检索结果-内蒙古大学图书馆

2018 3rd International Conference on Electrical, Automation and Mechanical Engineering(EAME 2018)

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

The performance of wavelet transform based image compressed sensing coding algorithms severely rely on the level of wavelet transform. To this end, this paper investigated the combination of mutil-level wavelet full sub-band in compressed sensing framework. Firstly, we constructed a full sub-band coefficient sparse vector of mutil-level discrete wavelet transform. Secondly, we designed a weight matrix to improve measurement matrix. Finally, sparsity vector was processed by compressed sensing to get the measured value. Compared with the exiting algorithms, the experimental results of the proposed algorithm show that the PSNRs of reconstructed images is improve up to 1～2 dB under the same objective quality.

关键词： image coding wavelet transform compressed sensing full sub-band coefficient sparsity vector

来源：评论

学校读者我要写书评

暂无评论

A Fast Quality Scalab.e Video Coding Method Based on Compressed Sensing

A Fast Quality Scalable Video Coding Method Based on Compres...

引用

2018 3rd International Conference on Electrical, Automation and Mechanical Engineering(EAME 2018)

作者： Min Sun Dong Hu Jianyu Ding Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Education Ministry's Engineering Research Center of Ubiquitous Network and Heath Service Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing University of Posts and Telecommunications

This paper presents a fast quality scalab.e video coding method based on compressed sensing(CS). The proposed method obtained the coding scheme of the enhancement MJU by using the interlayer and spatial correlation and kept the base layer's coding scheme unchanged. And the part in the enhancement layer which needed to be fine quantified was combined with the compressed sensing theory selectively which based on the sparsity of the signal and the complexity of the reconstruction. In order to satisfy the coding syntax structure of the reference software, the measurement value got by compressed sensing was complemented by 0 s and the flag bit was set to distinguish the special sub-blocks coded by CS. Experimental results show that the proposed algorithm can effectively improve the efficiency of scalab.e video coding and reduce the computational complexity.

关键词： video coding compressed sensing quality scalab.e video coding

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stage PCA Algorithm for Object Tracking

A Novel Two-Stage PCA Algorithm for Object Tracking

引用

2016 International Conference on communications, Information Management and Network Security (CIMNS2016)

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

ISBN: (纸本)9781510830981

In this paper, we propose a two-stage PCA algorithm to deal with the problem of target appearance changes in object tracking. Our method is based on particle filter framework and aims at building up a robust appearance model for the target. In the first-stage, PCA is applied on several templates collected before tracking to construct a low dimensional subspace for the targets. Correspondingly, in the later tracking, all particles will be projected into this subspace to calculate the weight of particles, as well as the location of the target by weighted sum of particles. In the second-stage, PCA is adopted to decompose the reconstruction error into orthogonal basis to find the basis with biggest variance which can best present the appearance changes. Correspondingly, we uses this basis to update the old subspace. Besides, a threshold is set to decide when to update which greatly reduce the numbers of update. The two stages work together to establish a robust appearance model making our tracking algorithm more robust. Experimental results on public video sequence demonstrate the effectiveness of our proposed algorithm.

关键词： particle filter two-stage PCA eigenspace reconstruction error

来源：评论

学校读者我要写书评

暂无评论

A parallel HEVC encoder scheme based on Multi-core platform

A parallel HEVC encoder scheme based on Multi-core platform

引用

2015 4th National Conference on Electrical,Electronics and Computer Engineering(NCEECE 2015)

作者： Shu Jun Hu Dong Education Ministry’s Key Lab of Broadband Wireless Communication and Sensor Network Technology Education Ministry’s Engineering Research Center of Ubiquitous Network and Health Service System Jiangsu Province’s Key Lab of Image Procession and Image Communications Nanjing University of Post and Telecommunications

ISBN: (纸本)9781510819085

In this paper, we propose a parallel HEVC encoder scheme based on multi-core platform, which provides maximized parallel scalab.lity by exploiting two-level parallelism, namely, the frame level parallelism and the CTB level parallelism. Inspired by the intra-CTB row level parallelism of WPP in HEVC, we investigate the inter-frame CTB prediction dependency to its reference CTBs, and find the inter-CTB correlation. Using this inter-correlation, we divide a frame into CTB units and create CTB-row level coding threads when their corresponding reference CTBs are availab.e. Each thread is bonded to a processing core, therefore, both intra- and inter-CTB rows can be encoded in parallel. Moreover, we introduce a priority scheduling mechanism to control the coding threads. Experiments on Tilera-Gx36 multi-core platform show that, compared with serial execution, the proposed method achieves 3.6 and 4.3 times speedup for 1080 P and 720 P video sequences, respectively.

