检索结果-内蒙古大学图书馆

GridNet-3d: A Novel Real-Time 3d Object detection Algorithm Based on Point Cloud

Chinese Journal of Electronics 2021年第5期30卷 931-939页

作者： YUE Yuanchen CAI Yunfei WANG dongsheng School of Computer Science and Engineering Nanjing University of Science and Technology

3d object detection based on point cloud has an important application prospect in automatic driving technology. Aiming at the low precision of 3d object detection based on point cloud and the poor real-time performance caused by large numbers of 3d convolutions, a novel end-to-end real-time object detection algorithm named GridNet-3d is proposed. In the work, 2d gridmapping is used to preprocess the original point *** a novel structure grid encoding layer is adopted to encode point cloud features and is gotten grid feature maps in bird's eye view which is connected to region proposal network module to generate detections. despite only using point clouds, the results on the KITTI 3d detection benchmark show that our algorithm has higher detection precision and better real-time performance on the detection of cars, pedestrians and cyclists, which has high practical value.

关键词： GridNet-3d point cloud features region proposal network module structure grid encoding layer grid feature maps 2d gridmapping intelligent transportation systems end-to-end real-time object detection algorithm KITTI 3d detection benchmark feature extraction automatic driving technology object detection 3d convolution

来源：评论

学校读者我要写书评

暂无评论

GFNet: gated fusion network for video saliency prediction

引用

APPLIEd INTELLIGENCE 2023年第22期53卷 27865-27875页

作者： Wu, Songhe Zhou, Xiaofei Sun, Yaoqi Gao, Yuhan Zhu, Zunjie Zhang, Jiyong Yan, Chenggang Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Hangzhou Dianzi Univ Lishui Inst Hangzhou 310018 Peoples R China Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310018 Peoples R China

Most of the cutting-edge 3d convolutional-based video saliency prediction models adopt a fully convolutional encoder-decoder architecture, which provides a good spatiotemporal representation of salient regions. However, the spatiotemporal cues of the saliency models will be continuously diluted during the decoding process, leading to a decreased ability to locate salient regions. To address this limitation, we propose a simple and effective gated fusion network (GFNet) to conduct video saliency prediction. Specifically, GFNet is built on a fully 3d convolutional encoder-decoder architecture and consists of a key component named the gated fusion (GF) module, which acts as a message screening unit between each level encoder and decoder features. In the GF module, the gate can be obtained via the combination of features from the previous decoder block and the current encoder block, which is employed to weight the encoder features. In this way, GFNet can control the message passing between each level encoder and decoder block. Extensive experimental results on four video saliency datasets show that our method achieves comparable performance against state-of-the-art models. The code is available at https://***/wusonghe/GFNet.

关键词： 3d convolution Video saliency prediction Spatiotemporal information Gated fusion

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution for Hyperspectral Remote Sensing Images Based on the 3d Attention-SRGAN Network

引用

REMOTE SENSING 2020年第7期12卷 1204-1204页

作者： dou, Xinyu Li, Chenyu Shi, Qian Liu, Mengxi Sun Yat Sen Univ Sch Geog & Planning Guangdong Key Lab Urbanizat & Geoslimulat Guangzhou 510275 Peoples R China

Hyperspectral remote sensing images (HSIs) have a higher spectral resolution compared to multispectral remote sensing images, providing the possibility for more reasonable and effective analysis and processing of spectral data. However, rich spectral information usually comes at the expense of low spatial resolution owing to the physical limitations of sensors, which brings difficulties for identifying and analyzing targets in HSIs. In the super-resolution (SR) field, many methods have been focusing on the restoration of the spatial information while ignoring the spectral aspect. To better restore the spectral information in the HSI SR field, a novel super-resolution (SR) method was proposed in this study. Firstly, we innovatively used three-dimensional (3d) convolution based on SRGAN (Super-Resolution Generative Adversarial Network) structure to not only exploit the spatial features but also preserve spectral properties in the process of SR. Moreover, we used the attention mechanism to deal with the multiply features from the 3d convolution layers, and we enhanced the output of our model by improving the content of the generator's loss function. The experimental results indicate that the 3dASRGAN (3d Attention-based Super-Resolution Generative Adversarial Network) is both visually quantitatively better than the comparison methods, which proves that the 3dASRGAN model can reconstruct high-resolution HSIs with high efficiency.

