检索结果-内蒙古大学图书馆

An Improved VGG-19 Network Induced Enhanced Feature Pooling for Precise Moving Object Detection in Complex Video Scenes

引用

IEEE ACCESS 2024年 12卷 45847-45864页

作者： Sahoo, Prabodh Kumar Panda, Manoj Kumar Panigrahi, Upasana Panda, Ganapati Jain, Prince Islam, Md. Shabiul Islam, Mohammad Tariqul Parul Univ Parul Inst Technol Dept Mechatron Vadodara 391760 Gujarat India GIET Univ Dept Elect & Commun Engn Rayagada 765022 Odisha India CV Raman Global Univ Dept Elect & Commun Bhubaneswar 752054 Odisha India Multimedia Univ Fac Engn FOE Cyberjaya 63100 Selangor Malaysia UKM Fac Engn & Built Environm Dept Elect Elect & Syst Engn Bangi 43600 Selangor Malaysia

Background subtraction is a crucial stage in many visual surveillance systems. The prime objective of any such system is to detect local changes, and the system could be utilized to face many real-life challenges. Most of the existing methods have addressed the problems of moderate and fast-moving object detection. However, very few literature have addressed the issues of slow moving object detection and these methods need further improvement to enhance the efficacy of detection. Hence, within this article, our significant endeavor involved identifying moving objects in challenging videos through an encoder-decoder architectural design, incorporating an enhanced VGG-19 model alongside a feature pooling framework. The proposed algorithm has various folds of novelties: a pre-trained VGG-19 architecture is modified and is used as an encoder with a transfer learning mechanism. The proposed model learns the weights of the improved VGG-19 model by a transfer-learning mechanism which enhances the model's efficacy. The proposed encoder is designed using a smaller number of layers to extract crucial fine and coarse scale features necessary for detecting the moving objects. The feature pooling framework (FPF) employed is a hybridization of a max-pooling layer, a convolutional layer, and multiple convolutional layers with distinct sampling rates to retain the multi-scale and multi-dimensional features at different scales. The decoder network consists of stacked convolution layers projecting from feature to image space effectively. The developed technique's efficacy is demonstrated against thirty-six state-of-the-art (SOTA) methods. The outcomes acquired by the developed technique are corroborated using subjective as well as objective analysis, which shows superior performance against other SOTA techniques. Additionally, the proposed model demonstrates enhanced accuracy when applied to unseen configurations. Further, the proposed technique (MOD-CVS) attained adequate efficiency

关键词： Object detection Feature extraction Videos Surveillance Visualization Transfer learning Lighting Artificial neural networks Encoding Deep neural network background subtraction transfer learning encoder-decoder architecture feature pooling framework

来源：评论

学校读者我要写书评

暂无评论

Adversarial learning-based skeleton synthesis with spatial-channel attention for robust gait recognition

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第1期82卷 1489-1504页

作者： Chen, Ying Xia, Shixiong Zhao, Jiaqi Zhou, Yong Niu, Qiang Yao, Rui Zhu, Dongjun Chen, Hao China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Jiangsu Peoples R China Minist Educ Engn Res Ctr Mine Digitizat Xuzhou 221116 Jiangsu Peoples R China Xuzhou Guanglian Technol Co Ltd Xuzhou 221116 Jiangsu Peoples R China

Person re-identification (ReID) aims to identify the same person across multiple cameras. Gait recognition is the person ReID using human gait to identify a walking person, which is an effective identification technology with many advantages, such as remote identification and without invasion. State-of-the-art solutions solve the problem of extensive annotation skeleton information and labeling process by employing encoder-decoders to reconstruct skeleton data, which encodes gait feature with a fixed-length vector limiting the performance of this architecture. In this paper, we propose an end-to-end pipeline dubbed as SCA-GAN, which assembles spatial-channel attention with GAN-like framework to synthesize skeleton sequences reversely without labeled skeleton data. A disadvantage of traditional encoder-decoder architecture is that, because of the fixed-length latent vector encoded from the encoder, the decoder fails to learn the reasonable standard to generate imperfect samples. Therefore, we design a GAN-like framework for discriminative gait feature extraction via adversarial learning. In addition, for learning the rich global information of skeleton data, the information of skeleton is extracted via convolutional block embedding locality-aware attention mechanism. Specifically, a contrastive feature loss is constructed between the gait encoder and the gait decoder to minimize their pixel-wise distance explicitly. The proof-of-principle experiments and ablation study on several benchmarks prove that the proposed method significantly outperforms gait recognition counterparts in precision.

