检索结果-内蒙古大学图书馆

44th IEEE international conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Duarte, Amanda Roldan, Francisco Tubau, Miquel Escur, Janna Pascual, Santiago Salvador, Amaia Mohedano, Eva McGuinness, Kevin Torres, Jordi Giro-i-Nieto, Xavier Univ Politecn Cataluna Barcelona Spain Barcelona Supercomp Ctr Barcelona Spain Insight Ctr Data Analyt DCU Dublin Ireland

ISBN: (纸本)9781479981311

Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face images of a speaker by conditioning a Generative Adversarial Network (GAN) with raw speech input. We propose a deep neural network that is trained from scratch in an end-to-end fashion, generating a face directly from the raw speech waveform without any additional identity information (e.g reference image or one-hot encoding). Our model is trained in a self-supervised approach by exploiting the audio and visual signals naturally aligned in videos. With the purpose of training from video data, we present a novel dataset collected for this work, with highquality videos of youtubers with notable expressiveness in both the speech and visual signals.

关键词： deep learning adversarial learning face synthesis computer vision

来源：评论

学校读者我要写书评

暂无评论

An Enhancement Method of Obstacle Information Obtaining Accuracy in Binocular vision 1

引用

1st international conference on Intelligent Technologies and Applications (INTAP)

作者： Zhang, Zichao Han, Yu Chen, Jian Dou, Wenhao Wang, Shubo Du, Nannan Wang, Guangqi Zheng, Yongjun China Agr Univ Coll Engn Beijing 100083 Peoples R China China Agr Univ Coll Water Resources & Civil Engn Beijing 100083 Peoples R China South China Univ Technol Sch Mech & Automot Engn Guangzhou 510006 Guangdong Peoples R China

ISBN: (数字)9789811360527

ISBN: (纸本)9789811360527

The accuracy of the location information acquisition technology based on binocular vision is directly related to the resolution of the image obtained. To improve the applicability of the measurement accuracy in binocular vision under limited image resolution, an enhancement method based on sub-pixel was put forward. First, correlate peak is slit 4 times (vertical, horizontal, left oblique and right oblique) along 8 directions. Second, four maxima points in 4 slit directions are obtained. Finally, sub-pixel coordinates are obtained according to the established cabinet. According to the image data collected on the unmanned aerial vehicle (UAV) platform, the normalized cross correlation (NCC) stereo matching is carried out. The distance, size and orientation of obstacles are obtained after subpixel processing. In theory, the method proposed in this study can reach 0.01 pixel.

关键词： Obstacle information Sub-pixel coordinates Binocular vision Normalized cross correlation Stereo matching UAV

来源：评论

学校读者我要写书评

暂无评论

A Framework for Automatic Building Detection from Low-Contrast VHR Satellite imagery 3

A Framework for Automatic Building Detection from Low-Contra...

引用

3rd international conference on Video and image processing (Icvip)

作者： Li, Junjun Cao, Jiannong Changan Univ Sch Geol Engn & Surveying Xian Shaanxi Peoples R China Changan Univ Sch Earth Sci & Resources Xian Shaanxi Peoples R China

ISBN: (纸本)9781450376822

Automatic separation of buildings from built-up area has attracted considerable interest in computer vision and digital photogrammetry field. While many efforts have been made for building extraction, none of them address the problem completely. This even a greater challenge in low-contrast very-high resolution (VHR) panchromatic satellite images. To alleviate this issue, a framework for automatic building detection approach using dominant structural feature (DSF) is proposed in this study. Firstly, in order to suppress noise while enhancing structural feature, contourlet transform based image contrast enhancement is employed followed by directional morphological filtering operation. Considering the structural characteristics of buildings which are significantly different from the other non-manmade objects. We then exploit DSF by means of windowed structure tensor analysis. Candidate building edges are generated using multi-seed classification technique in DSF space, subsequently. Finally, a series rule- and knowledge-based criterions are elaborate designed for false alarm reduction procedures.

关键词： Building detection Low-contrast panchromatic satellite image image enhancement Dominant structural feature

来源：评论

学校读者我要写书评

暂无评论

Research on the technology used to inspect the visual appearance of tropical fruit, based on machine vision color space

Research on the technology used to inspect the visual appear...