关键词： hyperspectral image 3d convolution generative adversarial networks super-resolution spectral angle

来源：评论

学校读者我要写书评

暂无评论

Video prediction: a step-by-step improvement of a video synthesis network

引用

APPLIEd INTELLIGENCE 2022年第4期52卷 3640-3652页

作者： Jing, Beibei ding, Hongwei Yang, Zhijun Li, Bo Bao, Liyong Yunnan Univ Sch Informat Sci & Engn Kunming 650000 Yunnan Peoples R China

Although focusing on the field of video generation has made some progress in network performance and computational efficiency, there is still much room for improvement in terms of the predicted frame number and clarity. In this paper, a depth learning model is proposed to predict future video frames. The model can predict video streams with complex pixel distributions of up to 32 frames. Our framework is mainly composed of two modules: a fusion image prediction generator and an image-video translator. The fusion picture prediction generator is realized by a U-Net neural network built by a 3d convolution, and the image-video translator is composed of a conditional generative adversarial network built by a 2d convolution network. In the proposed framework, given a set of fusion images and labels, the image picture prediction generator can learn the pixel distribution of the fitted label pictures from the fusion images. The image-video translator then translates the output of the fused image prediction generator into future video frames. In addition, this paper proposes an accompanying convolution model and corresponding algorithm for improving image sharpness. Our experimental results prove the effectiveness of this framework.

关键词： Video generation Fusion image prediction generator Image-video translator 3d convolution Conditional generative adversarial nets 2d convolution network

来源：评论

学校读者我要写书评

暂无评论

deep Learning-Based Standard Sign Language discrimination

引用

IEEE ACCESS 2023年 11卷 125822-125834页

作者： Zhang, Menglin Yang, Shuying Zhao, Min Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China Minist Educ Key Lab Comp Vis & Syst Tianjin 300384 Peoples R China

General sign language recognition models are only designed for recognizing categories, i.e., such models do not discriminate standard and nonstandard sign language actions made by learners. It is inadequate to use in a sign language education software. To address this issue, this paper proposed a sign language category and standardization correctness discrimination model for sign language education. The proposed model is implemented with a hand detection and standard sign language discrimination method. For hand detection, the proposed method utilizes flow-guided features and acquires relevant proposals using stable and flow key frame detections. This model can resolve the inconsistency between the forward optical flow and the box center point offset. In addition, the proposed method employs an encoder-decoder model structure for sign language correctness discrimination. The encoder model combines 3d convolution and 2d deformable convolution results with residual structures, and it implements a sequence attention mechanism. A Sign Language Correctness discrimination dataset (SLCd dataset) was also constructed in this study. In this dataset, each sign language video has two recognition labels, i.e., sign language category and standardization category. The semi-supervised learning method was employed to generate pseudo hand position labels. The hand detection model was getting sufficiently high hand detection result. The sign language correctness discrimination model was tested with hand patches or full images. SLCd dataset is available at https://***/10.21227/p9sn-dz70.

关键词： Sign language Encoding Video coding Object detection Three-dimensional displays convolution Gesture recognition Assistive technologies Semisupervised learning Educational courses Software packages Continuous sign language recognition encoder-decoder tubelet video object detection 3d convolution

来源：评论

学校读者我要写书评

暂无评论

AGARNet: Adaptively Gated JPEG Compression Artifacts Removal Network for a Wide Range Quality Factor

引用

IEEE ACCESS 2020年 8卷 20160-20170页

作者： Kim, Yoonsik Soh, Jae Woong Cho, Nam Ik Seoul Natl Univ Dept Elect & Comp Engn INMC Seoul 08826 South Korea

