检索结果-内蒙古大学图书馆

Compressive sensing reconstruction of hyperspectral images based on codec space-spectrum joint dense residual network

引用

IET image processing 2023年第3期17卷 916-931页

作者： Xiao, Shuming Zhang, Ye Chang, Xuling Xu, Jiajia Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys 3888 Dong Nanhu Rd Changchun 130033 Peoples R China Univ Chinese Acad Sci Daheng Coll Beijing 100000 Peoples R China Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun Peoples R China

The spatial and spectral information contained in the hyperspectral image (HSI) make it widely used in many fields. However, the sharp increase of HSI data brings enormous pressure to the data storage and real-time transmission. The research shows that hyperspectral compressive sensing (HCS) breaks through the bottleneck of the Nyquist sampling theorem, which can relieve the massive pressure on data storage and real-time transmission. Existing HCS methods try to design advanced compression sampling matrix or reconstruction algorithms, but cannot connect the two through a unified framework. To further improve the image reconstruction quality, a novel codec space-spectrum joint dense residual network (CDS2-DResN) is proposed. The CDS2-DResN is divided into block compression sampling part and reconstruction part. For block compression sampling, coded convolutional layer (CCL) is leveraged to compress and sample HSI. For measurements reconstruction, deconvolution layer is first leveraged to initially reconstruct HSI, and then build a space-spectrum joint network to refine the initial reconstructed HSI. Moreover, the CCL and reconstruction network are optimized via a unified framework, which can simplify the pre-processing and post-processing process of HCS. Extensive experiments have shown that CDS2-DResN has an excellent HCS reconstruction effect at measurement rates 0.25, 0.10, 0.04 and 0.01, respectively.

关键词： feature extraction block compression sampling part Nyquist sampling theorem hyperspectral image compression sampling matrix massive pressure Geophysics computing CDS2-DResN enormous pressure initial reconstructed HSI reconstruction network image and video coding Neural nets geophysical image processing coded convolutional layer Optical, image and video signal processing computer vision and image processing techniques convolutional neural nets measurements reconstruction compressed sensing hyperspectral imaging compressive sensing reconstruction Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research reconstruction part HSI data excellent HCS reconstruction effect hyperspectral compressive sensing sample HSI image reconstruction space-spectrum joint network spatial information Geophysical techniques and equipment real-time transmission spectral information novel codec space-spectrum joint dense residual network image reconstruction quality data storage HCS methods

来源：评论

学校读者我要写书评

暂无评论

Addressing robust travel mode identification with individual trip-chain trajectory noise reduction

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第1期17卷 129-143页

作者： Zeng, Jiaqi Zhang, Guozheng Hu, Youwei Wang, Dianhai Zhejiang Univ Coll Civil Engn & Architecture B820 Anzhong Bldg866 Yuhangtang Rd Hangzhou 310058 Peoples R China Zhejiang Univ Ctr Balance Architecture Hangzhou Peoples R China Zhejiang Univ Co Ltd Architectural Design & Res Inst Hangzhou Peoples R China Alibaba Zhejiang Univ Joint Res Inst Frontier Tec Hangzhou Peoples R China

Identifying travel modes from Global Navigation Satellite System (GNSS) trajectories is helpful for traffic management. In mode identification, the motion features are extracted from trajectories to train the classifiers. However, features would be distorted by the positioning noise when migrating existing frameworks to poor-quality tracks. This study aims to answer how to eliminate the impact of positioning error on mode identification. Specifically, six widely used Trajectory Noise Reduction (TNR) methods were tested. Representative motion features were calculated and sent to several classical classifiers to evaluate the effect of TNR. Then, the extent to which TNR restores motion features is analysed by information gain. To verify the robustness of these methods, multiple noise scenarios are designed to simulate possible positioning noise. The results show that the trajectory smoothing methods perform better than the outlier elimination methods regardless of the type and magnitude of noise. In particular, the Gaussian kernel smoothing can achieve the highest effect in almost all noise scenarios. For untested TNR methods that require a time window radius parameter, a 30-s time window is a good candidate. Moreover, the visualisation verification cannot ensure the best TNR method for travel mode identification.

