI Research Center for Information Technology Intelligent Systems and Production Engineering Karlsruhe Germany Institute of Measurement and Control Systems Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

ISBN: (纸本)9781538670255

We propose a 3D object detection and pose estimation method for automated driving using stereo images. In contrast to existing stereo-based approaches, we focus not only on cars, but on all types of road users and can ensure real-time capability through GPU implementation of the entire processing chain. These are essential conditions to exploit an algorithm for highly automated driving. Semantic information is provided by a deep convolutional neural network and used together with disparity and geometric constraints to recover accurate 3D bounding boxes. Experiments on the challenging KITTI 3D object detection benchmark show results that are within the range of the best image-based algorithms, while the runtime is only about a fifth. This makes our algorithm the first real-time image-based approach on KITTI.

关键词： Three-dimensional displays Object detection Semantics Laser radar Proposals Two dimensional displays Estimation

来源：评论

学校读者我要写书评

暂无评论

Learning to Rank: A Progressive Neural Network Learning Approach 44

Learning to Rank: A Progressive Neural Network Learning Appr...

引用

44th IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2019

作者： Tran, Dat Thanh Iosifidis, Alexandros Laboratory of Signal Processing Tampere University of Technology Finland Department of Engineering ECE Aarhus University Denmark

ISBN: (纸本)9781479981311

Learning to rank is an essential component in an information retrieval system. The state-of-the-art ranking systems are often based on an ensemble of classifiers, such as Random Forest or LambdaMART, which aggregates the ranking outputs produced by thousands of classifiers. The storage and computation requirement of an ensemble model is usually very high, imposing a significant operating cost to the retrieval system. To tackle this problem, we propose an algorithm that adaptively learns a single heterogeneous feedfor-ward network architecture, composing of Generalized Operational Perceptrons, given a ranking problem. Experimental results in web search ranking and image retrieval tasks show that the proposed algorithm compares favourably to the related algorithms. © 2019 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of Information Bottleneck LDPC Decoders for Software Defined Radios 12

Design and Evaluation of Information Bottleneck LDPC Decoder...

引用

12th International conference on Signal processing and Communication systems (ICSPCS)

作者： Lewandowsky, Jan Bauch, Gerhard Tschauner, Matthias Oppermann, Peter Hamburg Univ Technol Inst Commun D-21073 Hamburg Germany Fraunhofer Inst Commun Informat Proc & Ergon FKIE D-53343 Wachtberg Germany Fraunhofer Inst Med Image Comp MEVIS D-28359 Bremen Germany

ISBN: (纸本)9781538656020

The Information Bottleneck method allows to construct information-optimum message passing decoders for low-density parity-check codes. In such decoders lookup tables replace the classical node operations of the variable and the check nodes. These lookup tables are designed using the Information Bottleneck principle of maximizing the relevant information. Unlike state-of-the-art decoders which use real valued log-likelihood ratios for decoding, the considered decoders do not process any real values, but only quantization indices. Nevertheless, they have performance extremely close to belief propagation decoding. Since hardware representation of unsigned integers is efficient and lookup table implementations have low complexity, it is reasonable to assume that the designed decoders offer advantages over their conventional counterparts in practice. In this paper, we evaluate, quantify and discuss these advantages in a practical experiment. Our focus lies on a software defined radio application, where the channel decoder is implemented on a digital signal processor. We present several implementations of the considered decoders and compare them with state-of-the-art decoders. Our results show considerable gains of the Information Bottleneck decoders in terms of bit error rate performance and net decoding throughput.

关键词： Decoding Table lookup Iterative decoding Belief propagation Approximation algorithms Signal processing algorithms

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：