Most of existing compression artifacts reduction methods focused on the application for low-quality images and usually assumed a known compression quality factor. However, images compressed with high quality should also be manipulated because even small artifacts become noticeable when we enhance the compressed image. Also, the use of quality factor from the decoder is not practical because there are too many recompressed or transcoded images whose quality factor are not reliable and spatially varying. To address these issues, we propose a quality-adaptive artifacts removal network based on the gating scheme, with a quality estimator that works for a wide range of quality factor. Specifically, the estimator gives a pixel-wise quality factor, and our gating scheme generates gate-weights from the quality factor. Then, the gate-weights control the magnitudes of feature maps in our artifacts removal network. Thus, our gating scheme guarantees the proposed network to perform adaptively without changing the parameters according to the change of quality factor. Moreover, we exploit the discrete Cosine Transform (dCT) scheme with 3d convolution for capturing both spatial and frequency dependencies of images. Experiments show that the proposed network provides better performance than the state-of-the-art methods over a wide range of quality factor. Also, the proposed method provides robust results in real-world scenarios such as the manipulation of transcoded images and videos.

关键词： Compression artifacts removal recompression adaptive network convolutional neural network (CNN) dCT network 3d convolution

来源：评论

学校读者我要写书评

暂无评论

PMSNet: Parallel Multi-Scale Network for Accurate Low-Light Light-Field Image Enhancement

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2024年 26卷 2041-2055页

作者： Wang, Xingzheng Chen, Kaiqiang Wang, Zixuan Huang, Wenhao Shenzhen Univ Coll Mechatron & Control Engn Shenzhen 518060 Peoples R China

Current low-light light-field (LF) image enhancement algorithms tend to produce blurry results, for (1) loss of spatial details during enhancement and (2) inefficient exploitation of angular correlations, which helps to recover spatial details. Therefore, in this article, we propose a parallel multi-scale network (PMSNet), which attempts to (1) process features of different scales in parallel to aggregate the different contributions of multi-scale features at each layer, thus fully preserve spatial details, and (2) integrate multi-resolution 3d convolution streams to efficiently utilize angular correlations. Specifically, PMSNet consists of three stages: Stage-I employs multi-scale modules (MSMs) to generate local understanding with the aid of adjacent views. Notably, MSM retains high-resolution feature extraction to minimize loss of spatial details. Stage-II processes all views to encode global information. Based on the above extracted local and global information, Stage-III utilizes 3d multi-scale modules (3d-MSMs) to efficiently exploit angular correlations. To validate our idea, we comprehensively evaluate the performance of PMSNet on three publicly available datasets. Experimental results show that our method is superior to the current state-of-the-art methods, achieving an average PSNR of 24.76 dB.

关键词： Correlation Feature extraction convolution Spatial resolution Image reconstruction Three-dimensional displays Lighting Low-light light field image enhancement Parallel multi-scale 3d convolution

来源：评论

学校读者我要写书评

暂无评论

d³-LNd: A two-stream framework with discriminant deep descriptor, linear CMdT and nonlinear KCMdT descriptors for action recognition

引用

NEUROCOMPUTING 2019年 325卷 90-100页

作者： Tong, Ming Zhao, Mengao Chen, Yiran Wang, Houyi Xidian Univ Sch Elect Engn Xian 710071 Shaanxi Peoples R China

In order to improve recognition accuracy, a two-stream framework which incorporates deep-learned stream and hand-crafted stream is proposed. Firstly, a discriminant nonlinear feature fusion method is proposed, which introduces the category structure information and obtains the nonlinear relationships between features. Secondly, the global features and local features are extracted from deep network, both of them are fused by the proposed fusion method to obtain a discriminant deep descriptor. Thirdly, to capture the spatio-temporal characteristics of video, the temporal derivatives of gradient, optical flow and motion boundary are extracted in the space-time cube centered at trajectory and taken as low-level features. Subsequently, the covariance and kernelized covariance of low-level features are respectively computed to obtain the Covariance Matrix based on dense Trajectory (CMdT) and Kernelized Covariance Matrix based on dense Trajectory (KCMdT) descriptors. Finally, a two-stream framework with discriminant deep descriptor, linear CMdT and nonlinear KCMdT descriptors (d-3-LNd) is presented, which shares the benefits of both deep-learned and hand-crafted features, and further improves recognition accuracy. Experiments on challenging HMdB51 and UCF101 datasets verify the effectiveness of our method. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Action recognition Two-stream framework Feature fusion 3d convolution Spatio-temporal feature

