检索结果-内蒙古大学图书馆

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Wang, Ning Liu, Feng Gan, Zongliang Jiangsu Province Key Lab on Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783030317256

License plate detection has wide applications in the intelligent transportation system, while it still remains challenges to improve the robustness under various shooting distance and observation angles. To get better performance, a novel convolutional-neural-network-based method is proposed, which is achieved with auxiliary information and context fusion model. First, the auxiliary information is employed in our framework, which corresponds with resolutions, orientations and shapes of license plates. Specifically, the multiple resolutions are collected through integrating multi-level features of convolution hierarchy. Besides the various scales and ratios, the region proposal network RPN with multi-angle anchors and branching structure is applied to generate proper proposals. Second, an effective context fusion model is designed to fully exploit the hidden correlation between license plates and contextual properties. The local and contextual features are independently learned in the dual pathways, which are later joint to form a powerful representation in subsequent layers. Comprehensive experiments on the publicly available datasets confirm the effectiveness of the proposed method. © Springer Nature Switzerland AG 2019.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Study on the segmentation method of multi-phase CT liver tumor based on dual channel U-Nets

Study on the segmentation method of multi-phase CT liver tum...

引用

2020 International Symposium on Automation, Information and Computing, ISAIC 2020

作者： Xu, Changchang Hu, Dong Zhang, YaoDong Pang, Yuwei Jiangsu Province’s Key Lab of Image Procession and Image Communications Nanjing University of Posts and Telecommunications Nanjing210003 China Education Ministry’s Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Nanjing210003 China Education Ministry’s Engineering Research Center of Ubiquitous Network and Heath Service Nanjing University of Posts and Telecommunications Nanjing210003 China first clinical medical college of Nanjing Medical University Nanjing University of Posts and Telecommunications Nanjing210003 China

As a common malignant tumor disease, hepatocellular carcinoma is the most common cancers in the world. The incidence of hepatocellular carcinoma in China is higher than that in the world. Therefore, it is very important for doctors to separate liver and tumor from CT images by means of computer-aided diagnosis and treatment. In this paper, a multiscale DC-CUNets network liver tumor segmentation method is proposed to enhance the fusion of multi-phase image features in CT, the scale of liver tumors, and the optimization of network training process. (1) A multistage CT liver tumor segmentation method based on two-channel cascaded U-Nets (DC-CUNets) is proposed. The liver was segmented using the first-order U-Net, and then the segmented area of interest of the liver was input into the second-order U-Net network to segment liver tumors. We designed two-channel U-Nets to learn the image characteristics of CT images in arterial and venous phases respectively, and to achieve two-channel feature fusion through feature cascade to improve the overall accuracy of liver tumor segmentation.(2) A multistage CT liver tumor segmentation method based on multiscale DC-CUNets was proposed. For the scale problem of liver tumors, we designed a two-layer multiscale void convolution module to obtain image features at different scales for large, medium and small tumors, and fuse the multiscale features at the output of the module. We have replaced the convolution layer of the fourth module in the second-order two-channel liver tumor segmentation U-Nets by the two-layer multiscale cavity convolution module to implement multiscale DC-CUNets. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Anchored Neighborhoods Search Based on Global Dictionary Atoms for Face Photo-Sketch Synthesis

Anchored Neighborhoods Search Based on Global Dictionary Ato...

引用

2019第十一届数字图像处理国际会议

作者： Feng Liu Ran Xu Jieying Zheng Qiuli Lin Zongliang Gan College of Educational Science and Technology Nanjing University of Posts and Telecommunications Jiangsu Province Key Lab on Image Processing & Image Communications Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications

Example-based face sketch synthesis technology generally requires face photo-sketch images with face alignment and size *** break through the limitation,we propose a global face sketch synthesis method:In training,all training photo-sketch patch pairs are collected together and a photo feature dictionary is learned from the photo *** each atom of the dictionary,its K closest photo-sketch patch pairs are clustered,namely "Anchored Neighborhood".In testing,for each test photo patch,we search its nearest photo patch in the Anchored Neighborhood determined by its closest atom,then the corresponding sketch patch is the *** the same way,we train and test in the high-frequency domain and synthesis the high-frequency ***,the fusion of the initial and the high-frequency results is the final *** experiments on three public face sketch datasets and various real-world photos demonstrate the effectiveness and robustness of the proposed method.

