检索结果-内蒙古大学图书馆

4th International Conference on Cognitive systems and Information processing (ICCSIP)

作者： Yu, Jiachen Jin, Li Chen, Jiayi Tian, Zhiqiang Lan, Xuguang Xi An Jiao Tong Univ Sch Software Engn Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China

ISBN: (纸本)9789811379864;9789811379857

Existing Neural Style Transfer (NST) algorithms do not migrate styles well to a reasonable location where the output image can render the correct spatial structure of the object being painted. We propose a deep semantic matching-based multi-scale (DSM-MS) neural style transfer method, which can achieve the reasonable transfer of styles guided by the prior spatial segmentation and illumination information of input images. First, according to real drawing process, before an artist decides how to paint a stroke, he/she needs to observe and then understand subjects, segmenting space into different regions, objects and structures and analyzing the illumination conditions on each object. To simulate the two visual cognition processes, we define a deep semantic space (DSS) and propose a method for calculating DSSs using manual image segmentation, automatic illumination estimation and convolutional neural network (CNN). Second, we define a loss function, named deep semantic loss, which uses DSS to guide reasonable style transfer. Third, we propose a multi-scale optimization strategy for improving the efficiency of our method. Finally, we achieve an interdisciplinary application of our method for the first time-painterly rendering 3D scenes by neural style transfer. The experimental results show that our method can synthesize images in better original structures, with more reasonable placement of each styles and visual aesthetic feeling.

关键词： Neural style transfer image segmentation Illumination estimation Patch matching

来源：评论

学校读者我要写书评

暂无评论

Sparse spectral signal reconstruction for one proposed nine-band multispectral imaging system

引用

MECHANICAL systems AND SIGNAL processing 2020年 141卷 106627-000页

作者： Sun, Bangyong Zhao, Zhe xie, Dehong Yuan, Nianzeng Yu, Zhe Chen, Fuwei Cao, Congjun de Dravo, Vincent Whannou Xian Univ Technol Sch Printing Packaging & Digital Media Xian Peoples R China Nanjing Forestry Univ Coll Informat Sci & Technol Nanjing Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Key Lab Spectral Imaging Technol CAS Xian Peoples R China

Multispectral filter array (MSFA) imaging with one single sensor is a portable and inexpensive means of acquiring spectral image which is widely used for object detection, material analysis and mechanical system diagnosis. The most challenging task for MSFA imaging is the multispectral demosaicking with the aim of reconstructing the captured raw/mosaic image, especially for the systems with many bands which result in higher sparseness of the raw data. In this paper, we present a 9-band MSFA imaging system in a repetitive 4 x 4 filter array on a single sensor, and propose a demosaicking algorithm for reconstructing the raw spectral image. Within the 4 x 4 MSFA pattern, the fifth spectral band takes up half of the total spatial position while the remaining eight bands occupy 1/16 respectively. To reconstruct the sparse raw data, we first recover the fifth band by propagating the neighboring sampled pixels to the unsampled position using the image gradients, and then employ the reconstructed fifth band as a guided image to demosaick the other bands with the guided filter and residual interpolation. Finally, we estimate the spectral reflectance values from the multispectral image and the characterization matrix. In the experiment, we evaluate the performance of the 9-band imaging system with the binary tree-based edge-sensing (BTES) algorithm, compressed sensing (CS) algorithm, and our proposed demosaicking algorithm. The experiment results demonstrate that our demosaicking algorithm not only outperforms BTES and CS algorithms in terms of objective image quality, e.g., PSNR values and spectral errors, but also reduces the demosaicking artifacts in terms of subjective evaluations. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Multispectral imaging system image demosaicking Guide filter Filter array

来源：评论

学校读者我要写书评

暂无评论

结合LSTM的强化学习动态环境路径规划算法

引用

小型微型计算机系统 2021年第2期42卷 334-339页

作者：武曲张义郭坤王玺青岛理工大学信息与控制工程学院山东青岛266520

在路径规划领域已经涌现出了诸多的优秀的经典算法,但这些传统方法往往基于静态环境,对于动态可变环境缺乏处理能力.本文提出一种结合LSTM强化学习动态环境路径规划算法.首先,本文以环境图像作为输入,最大限度了保证了原始的信息来源.... 详细信息

在路径规划领域已经涌现出了诸多的优秀的经典算法,但这些传统方法往往基于静态环境,对于动态可变环境缺乏处理能力.本文提出一种结合LSTM强化学习动态环境路径规划算法.首先,本文以环境图像作为输入,最大限度了保证了原始的信息来源.而后构建了自动编码器用来对环境图像进行特征降维,降低了整体模型的复杂程度.最后采用深度强化学习算法DDPG进行路径规划,其中Actor部分采用LSTM的网络构建,使Actor在决策时可以参考前序信息,做到有预测的避开动态障碍.最后通过实验证明了本文算法的可行性和高效性.