来源：评论

学校读者我要写书评

暂无评论

Recognition of Motor Imagery EEG Signals Based on Capsule Network

引用

IEEE ACCESS 2023年 11卷 31262-31271页

作者： du, Xiuli Kong, Meiya Qiu, Shaoming Guo, Jiangyu Lv, Yana Dalian Univ Commun & Network Lab Dalian Peoples R China Dalian Univ Sch Informat Engn Dalian 116622 Peoples R China North Automat Control Technol Inst Taiyuan Shanxi Peoples R China

In order to fully extract the temporal and spatial features contained in motor imagery electroencephalography (EEG) signals for effective identification of motor imagery, a three-dimensional capsule network (3d-CapsNet) EEG signal recognition model is proposed, which can integrate the MI-EEG temporal dimension, channel spatial dimension and the intrinsic relationship between features to maximize the feature representation capability. Firstly, a multi-layer 3d convolution module is used to extract features in the time and inter-channel space dimensions as the low-level features. Secondly, advanced spatial features are also obtained through capsule network integration. Finally, dynamic routing connections and squash functions are applied for classification. The experimental analysis is conducted on the BCI competition IV dataset 2a. The proposed model performs well on all the subjects' datasets, such that the average accuracy and average Kappa value of 9 subjects are 84.028% and 0.789, respectively. The experimental results confirm effectiveness of the proposed method. Additionally, accuracy of the four-class classification is improved, and the impact of individual variability is overcome to a certain extent.

关键词： Electroencephalography Feature extraction Three-dimensional displays Heuristic algorithms Routing Electrodes convolution motor imagery 3d convolution capsule network individual differences

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Feature Hierarchy-Based Blind Prediction of Natural Video Quality via Transfer Learning

引用

IEEE TRANSACTIONS ON BROAdCASTING 2023年第1期69卷 130-143页

作者： Xian, Weizhi Zhou, Mingliang Fang, Bin Liao, Xingran Ji, Cheng Xiang, Tao Jia, Weijia Chongqing Univ Sch Comp Sci Chongqing 400044 Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Beijing Normal Univ BNU UIC Inst Artificial Intelligence & Future Net Zhuhai 519088 Peoples R China BNU HKBU United Int Coll Guangdong Key Lab AI Multi Modal Data Proc Zhuhai 519087 Guangdong Peoples R China

In this paper, we propose a pyramidal spatiotemporal feature hierarchy (PSFH)-based no-reference (NR) video quality assessment (VQA) method using transfer learning. First, we generate simulated videos by a generative adversarial network (GAN)-based image restoration model. The residual maps between the distorted frames and simulated frames, which can capture rich information, are utilized as one input of the quality regression network. Second, we use 3d convolution operations to construct a PSFH network with five stages. The spatiotemporal features incorporating the shared features transferred from the pretrained image restoration model are fused stage by stage. Third, with the guidance of the transferred knowledge, each stage generates multiple feature mapping layers that encode different semantics and degradation information using 3d convolution layers and gated recurrent units (GRUs). Finally, five approximate perceptual quality scores and a precise prediction score are obtained by fully connected (FC) networks. The whole model is trained under a finely designed loss function that combines pseudo-Huber loss and Pearson linear correlation coefficient (PLCC) loss to improve the robustness and prediction accuracy. According to the extensive experiments, outstanding results can be obtained compared with other state-of-the-art methods. Both the source code and models are available ***://***/WeizhiXian/PSFHNRVQA

关键词： Three-dimensional displays Spatiotemporal phenomena Quality assessment Transfer learning distortion Image restoration Feature extraction Video quality assessment pyramidal spatiotemporal feature transfer learning 3d convolution generative adversarial network

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：