引用

international conference on Intelligent Computing, Communication and Devices, ICCD 2017

作者： Zhang, Kun Wang, Haifeng Shen, Chong Chen, Xiaoyan College of Ocean Information Engineering Hainan Tropical Ocean University SanyaHainan572022 China State Key Laboratory of Marine Resources Utilization in South China Sea Hainan University HaikouHainan570228 China College of Information Science and Technology Hainan University HaikouHainan570228 China Sanya Key Laboratory of Computer Vision Hainan Tropical Ocean University SanyaHainan572022 China

ISBN: (纸本)9789811089435

Machine vision (computer vision) technology and image processing has been widely used for the automatic classification of fruit—representing an area for future research. In this chapter, we mainly use the method of machine vision to study color characteristics, size contours, and surface textures of fruit surfaces in the hue, saturation, and value (HSV) color space. The chapter goes on to realize the automatic classification of Hainan tropical fruit presenting typical characteristics. © Springer Nature Singapore Pte Ltd. 2019.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Neural Network Based Electronics Segmentation 12th

Neural Network Based Electronics Segmentation

引用

12th international conference on Intelligent Robotics and Applications (ICIRA)

作者： Ma, Senwei Fan, Xiaoyuan Wang, Lei Cheng, Jun Xu, Chengjun Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen Peoples R China

ISBN: (纸本)9783030275419;9783030275402

In traditional automated assembly lines, operations of the robotic arm settings always rely on programming, which is unconvenient and time consuming. To solve this problem, computer vision is an alternative choice, and popular in robotics recently. With the great breakthrough of deep learning in the field of computer vision, image processing methods based on deep neural network (DNN) have been applied in various industry scenes. This paper explores the application of DNN-based image segmentation technology in factory assembly lines. We have developed one electronics' image datasets for experiments. And deep convolution neural networks (CNN) based on region proposal have been used to detect, segment objects, and generate masks for corresponding electronics. Experimental results show that the proposed framework has high recognition accuracy and strong robustness, which will be helpful when applied in robotic arm settings in automated assembly lines.

关键词： Deep neural network Detection of electronics object image mask Robotic

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Spider images in Natural Background 4

Automatic Classification of Spider Images in Natural Backgro...

引用

4th IEEE international conference on Signal and image processing (ICSIP)

作者： Jian, Yang Peng, Su Li Zhenpeng Yu, Zhao Zhang Chenggui Yang Zizhong Dali Univ Coll Math & Comp Sci Dali 671003 Yunnan Peoples R China Dali Univ Prov Key Lab Entomol Bio R&D Dali 671003 Yunnan Peoples R China

ISBN: (纸本)9781728136608

Spiders are the most abundant predatory natural enemies in terrestrial ecosystems. As an important natural enemy of many agricultural and forestry pests, spiders play a very significant role in the biological control of pests. In order to make rational use of spider resources, it is necessary to observe and study the population characteristics of it. Direct observation method is time-consuming and laborious. If we can take the videos or images of spiders by surveillance cameras, and then use computer vision technology to identify and classify automatically, the efficiency of image data acquisition and pest biological control will be greatly improved. Motivated by this, we studied the classification and recognition of spider images in natural background obtained by common surveillance equipment. However, the images of some species of spiders in natural background are difficult to be collected, and the inadequate clarity and contrast of the subjects in images will also affect the recognition accuracy. So, firstly, histogram equalization was used to enhance the contrast of the image;the dataset of spider images was expanded by image rotation, reflection, flipping, zooming, translating and increasing the pixel noise appropriately, and so on;the contour detection was carried out for assistant recognition. Secondly, taken the deep convolutional neural networks (CNN) as our basic framework, two automatic recognition models of spider images, that is the 8-layer deep CNN model and the transfer learning model based on Inception-v3, were constructed. After that, the two models were trained, evaluated and compared under a dataset with 4478 pre-processed images. The experimental results show that the first model has a limited effect on image feature extraction of spiders in natural background, while the second model based on transfer learning can achieve better recognition accuracy when combining image contour features as an auxiliary input. In the second model, the accuracy of

关键词： classification of spider images image preprocessing deep convolutional neural networks transfer learning contour detection

来源：评论

学校读者我要写书评

暂无评论

Multi-scale HOG Feature Used in Object Detection 10

Multi-scale HOG Feature Used in Object Detection

引用

10th international conference on Graphics and image processing (ICGIP)

作者： Li, Jin Zhang, Hong Zhang, Lei Li, Yawei Kang, Qiaochu Luo, Zhaohui Wu, Yujie Beihang Univ Image Ctr Sch Astronaut Beijing Peoples R China Univ Massachusetts Amherst MA 01003 USA