关键词： Person re-identification Gait recognition encoder-decoder architecture Adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Automatic image captioning system based on augmentation and ranking mechanism

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2024年第1期18卷 265-274页

作者： Revathi, B. S. Kowshalya, A. Meena Govt Coll Technol Coimbatore India

Research on automatically producing syntactically and semantically accurate captions is still an open challenge. This paper proposes an effective pretrained Augmentation-Ranking (A-R) Image Captioning model. The proposed model improves the properties of the images and produces appropriate captions. The employed novel augmentation strategy improves convolution neural network (CNN) operation, while Ranking and Feedback Propagation improve Long Short-Term Memory (LSTM). Our proposed model seeks to address the issues of complexity, vanishing gradients and context during training. The proposed A-R model improves the performance of LSTM and CNN. The image dataset for training is expanded using the augmented CNN. Through ranks, the Ranking LSTM aids in the identification of the semantic captions. This blending method enhances the working of image captioning system. Utilizing greedy and beam search, the proposed A-R model is examined under maximum and average pooling. The outcomes are compared with cutting-edge models such as the bidirectional recurrent neural network, Google NIC and Bi-LSTM combined with semantic attention mechanism. The proposed model is assessed using the Flickr 8 k and Flickr 30 k dataset and assessed using measures including BLEU, METEOR and CIDER. The proposed model with reduced complexity generated captions deemed accurate, syntactically correct and semantically correct by achieving an accuracy of 74.87% above all baseline models, according to experimental results.

关键词： Image captioning Deep neural network encoder-decoder architecture Ranking LSTM

来源：评论

学校读者我要写书评

暂无评论

BIPOOLNET: An advanced UNet architecture for enhanced lane detection in autonomous vehicles

引用

INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS 2024年第2期18卷 743-757页

作者： Santhiya, P. Jebadurai, Immanuel JohnRaja Paulraj, Getzi Jeba Leelipushpam Jenefa, A. Karunya Inst Technol & Sci Sch Comp Sci & Tech Coimbatore Tamil Nadu India

In the rapidly evolving landscape of autonomous vehicle technology, the imperative to bolster safety within smart urban ecosystems has never been more critical. This endeavor requires the deployment of advanced detection systems capable of navigating the intricacies of pedestrian, near-vehicle, and lane detection challenges, with a particular focus on the nuanced requirements of curved lane navigation - a domain where traditional AI models exhibit notable deficiencies. This paper introduces BIPOOLNET, an innovative encoder-decoder neural architecture, ingeniously augmented with a feature pyramid to facilitate the precise delineation of curved lane geometries. BIPOOLNET integrates max pooling and average pooling to extract critical features and mitigate the complexity of the feature map, redefining the benchmarks for lane detection technology. Rigorous evaluation using the TuSimple dataset underscores BIPOOLNET's exemplary performance, evidenced by an unprecedented accuracy rate of 98.45%, an F1-score of 98.17%, and notably minimal false positive (1.84%) and false negative (1.09%) rates. These findings not only affirm BIPOOLNET's supremacy over extant models but also signal a paradigm shift in enhancing the safety and navigational precision of autonomous vehicles, offering a scalable, robust solution to the multifaceted challenges posed by real-world driving dynamics.