关键词：自动编码器 LSTM DDPG 强化学习动态路径规划

来源：评论

学校读者我要写书评

暂无评论

Time Window Selection Algorithm for ISAR Ship Imaging Based on Instantaneous Doppler Frequency Estimations of Multiple Scatterers

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2019年第10期12卷 3799-3812页

作者： Zhou, Peng Zhang, xi Dai, Yongshou Sun, Weifeng Wan, Yong China Univ Petr Coll Ocean & Space Informat Qingdao 266580 Shandong Peoples R China Minist Nat Resources Peoples Republ China Inst Oceanog 1 Qingdao 266061 Shandong Peoples R China

Selecting a suitable time window is an important aspect of the ship imaging process for inverse synthetic aperture radar (ISAR) systems. One type of existing algorithm involves finding the time period during which a ship's rotation is relatively stable by extracting the instantaneous Doppler frequency variation caused by the ship's rotation. However, existing algorithms extract either the instantaneous Doppler frequency of only a single scatterer or the average Doppler frequency of the entire ship. A novel time window selection algorithm for ISAR ship imaging is proposed through extraction of the instantaneous Doppler frequencies of multiple scatterers. The instantaneous Doppler frequency of a scatterer caused by a ship's rotation is verified to behave approximately as a linear frequencymodulation signal over a short period. The formula for calculating the length of such a short period is derived. A parameter estimation method based on compressed sensing after data extrapolation is presented to extract the centroid and frequency modulation rate for short-time chirp signals. The instantaneous Doppler frequency variations in the multiple scatterers over the entire acquisition period are obtained by associating the data from adjacent short time periods. The suitable time window during which the instantaneous Doppler frequency changes are all relatively stable in the multiple scatterers is then selected. The results of the performed simulation and real data processing verify the effectiveness of the proposed algorithm. The proposed algorithm achieves better image quality than the imagecontrast-based algorithm and algorithms based on instantaneous Doppler frequency estimation of a single scatterer.

关键词： Instantaneous Doppler frequency estimation inverse synthetic aperture radar (ISAR) imaging ship imaging time window selection

来源：评论

学校读者我要写书评

暂无评论

Automatic Analog Pointer Instruments Reading Using Panel Detection and Landmark Localization Networks 4th

Automatic Analog Pointer Instruments Reading Using Panel Det...

引用

4th International Conference on Cognitive systems and Information processing, ICCSIP 2018

作者： Yang, Keshan Duan, Zhansheng Fang, Kai Center for Information Engineering Science Research Xi’an Jiaotong University Xi’anShanxi710049 China

ISBN: (纸本)9789811379826

Analog pointer instruments are widely used in industrial automation. However, reading their values by human is time and labour consuming. Most current pointer reading algorithms lack universality and can not handle complex and varying application scenarios. Therefore, this paper proposes a general pointer instrument reading scheme based on CNN. Our main contributions are two folds. First, we combine two sub-networks into one backbone, which has shortened the inference time. Second, we propose a light-weighted sampling decoder, which makes our scheme achieve a higher accuracy. Comparing to other algorithms, our scheme can deal with the case in which the instrument is too difficult to read, e.g., there is more than one similar pointer in one panel. Also, our scheme only needs less than 100Â ms on a typical laptop for a 512 × 512 image. It is fast enough and can satisfy most requirements in industrial automation. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Landmark localization Panel detection Pointer instrument reading

来源：评论

学校读者我要写书评

暂无评论

Building 3D Map Based on Monte Carlo Localization and Feature Extraction

Building 3D Map Based on Monte Carlo Localization and Featur...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent systems

作者： Zhun Fan Ying Chen Chong Li Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shantou Guangdong China School of Electrical and Information Engineering Shantou University Shantou Guangdong China