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

Object detection is one of the most popular and difficult field in computer vision. Although deep learning methods have great performance on object detection. For specific application, algorithms which use hand-crafted features are still widely used. One main problem in object detection is the scale problem. Algorithms usually use image pyramid to cover as many scales as possible. But gaps still exist between scale levels in image pyramid. Our work extends some sub scale level to fill the gaps between image pyramids. To this end, we use Gaussian Scales Pyramid to generate sub-scale image and extract HOG feature on the sub-scale. We use framework offered by DPM algorithm and make modification on it. We compare the result of our method with DPM baseline on Pascal VOC database. Our work has great performance on some categories and makes an improvement on the overall performance. This work can be used in other object detection frameworks. We apply multi-scale HOG feature on pre-process procedure of our own detection framework and test it on our own dataset. Then the framework gains performance improvement on precision and recall rate of the pre-process procedure comparing to the original HOG feature architecture.

关键词： multi-scale HOG object detection

来源：评论

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and Computing 2020年 1022 AISC卷 v-vi页

作者： Chaudhuri, Bidyut B. Nakagawa, Masaki Khanna, Pritee Kumar, Sanjeev Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Techno India University Kolkata India Department of Advanced Information Technology and Computer Sciences Tokyo Institute of Agriculture and Technology Koganei Tokyo Japan Department of Computer Science Indian Institute of Information Technology Design and Manufacturing Jabalpur Jabalpur Madhya Pradesh India Department of Mathematics Indian Institute of Technology Roorkee Roorkee Uttarakhand India

来源：评论

学校读者我要写书评

暂无评论

A YOLO-based Separation of Touching-Pigs for Smart Pig Farm Applications 21

A YOLO-based Separation of Touching-Pigs for Smart Pig Farm ...

引用

21st international conference on Advanced Communication Technology (ICACT)

作者： Seo, Jihyun Sa, Jaewon Choi, Younchang Chung, Yongwha Park, Daihee Kim, Hakjae Korea Univ Dept Comp Convergence Software Sejong South Korea Class Act Co Ltd Seoul South Korea

ISBN: (纸本)9791188428021

For specific livestock such as pigs in a pigsty, many surveillance applications have been reported to consider their health for efficient livestock management. For pig surveillance applications, separating touching-pigs in real-time is an important issue for a final goal of 24-hour tracking of individual pigs. Although convolutional neural network (CNN)-based instance segmentation techniques can be applied to this separation problem, their collective performance of accuracy-time may not satisfy the required performance. In this study, we improve the collective performance of accuracy-time by combining the fastest CNN-based object detection technique (i.e., You Only Look Once, YOLO) with image processing techniques. We first apply image processing techniques to detect touching-pigs by using both infrared and depth information acquired from an Intel RealSense camera, then apply YOLO to separate the touching-pigs. Especially, in using YOLO as an object detector, we consider the target object as the boundary region of the touching-pigs, rather than the individual pigs of the touching-pigs. Finally, we apply image processing techniques to determine the final boundary line from the YOLO output. Our experimental results show that this method is effective to separate touching-pigs in terms of the collective performance of accuracy-time, compared to the recently reported CNN-based instance segmentation technique.

关键词： Smart farm computer vision Touching-Pigs Separation Convolutional Neural Network YOLO

来源：评论

学校读者我要写书评

暂无评论

Fruit tree image registration based on improved FAST algorithm 10th

Fruit tree image registration based on improved FAST algorit...

引用

10th international conference on computer and Computing Technologies in Agriculture, CCTA 2016

作者： Feng, Juan Zeng, Lihua Li, Jianping College of Information Science and Technology Hebei Agricultural University Baoding China College of Mechanical and Electrical Engineering Hebei Agricultural University Baoding China

ISBN: (纸本)9783030061548

In order to promote the efficiency and accuracy of image registration, this paper proposes an improved registration algorithm for fruit tree images acquired by a dual-sensor vision system. In the algorithm, feature points are extracted by FAST detectors from Gaussian scale space, and main orientation is determined and SURF descriptor is created with statistical method of neighbor intensity distribution, matching pairs are determined with a relative ratio method and a iterative purifying method in succession. Experimental results show that the proposed algorithm outperforms previous algorithms comprehensively. © IFIP international Federation for Information processing 2019.

关键词： image registration

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：