关键词： traffic engineering computing feature extraction multiple noise scenarios poor-quality tracks outlier elimination methods classical classifiers smoothing methods Gaussian processes identifying travel modes possible positioning noise traffic management untested TNR methods satellite navigation computer vision and image processing techniques Traffic engineering computing trajectory smoothing methods Data handling techniques TNR method representative motion features Radionavigation and direction finding individual trip-chain trajectory noise reduction Global Positioning System Other topics in statistics Global Navigation Satellite System trajectories widely used Trajectory Noise Reduction methods robust travel mode identification image motion analysis Probability theory, stochastic processes, and statistics

来源：评论

学校读者我要写书评

暂无评论

An efficient anchor-free method for pig detection

引用

IET image processing 2023年第2期17卷 613-626页

作者： Mattina, Morann Benzinou, Abdesslam Nasreddine, Kamal Richard, Francis ENIB UMR CNRS 6285 LabSTICC F-29238 Brest France COOPERL INNOVAT SAS Lamballe France

Given the rapid growth of commercial pig farms, the need to automatically monitor pig behaviour becomes more important in order to assist farmers. Recent advances in convolutional neural networks may pave the way for new solutions. However, the primary task of individual pig detection under real-world conditions is still a challenging task. Previous studies used anchor-based frameworks that are unsuitable for such crowded scenarios with extreme overlapping. Furthermore, most applications focus on specific levels of brightness, farm facilities, or pig species without considering generalization. To tackle these problems, an anchor-free pig detection method based on pig centre localization is first proposed. Then, a novel negative training data augmentation technique is introduced using examples from outside the training distribution. Furthermore, using the test time augmentation technique is proposed to improve the model performance. Experiments are conducted on two online pig detection datasets;the network surpasses state-of-the-art results for both datasets. It is also found that the proposed method outperforms the latest anchor-free techniques commonly used in crowded scenarios. The method can detect pigs individually, even if their bounding boxes overlap strongly or occlude each other. Moreover, the real-time system achieves an improvement of 10% in Fmeasure$F_{\text{measure}}$ when testing in unconstrained real-world conditions.

关键词： efficient anchor-free method online pig detection datasets feature extraction test time augmentation technique farming learning (artificial intelligence) Neural nets Agriculture, forestry and fisheries computing real-world conditions computer vision and image processing techniques convolutional neural nets commercial pig farms novel negative training data augmentation technique Data handling techniques object detection convolutional neural networks image recognition pigs farm facilities Agriculture network surpasses state-of-the-art results pig species pig behaviour anchor-based frameworks anchor-free pig detection method crowded scenarios latest anchor-free techniques individual pig detection data augmentation pig centre localization

来源：评论

学校读者我要写书评

暂无评论

Context-guided ground truth sampling for multi-modality data augmentation in autonomous driving

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第3期17卷 459-469页

作者： Shi, Peicheng Qi, Heng Liu, Zhiqiang Yang, Aixi Anhui Polytech Univ Wuhu Peoples R China Inst Zhejiang Univ Hangzhou Peoples R China

Data augmentation is an important pre-processing step for object detection in 2D image and 3D point clouds. However, studies on multimodal data augmentation are extremely limited compared to single-modal work. Moreover, simultaneously ensuring consistency and rationality when pasting both image and point cloud samples is a major challenge in multimodal methods. In this study, a novel multimodal data augmentation method based on ground truth sampling (GT sampling) is proposed for generating content-rich synthetic scenes. A GT database and scene ground database based on the raw training set is initially built, following which the context of the image and point cloud is used to guide the paste location and filtering strategy of the GT samples. The proposed method can avoid the cluttered features caused by random pasting of samples;the image context information can help the model to learn the correlation between the object and the environment more comprehensively, and the point cloud context information can reduce occlusion in the case of long-distance objects. The effectiveness of the proposed strategy is demonstrated on the publicly available KITTI dataset. Utilizing the multimodal 3D detector MVXNet as an implementation tool, our experiments evaluate different superimposition strategies ranging from context-free sample pasting methods to context-guided new training scenes. In comparison with existing GT sampling methods, our method exhibits a relative performance improvement of 15% on benchmark datasets. In ablation studies, our sample pasting strategy achieves a +2.81% gain compared with previous work. In conclusion, considering the multimodal context of modelled objects is crucial for placing them in the correct environment.