关键词： HEVC multi-core platform parallel processing frame-level CTB-level

来源：评论

学校读者我要写书评

暂无评论

Data-consistent Unsupervised Diffusion Model for Metal Artifact Reduction

Data-consistent Unsupervised Diffusion Model for Metal Artif...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tong, Zhan Wu, Zhan Yang, Yang Mao, Weilong Wang, Shijie Li, Yinsheng Chen, Yang Southeast University Laboratory of Image Science and Technology Nanjing210096 China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Chinese Academy of Sciences Research Center for Medical Artificial Intelligence Shenzhen Institutes of Advanced Technology Shenzhen518055 China School of Computer Science and Engineering Key Lab. of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology Nanjing210096 China

ISBN: (纸本)9798350337488

Computed Tomography (CT) is an imaging technique widely used in clinical diagnosis. However, high-attenuation metallic implants result in the obstruction of low-energy Xrays and further lead to metal artifacts in the reconstructed CT images. Deep supervised model-based metal artifact reduction(MAR) approaches are limited in clinical applications due to the difficulty in obtaining paired artifact-affected and artifactfree data. Furthermore, these model-based methods lack the consideration of data consistency in the sinogram-domain to perform exact metal trace inpainting. To address these challenges, we propose a Data-consistent unsupErVised diffusiOn model for meTal artifact rEDuction, called DEVOTED-Net. First, DEVOTED-Net leverages prior knowledge to guide the conditional diffusion model for fine-grained metal trace inpainting. Second, an unsupervised MAR framework is designed in the reverse process for the unknown metal traces restoration in the sinogram domain. Third, to further enhance the sinogram-domain data consistency, physics-based consistency constraint loss including conjugateray consistency loss and accumulation-ray consistency loss is designed. Extensive experiments are carried out to verify the performance of our algorithm on the publicly availab.e dataset and clinical experimental dataset. This efficient, accurate, and reliable MAR approach holds great potential in clinics. © 2023 IEEE.

关键词： computed tomography deep unsupervised learning denoising diffusion probabilistic model Metal artifact reduction physics-based consistency constraint

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Vehicle Color Recognition Using Monocular camera

Vehicle Color Recognition Using Monocular camera

引用

2011年无线通信与信号处理国际会议(WCSP 2011)

作者： Mengjie Yang Xiuchang Zhu Liang Li Guang Han Xiaofei Li Jiangsu Provincial Key Lab of Image Processing and ImageCommunication Nanjing Univ. of P&TNanjing Engineering Research Center of Wideband Wireless Communication and Display Technique Ministry of Ed Engineering Research Center of Wideband WirelessCommunication and Display Technique Ministry ofEduc

This paper introduces a novel moving vehicle color recognition method. By processing videos recorded by monocular camera on traffic, we get single color image of vehicles which are crossed the traffic in any direction. First, paper employed a H-S two dimension histogram method to detect the color of the vehicles, and distinguish red, yellow, green and blue four color vehicles. Due to deal with the vehicles that do not satisfy above 4 colors, Regional Color Judgment method is proposed. This method consists of the following five steps: Firstly, position the color detection region by identifying the travelling direction of the vehicle. Then pick out the candidate color extraction region used to vehicle recognition. At last extract the color of the candidate region and match the color with the templates we predefined, the color of the best fit template is the color of the vehicle.

关键词： vehicle color recognition region choice HSV space vehicle detection

来源：评论

学校读者我要写书评

暂无评论

image Fusion Algorithm Based on Features Motivated Multi-Channel Pulse Coupled Neural Networks

Image Fusion Algorithm Based on Features Motivated Multi-Cha...

引用

International Conference on Bioinformatics and Biomedical Engineering (ICBBE)

作者： Xiaobo Qu Jingwen Yan 1Dept. of Communication Engineering Xiamen University.Fujian P.R.China 361005 1Dept. of Communication Engineering Xiamen University.Fujian P.R.China 3610052Key Lab of Digital Signal and Image Processing ofGuangdong Province Shantou University.Guangdong P.R.China 515063.

Pulse coupled neural networks (PCNN) is a mammal visual cortex-inspired artificial neural networks. Owing to the coupling links in neurons, PCNN is successful to utilize the local information, thus it has been successfully employed in image fusion. However, in traditional PCNN for image fusion, value of per pixel is used to motivate per neuron. In this paper, image feature of per pixel, e.g. gradient and local energy, is used to motivate per neuron and generate firing maps. Each firing map is corresponding to one type feature. Furthermore, a new multi-channel PCNN is presented to combine these firing maps via a weighting function which measures the contribution of these features to the fused image quality. Finally, pixels with maximum firing times, when firing times of source images are compared, are selected as the pixels of the fused image. Experimental results demonstrate that the proposed algorithm outperforms Wavelet- based and Wavelet-PCNN-based fusion algorithms.

关键词： image fusion Neural networks Neurons Pixel Discrete wavelet transforms image processing Artificial neural networks Fusion power generation Humans Pulse modulation

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird’s-Eye-View Representations in Autonomous Driving

arXiv

引用

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code availab.e at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

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：