ISBN: (数字)9781728190105

ISBN: (纸本)9781728190112

In this project, we mainly explore and construct the 3D indoor map. The goal of this paper is to merge the data from the laser and kinect sensor with Monte Carlo Location(MCL) in 2D map. We use the laser range sensor to construct the 2D map and get the robot's pose transformation matrix. Then, we obtain the color and depth image by using the kinect sensor and build 3D point cloud map by using the feature extraction method, getting the kinect's pose transformation matrix. After that, we get the optimal pose transformation by using the Kalman Filter to calibrate the robot's pose transformation matrix and the kinect's pose transformation matrix. Finally, the optimal pose transformation matrix is employed to accomplish the local 3D map and construct the global 3D indoor map. To show the superiority of our method, we make some experiments and compare with some other algorithms. Experimental results show that our method has a better superiority.

关键词： Three-dimensional displays Robots Robot sensing systems Two dimensional displays Kalman filters Feature extraction Buildings

来源：评论

学校读者我要写书评

暂无评论

路面破损图像自动处理技术研究进展

引用

交通运输工程学报 2019年第1期19卷 172-190页

作者：徐志刚车艳丽李金龙赵祥模潘勇王忠仁韦娜宋宏勋长安大学信息工程学院陕西西安710064 石家庄华燕交通科技有限公司西安分公司陕西西安710000 中咨数据有限公司北京100083 美国加州交通厅养护处加利福尼亚萨克拉门托95835

总结了路面破损图像自动处理技术的重要研究成果,分析了该领域关键技术的研究进展,包括路面破损检测系统、图像处理算法和识别算法评估;比较了不同路面破损检测系统与目标自动识别算法的检测精度和适用性,给出了路面破损图像自动处理技... 详细信息

总结了路面破损图像自动处理技术的重要研究成果,分析了该领域关键技术的研究进展,包括路面破损检测系统、图像处理算法和识别算法评估;比较了不同路面破损检测系统与目标自动识别算法的检测精度和适用性,给出了路面破损图像自动处理技术未来可能的主要研究方向。研究结果表明:在路面破损检测系统方面,从早期基于摄影技术的图像采集到目前的3D激光扫描技术,路面图像采集技术更加便捷和高效,但破损图像自动分析和目标自动识别算法仍然存在挑战;在路面破损图像处理算法方面,传统的路面裂缝目标分割算法已由过去的基于单一特征(灰度、边缘形状等)的检测方法演化到多特征融合检测方法和图优化检测方法,还出现了一些精细化的裂缝目标连接与恢复算法,大幅提高了裂缝检测精度,但需要的计算资源和人工先验知识库也随之不断增大;在路面裂缝处理算法评估和比较方面,主要利用人工分割来评价自动识别结果,目前迫切需要建立一个面向全球开放的大型路面破损图像数据库,以客观、有效地评估现有各种路面破损图像处理算法;基于2D图像特征分析的路面破损图像自动识别算法很难在识别精确性、算法通用性和实时性方面同时取得最佳效果;近年来,大量学者开始尝试借助深度学习神经网络自动识别路面破损,但该技术仍处于活跃的演进过程中;在提高路面破损自动识别精度和效率方面,3D激光扫描技术和基于人工智能的深度学习技术的发展将对未来路面破损图像自动识别技术的最终突破产生重大推进作用。

关键词：路面养护路面破损图像处理破损识别裂缝检测破损分类

来源：评论

学校读者我要写书评

暂无评论

Optimizing Schedule Length for DAG Type Applications with Energy Consumption Constraint in Heterogeneous Computing systems

Optimizing Schedule Length for DAG Type Applications with En...

引用

Symposium of image, Signal processing, and Artificial Vision (STSIVA)

作者： Yu He Jinchao Chen Chenglie Du Pengcheng Han Northwestern Polytechnical University Xi’an China

ISBN: (数字)9781728170862

ISBN: (纸本)9781728170879

Schedule length minimization of a parallel application with precedence constrained tasks in heterogenous computing systems is always a research hotspot of distributed computing. Unfortunately, accelerating the execution of tasks requires faster processors and consequently produces more energy. Users are faced to a time-energy tradeoff in selecting processors and execution frequencies for tasks. A common way to address this trade-off is to minimize schedule length under energy constraints. Up to now only a few works have been done to address this problem. Nevertheless, the energy preassignment methods of these works are unfair for low priority tasks in various degrees. Furthermore, existing works pay little attention to the priority assignment strategy, which can be critical for task scheduling. Hence, we proposed a novel approach named DAG Scheduling with Energy Consumption Constraint (DSECC) to solve this problem. DSECC combines several priority assignment strategies to assign priorities for tasks, and preassigns energy for tasks based on the average energy consumption of tasks on different processors. A large number of experiments based on randomly generated DAG show that compared against state-of-the-art algorithms, our proposed algorithm can obtain smaller schedule length and generate less energy consumption.