关键词： sample pasting strategy image segmentation feature extraction publicly available KITTI dataset multimodality data augmentation context-guided new training scenes scene ground database paste location long-distance objects learning (artificial intelligence) autonomous driving filtering strategy point cloud context information single-modal work important pre-processing step multimodal methods multimodal context 3D point clouds context-guided ground truth context-free sample pasting methods Optical, image and video signal processing computer vision and image processing techniques sampling methods Data handling techniques object detection GT samples ablation studies existing GT sampling methods multimodal 3D detector MVXNet content-rich synthetic scenes modelled objects novel multimodal data augmentation method robot vision simultaneously ensuring consistency different superimposition strategies point cloud samples data augmentation image context information raw training

来源：评论

学校读者我要写书评

暂无评论

FAFNet: Fully aligned fusion network for RGBD semantic segmentation based on hierarchical semantic flows

引用

IET image processing 2023年第1期17卷 32-41页

作者： Chen, Jiazhou Zhan, Yangfan Xu, Yanghui Pan, Xiang Zhejiang Univ Technol Sch Comp Sci & Technol 288 Liuhe Rd Hangzhou Peoples R China

Depth maps are acquirable and irreplaceable geometric information that significantly enhances traditional color images. RGB and Depth (RGBD) images have been widely used in various image analysis applications, but they are still very limited due to challenges from different modalities and misalignment between color and depth. In this paper, a Fully Aligned Fusion Network (FAFNet) for RGBD semantic segmentation is presented. To improve cross-modality fusion, a new RGBD fusion block is proposed, features from color images and depth maps are first fused by an attention cross fusion module and then aligned by a semantic flow. A multi-layer structure is also designed to hierarchically utilize the RGBD fusion block, which not only eases issues of low resolution and noises for depth maps but also reduces the loss of semantic features in the upsampling process. Quantitative and qualitative evaluations on both the NYU-Depth V2 and the SUN RGB-D dataset demonstrate that the FAFNet model outperforms state-of-the-art RGBD semantic segmentation methods.

关键词： cross-modality fusion image segmentation multilayers FAFNet model image enhancement hierarchical semantic flows attention cross fusion module geometric information image sampling semantic networks RGBD semantic segmentation methods NYU-Depth V2 dataset Knowledge representation color image analysis applications image fusion Optical, image and video signal processing computer vision and image processing techniques semantic flow features SUN RGB-D dataset fully aligned fusion network multilayer structure image resolution image colour analysis RGBD fusion block

来源：评论

学校读者我要写书评

暂无评论

ImDeeplabV3plus with instance selective whitening loss in domain generalization semantic segmentation

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第1期17卷 180-192页

作者： Zhang, You Chen, Houjin Li, Yanfeng Zhou, Junqi Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China

Semantic segmentation is a classical problem in computer vision, which is important in the field of autonomous driving. Although significant progress has been achieved in semantic segmentation, its generalization ability to unknown domains is still challenging. To effectively solve this problem, a semantic segmentation method ImDeeplabV3plus with instance selective whitening loss is proposed in this paper. DeeplabV3plus is selected as the baseline. In order to enhance the representation of the region of interest, the coordinate attention (CA) mechanism is added. To better integrate multiple low-level features, the adaptively spatial feature fusion (ASFF) is employed to adaptively learn the importance of features at different levels for each location. For preferably coping with the domain changes, an instance selective whitening (ISW) loss is introduced in the early stage of the backbone. The model is trained with the Cityscapes dataset and then applied to the unknown domain RobotCar dataset. Compared with DeeplabV3plus, the authors' ImDeeplabV3plus model shows 1.29% mIoU improvement. When ISW loss is added, 2.08% improvement in mIoU is achieved compared with ImDeeplabV3plus. Experimental results show that the proposed method is simple and improves the domain generalization ability.