关键词： Face sketch synthesis Dictionary learning Dictionary atom Anchored neighborhood image patch

来源：评论

学校读者我要写书评

暂无评论

Vehicle Color Recognition Based on Superpixel Features

Vehicle Color Recognition Based on Superpixel Features

引用

2019第十一届数字图像处理国际会议

作者： Qiuli Lin Feng Liu Qiang Zhao Ran Xu Jiangsu Province Key Lab on Image Processing & Image Communications Nanjing University of Posts and Telecommunications College of Educational Science and Technology Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications

In this paper,a novel methodology is presented to settle the region of interest(ROI) detection problem in vehicle color recognition so as to remove the redundant components of vehicles that interfere greatly with color *** order to make full use of the local color and spatial information,vehicle images are divided into different superpixels at *** spatial relationship between superpixels and the outermost pixels is then used for the background removal of vehicle *** comparing with the vehicle window clustering centroids obtained by k-means,the superpixels close to the universal color characteristics of windows are removed so that the dominant color superpixels are ***,a linear Support Vector Machine classifier is trained for color *** experiments demonstrate that the proposed methodology is effective for color region of interest detection and thus contribute to vehicle color recognition.

关键词： vehicle color recognition region of interest superpixel universal color characteristics Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Partial Attribute-Driven Video Person Re-Identification

Partial Attribute-Driven Video Person Re-Identification

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Wanru Song Jieying Zheng Yahong Wu Changhong Chen Feng Liu Department of Telecommunication Nanjing Univ. Posts & Telecommun. Nanjing China Jiangsu Key Lab of Image Processing & Image Communications Nanjing Univ. Posts & Telecommun. Nanjing China

Person re-identification has gradually become a hot research topic in many fields, such as security, criminal investigation and video analysis. In this paper, we propose a novel feature extraction framework for video-based person re-identification, namely, the partial attribute-driven network (PADNet). The proposed method is based on the deep-learning architecture and incorporates the attribute and identity learning of the pedestrian. Existing attribute research always focuses on the feature representation at the global-level. Unlike them, first, the pedestrian is automatically partitioned to several body parts in our work. Then the pedestrian and his/her body parts are annotated by the global and partial attributes, respectively. Finally, we employ a four-branch multi-label network to explore the spatial-temporal cues of videos by utilizing these labeled samples. Extensive experiments are conducted on two video-based datasets, including PRID2011 and iLIDS-VID. The experimental results demonstrate the superiority and effectiveness of the proposed PADNet over the state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint DBF and SAO Parallel Filtering Based on Multithread Load Balancing

引用

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Hao Ma Dong Hu Yi Li Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing 210003 China Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing 210003 China Education Ministry's Engineering Research Center of Ubiquitous Network and Heath Service Nanjing University of Posts and Telecommunications Nanjing 210003 China

This paper presents a joint parallel loop filtering algorithm based on multi-thread load balancing in HEVC decoding, which implements the parallel processing of deblocking filtering (DBF) and sample adaptive compensation (SAO). Because of the diversity of video, the texture of different regions in an image is also different, which leads to various CTU partition methods. Therefore, the number of the boundary to be filtered is greatly different, resulting the computation load among multiple threads unbalanced in parallel processing. To solve this problem, an area division scheme is proposed, which divides the image into multiple areas, and the number of boundaries to be filtered in each area is similar. Then, the mapping relationship table is used to allocate these areas to multiple threads for parallel processing, so as to achieve the load balancing among the filtering threads. Finally, the cache technology is used to combine DBF and SAO to reduce the delay between them and improve the overall parallelism of the loop filter. Experimental results show that the performance of the proposed load balancing joint filtering algorithm is 8.15% higher than the previous scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scale Adaptive Block Target Tracking Based on Multi-layer Convolution Features and Kernel Correlation Filter

引用

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Ting Zhang Dong Hu Jing Zhang Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing 210003 China Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing 210003 China Education Ministry's Engineering Research Center of Ubiquitous Network and Heath Service Nanjing University of Posts and Telecommunications Nanjing 210003 China