关键词： Schedules Energy consumption Time-frequency analysis Program processors Scheduling algorithms Heterogeneous networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

Initial classification algorithm for pavement distress images using features fusion 11th

Initial classification algorithm for pavement distress image...

引用

11th International KES Conference on Intelligent Interactive Multimedia: systems and Services, KES-IIMSS 2018

作者： Xu, Zhigang Che, Yanli Min, Haigen Wang, Zhongren Zhao, xiangmo School of Information Engineering Chang’an University Xi’anShaanxi China California Department of Transportation SacramentoCA958833 United States

ISBN: (纸本)9783319922300

In this paper, a novel two-staged pavement image processing framework is presented. The pavement images are classified into four general categories in the first stage, so that the images can be processed using category-specific algorithms in the 2nd stage. The proposed algorithm first fuses a local contrast enhanced image with a global grayscale corrected image to obtain an enhanced distressed pavement image. The enhanced image is then decomposed with a three-layer wavelet transform to obtain three texture features of the entire image including High-Amplitude Wavelet Coefficient Percentage (HAWCP), the High-Frequency Energy Percentage (HFEP), and the Standard Deviation (STD). In the meantime, an improved P-tile method is used to obtain the binary image. From the binary image, three additional shape features are extracted including the Average Area of all Connected Components (AA), the Area of the Maximum Connected Component (AM), and the Equivalent Length of the longest Connected Component (EL). Finally, a BP neural network is used to fuse both the texture and shape features sequentially to achieve the initial classification. Experimental results show that for the four types of pavement images, the proposed algorithm achieves an effective classification of the pavement distress image with the accuracy rates of 96.5%, 91.4%, 95.2% and 98.1% respectively, which are higher than those of the classification algorithm with a single-type feature. © Springer International Publishing AG, part of Springer Nature 2019.

关键词： Pavements

来源：评论

学校读者我要写书评

暂无评论

A 4K$\times$ 2K@60fps Multifunctional Video Display Processor for High Perceptual image Quality

引用

IEEE Transactions on Circuits and systems I: Regular Papers 2019年第2期67卷 451-463页

作者： Hang Wang Xuchong Zhang Tiancheng Wang Wenchang Li Qiubo Chen Pengju Ren xiaogang Wu Hongbin Sun Zhiqiang Jiang xiang Li Daqiang Han Shiquan Yu Shouyi Yin Shaojun Wei Nanning Zheng Institute of Artificial Intelligence and Robotics School of Microelectronics Xi’an Jiaotong University Xi’an China Xi’an Jiaotong University Xi’an China Bytedance Inc. Beijing China Wireless Digital Chipset Development Department Hisilicon Inc. Shanghai China Changhong Electric Co. Ltd. Mianyang China Institute of Microelectronics Tsinghua University Beijing China

Video display processing is an indispensable module in a variety of multimedia systems. With the increase of video format to 4K×2K@60fps, the design of efficient display processing circuit faces severe challenges. This paper presents a video display processor which supports a variety of video formats and integrates multiple advanced algorithms for perpetual image quality improvement. By leveraging algorithm and architecture co-design, this paper efficiently implements these computational and memory intensive display processing algorithms in a single chip. In particular, we describe three representative design modules in detail, including motion compensated frame rate upconversion, content-adaptive contrast enhancement, and backlight local dimming. Extensive experiments demonstrate that the proposed design modules outperform the previous works in terms of either image quality or hardware efficiency. The overall chip is fabricated in GF 55nm CMOS technology, and can work at the maximum operating frequency of 594 MHz. The maximum input and output video formats reach up to 4K×2K@60fps.

关键词： Hardware Streaming media Computer architecture image quality Three-dimensional displays Very large scale integration TV

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：