关键词： image segmentation feature extraction instance selective whitening loss low-level features adaptively spatial feature fusion image representation learning (artificial intelligence) authors Neural nets Optical, image and video signal processing image fusion computer vision and image processing techniques domain generalization ability object detection deep learning (artificial intelligence) unknown domain RobotCar dataset semantic segmentation method ImDeeplabV3plus unknown domains ISW loss computer vision domain changes DeeplabV3plus, domain generalization semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Infrastructure camera calibration with GNSS for vehicle localisation

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第2期17卷 341-356页

作者： Ojala, Risto Vepsalainen, Jari Pirhonen, Jesse Tammi, Kari Aalto Univ Dept Mech Engn Espoo Finland

Intelligent transportation and smart city applications are currently on the rise. In many applications, diverse and accurate sensor perception of vehicles is crucial. Relevant information could be conveniently acquired with traffic cameras, as there is an abundance of cameras in cities. However, cameras have to be calibrated in order to acquire position data of vehicles. This paper proposes a novel automated calibration approach for partially connected vehicle environments. The approach utilises Global Navigation Satellite System positioning information shared by connected vehicles. Corresponding vehicle Global Navigation Satellite System locations and image coordinates are utilised to fit a direct transformation between image and ground plane coordinates. The proposed approach was validated with a research vehicle equipped with a Real-Time Kinematic-corrected Global Navigation Satellite System receiver driving past three different cameras. On average, the camera estimates contained errors ranging from 1.5 to 2.0 m, when compared to the Global Navigation Satellite System positions of the vehicle. Considering the vast lengths of the overlooked road sections, up to 140 m, the accuracy of the camera-based localisation should be adequate for a number of intelligent transportation applications. In future, the calibration approach should be evaluated with fusion of stand-alone Global Navigation Satellite System positioning and inertial measurements, to validate the calibration methodology with more common vehicle sensor equipment.

关键词： traffic engineering computing traffic cameras calibration methodology infrastructure camera calibration calibration smart cities camera-based localisation global navigation satellite system positions real-time kinematic-corrected global navigation satellite system receiver satellite navigation Measurement standards and calibration Optical, image and video signal processing computer vision and image processing techniques Control engineering computing ground plane coordinates Transportation administration image coordinates Traffic engineering computing automated calibration approach image processing vehicle localisation intelligent transportation applications Road-traffic system control intelligent transportation systems Smart cities Radionavigation and direction finding cameras research vehicle Global Positioning System connected vehicles vehicle global navigation satellite system locations smart city applications image sensors common vehicle sensor equipment road vehicles partially connected vehicle environments

来源：评论

学校读者我要写书评

暂无评论

LW-CovidNet: Automatic covid-19 lung infection detection from chest X-ray images

引用

IET image processing 2023年第2期17卷 362-374页

作者： Ahmed, Noor Tan, Xin Ma, Lizhuang Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Dept Comp Sci & Engn Shanghai Peoples R China

Coronavirus Disease 2019 (Covid-19) overtook the worldwide in early 2020, placing the world's health in threat. Automated lung infection detection using Chest X-ray images has a ton of potential for enhancing the traditional covid-19 treatment strategy. However, there are several challenges to detect infected regions from Chest X-ray images, including significant variance in infected features similar spatial characteristics, multi-scale variations in texture shapes and sizes of infected regions. Moreover, high parameters with transfer learning are also a constraints to deploy deep convolutional neural network(CNN) models in real time environment. A novel covid-19 lightweight CNN(LW-CovidNet) method is proposed to automatically detect covid-19 infected regions from Chest X-ray images to address these challenges. In our proposed hybrid method of integrating Standard and Depth-wise Separable convolutions are used to aggregate the high level features and also compensate the information loss by increasing the Receptive Field of the model. The detection boundaries of disease regions representations are then enhanced via an Edge-Attention method by applying heatmaps for accurate detection of disease regions. Extensive experiments indicate that the proposed LW-CovidNet surpasses most cutting-edge detection methods and also contributes to the advancement of state-of-the-art performance. It is envisaged that with reliable accuracy, this method can be introduced for clinical practices in the future.