Target tracking is currently a hot research topic in Computer Vision and has a wide range of use in many research fields. However, due to factors such as occlusion, fast motion, blur and scale variation, tracking method still needs to be deeply studied. In this paper, we propose a block target tracking method based on multi-convolutional layer features and Kernel correlation filter. Our method divides the tracking process into two parts: target position estimation and target scale estimation. First, we block the target frame based on the condition number. Second, we extract the features by the convolutional layer and apply it to the kernel correlation filter to get the center position of different block targets. With the reliability of different blocks measured by the Barker coefficient, the overall target position center is obtained. Then, the affine transformation is adopted to achieve the scale adaptation. The algorithm in this paper is evaluated by the public video sequences in OTB-2013. Numerous experimental results demonstrate that the proposed tracking method can achieve target scale adaptation and effectively improve the tracking accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Siamese Network Tracking Algorithm Based on Hierarchical Attention Mechanism

引用

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Hu Zhang Dong Hu Yingcan Qiu Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing 210003 China Nanjing University of Posts and Telecommunications Nanjing 210003 China Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing 210003 China Education Ministry's Engineering Research Center of Ubiquitous Network and Heath Service Nanjing 210003 China

A siamese network tracking algorithm based on hierarchical attention mechanism is proposed in this paper. In order to obtain more robust target tracking results, different layer features are fused effectively. In the process of extracting features, attention mechanism is used to recalibrate the feature map, and AdaBoost algorithm is used to weight the target feature map, which improves the reliability of the response map. Besides, the Inception module is also introduced which not only increases the width of the network and the adaptability of the siamese network to the scale, but also reduces the parameters and improves the speed of network training. Experimental results show that this method can effectively solve the impact of background clutter and improve the accuracy of tracking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Representation for Video-based Person Reidentification with Attribute-constraints

A Novel Representation for Video-based Person Reidentificati...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： Wanru Song Jieying Zheng Yahong Wu Qingqing Zhao Changhong Chen Feng Liu Jiangsu Key Lab of Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781538646748;9781538646731

Person re-identification is an important task in the field of intelligent video surveillance, which has become one of the research focus spots in the field of computer vision. Video-based person re-identification aims to verify a pedestrian identity of the video sequences which captured from non-overlapping cameras at different time. In this paper, we propose a novel feature extractor based on LSTM networks. These LSTM networks are used to extract the effective space-time feature representation named the attribute-constraints space-time feature (ASTF). Different from other methods, we manually annotate pedestrians in videos with three attributes. In the meantime, the attributes with the IDs of pedestrians are regarded as labels to train the feature extractor. The ASTF representation for a testing video is extracted by this feature extractor, which is an effective space-time feature representation for video-based re-identification. Extensive experiments on two public datasets demonstrate that our approach outperforms the state-of-the-art video-based re-identification methods.

关键词： Feature extraction Task analysis Training Cameras Testing Measurement Video sequences

来源：评论

学校读者我要写书评

暂无评论

Pixel classified colourisation method based on neighbourhood similarity priori

Pixel classified colourisation method based on neighbourhood...

引用

作者： Chen, Jie Gan, Zongliang Zhu, Xiuchang Wang, Jin Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Post and Telecommunications P.O. Box 166 No. 66 Xin Mofan Road Nanjing Jiangsu China College of Information Engineering Yangzhou University No. 88 South University Ave Yangzhou Jiangsu China

Colourisation is a kind of computer-aided technology which automatically adds colours to greyscale images. This paper presents a scribble-based colourisation method which treats the flat and edge pixels differently. First, we classify the pixels to flat or edge pixel categories using the neighbourhood similarity pixels searching algorithm. Then, we compute the weighted coefficients of the edge pixels by solving a constraint quadratic programming problem and compute the weighted coefficients of the flat pixels based on their luminance distances. Finally, we transmit the weighted coefficients to the chrominance images according to the joint correlation property between luminance and chrominance channels, and combine with the colours scribbled on by the user to compute all the unknown colours. The experimental results show that our method is effective especially on reducing colour bleeding in the boundary parts and can give better results when only a few colours are scribbled on. © 2018 Inderscience Enterprises Ltd.

关键词： Quadratic programming

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：