关键词： traditional covid-19 treatment strategy Biology and medical computing feature extraction diseases X-ray imaging image classification disease regions representations medical computing automated lung infection detection chest X-ray images X-rays and particle beams (medical uses) Neural nets detection boundaries Chest X-ray images Optical, image and video signal processing computer vision and image processing techniques convolutional neural nets X-ray techniques: radiography and computed tomography (biomedical imaging/measurement) covid-19 infected regions deep learning (artificial intelligence) image recognition epidemics edge detection Automatic covid-19 lung infection detection diagnostic radiography cutting-edge detection methods Patient diagnostic methods and instrumentation medical image processing infected features similar spatial characteristics lung

来源：评论

学校读者我要写书评

暂无评论

Cross-modality person re-identification using hybrid mutual learning

引用

IET computer vision 2023年第1期17卷 1-12页

作者： Zhang, Zhong Dong, Qing Wang, Sen Liu, Shuang Xiao, Baihua Durrani, Tariq S. Tianjin Normal Univ Tianjin Key Lab Wireless Mobile Commun & Power Tr Tianjin Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Strathclyde Elect & Elect Engn Glasgow Lanark Scotland

Cross-modality person re-identification (Re-ID) aims to retrieve a query identity from red, green, blue (RGB) images or infrared (IR) images. Many approaches have been proposed to reduce the distribution gap between RGB modality and IR modality. However, they ignore the valuable collaborative relationship between RGB modality and IR modality. Hybrid Mutual Learning (HML) for cross-modality person Re-ID is proposed, which builds the collaborative relationship by using mutual learning from the aspects of local features and triplet relation. Specifically, HML contains local-mean mutual learning and triplet mutual learning where they focus on transferring local representational knowledge and structural geometry knowledge so as to reduce the gap between RGB modality and IR modality. Furthermore, Hierarchical Attention Aggregation is proposed to fuse local feature maps and local feature vectors to enrich the information of the classifier input. Extensive experiments on two commonly used data sets, that is, SYSU-MM01 and RegDB verify the effectiveness of the proposed method.

关键词： feature extraction local representational knowledge local features Sensor fusion image classification image representation query identity learning (artificial intelligence) RGB modality Algebra Machine learning (artificial intelligence) classifier input cross-modality person re-identification hierarchical attention aggregation image fusion computer vision and image processing techniques local feature vectors RegDB red green blue images infrared images image recognition cross-modality person Re-ID distribution gap SYSU-MM01 hybrid mutual learning triplet relation local-mean mutual learning triplet mutual learning infrared imaging image colour analysis structural geometry knowledge local feature maps image sensors IR modality vectors

来源：评论

学校读者我要写书评

暂无评论

A fine-to-coarse-to-fine weakly supervised framework for volumetric SD-OCT image segmentation

引用

IET computer vision 2023年第2期17卷 123-134页

作者： Niu, Sijie Xing, Ruiwen Gao, Xizhan Liu, Tingting Chen, Yuehui Univ Jinan Sch Informat Sci & Engn Jinan Peoples R China Shandong Prov Key Lab Network Based Intelligent C Jinan Peoples R China Shandong First Med Univ & Shandong Acad Med Sci Shandong Eye Inst Jinan Peoples R China

Obtaining accurate segmentation of central serous chorioretinopathy in spectral-domain optical coherence tomography (SD-OCT) is critical for the determination of the disease severity. Although existing methods achieve considerable segmentation results, they heavily depend on large-scale data with high-quality annotations. Also, the lesions bear a large shape variation across different patients, which are often difficult to encode. To address the above problems, we propose a fine-to-coarse-to-fine weakly supervised framework. Specifically, global alternate max-avg pooling (GTP) network can be employed to locate the lesion regions accurately by using only image-level annotations. A network module based on the GTP network and a semantic transfer module are proposed to iteratively guide the network to continuously discover and expand the target lesion regions. Then, we employ 3D grey distribution histogram to generate pseudo-volumetric labels. Finally, a novel 3D level set loss function is proposed to perform coarse-to-fine volumetric segmentation. Experiments on a challenging dataset demonstrate that the performance of our proposed method is closer to those of models trained with pixel-level supervision.

关键词： Biology and medical computing image segmentation diseases central serous chorioretinopathy Optical and laser radiation (medical uses) volumetric SD-OCT image segmentation coarse-to-fine volumetric segmentation Optical and laser radiation (biomedical imaging/measurement) biomedical optical imaging Optical, image and video signal processing computer vision and image processing techniques fine-to-coarse-to-fine weakly supervised framework spectral-domain optical coherence tomography eye global alternate max-avg pooling network considerable segmentation results Patient diagnostic methods and instrumentation optical tomography medical image processing image-level annotations

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

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

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：