关键词： Lane detection autonomous vehicles encoder-decoder architecture feature pyramid enhancement BIPOOLNET

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach for regional-scale fine-resolution disaster impact prediction under tropical cyclones

引用

NATURAL HAZARDS 2024年第8期120卷 7461-7479页

作者： Lin, Peihui Wang, Naiyu Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China

Tropical cyclones (TCs) pose a significant threat to coastal regions worldwide, demanding accurate and timely predictions of potential disaster impacts. Existing regional-scale impact prediction models, however, are largely limited by the sparsity of modeling data and incapability of fine-resolution predictions in a computationally efficient manner, thus hindering real-time identification of potential disaster hotspots. To address these limitations, we present a data-driven image-to-image TC impact prediction model based on a deep convolutional neural network (CNN) for Zhejiang Province, China, an area of approximately 105,000 km2 consisting of 90 counties. The proposed model utilizes twelve carefully selected predictors, including hazard, environmental and vulnerability factors, which are processed into province-scale 1 km-grid image-format data. An end-to-end encoder-decoder architecture is subsequently designed to extract impact-relevant spatial features from the multi-channel input images, then to construct a spatial impact map of identical size (i.e., \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\sim}105,000$$\end{document} km2) and resolution (i.e.,1 km-grid). This gridded impact map is then aggregated spatially to derive county-level impact predictions, which serve as the final layer of the CNN model and are used to evaluate the model's loss function in terms of mean squared error. This design is informed by the fact that the training data on TC impact, collected from historical events, were recorded at county level. Validation and error analysis demonstrate the model's promising spatial accuracy and time efficacy. Furthermore, an illustration of the model's application with Typhoon Lekima in 2019 underscores its potential for integrating meteorological forecasts to achieve re

关键词： Tropical cyclone Convolutional neural network (CNN) encoder-decoder architecture Fine-resolution prediction Regional impact Resilience

来源：评论

学校读者我要写书评

暂无评论

MPOCSR: optical chemical structure recognition based on multi-path Vision Transformer

引用

COMPLEX & INTELLIGENT SYSTEMS 2024年第6期10卷 7553-7563页

作者： Lin, Fan Li, Jianhua East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China

Optical chemical structure recognition (OCSR) is a fundamental and crucial task in the field of chemistry, which aims at transforming intricate chemical structure images into machine-readable formats. Current deep learning-based OCSR methods typically use image feature extractors to extract visual features and employ encoder-decoder architectures for chemical structure recognition. However, the performance of these methods is limited by their image feature extractors and the class imbalance of elements in chemical structure representation. This paper proposes MPOCSR (multi-path optical chemical structure recognition), which introduces the multi-path Vision Transformer (MPViT) and the class-balanced (CB) loss function to address these two challenges. MPOCSR uses MPViT as an image feature extractor, combining the advantages of convolutional neural networks and Vision Transformers. This strategy enables the provision of richer visual information for subsequent decoding processes. Furthermore, MPOCSR incorporates CB loss function to rebalance the loss weights among different categories. For training and validation of our method, we constructed a dataset that includes both Markush and non-Markush structures. Experimental results show that MPOCSR achieves an accuracy of 90.95% on the test set, surpassing other existing methods.

关键词： Optical chemical structure recognition Deep learning Multi-path Vision Transformer encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

A contrastive triplet network for automatic chest X-ray reporting

引用

NEUROCOMPUTING 2022年 502卷 71-83页

作者： Yang, Yan Yu, Jun Jiang, Hanliang Han, Weidong Zhang, Jian Jiang, Wei Hangzhou Dianzi Univ Sch Comp Sci & Technol Key Lab Complex Syst Modeling & Simulat Hangzhou 310018 Peoples R China Zhejiang Univ Coll Med Reg Med Ctr Natl Inst Resp DisSir Run Run Shaw Hosp Hangzhou 310016 Peoples R China Zhejiang Univ Sir Run Run Shaw Hosp Coll Med Dept Med Oncol Hangzhou 310016 Peoples R China Zhejiang Int Studies Univ Sch Sci & Technol Hangzhou 310023 Peoples R China

Chest X-ray reporting aims at generating linguistic descriptions automatically for chest X-ray images, in which accurate detection and description of abnormalities are essential. However, the seriously biased data distribution (e.g., the normal cases usually dominate the whole dataset over abnormal cases) causes huge challenges for the data-driven neural models to generate satisfied abnormality descriptions. To this end, we propose a contrastive triplet network (CTN) built on the Transformer architecture for automatic chest X-ray reporting to alleviate the data-bias problem. Our CTN effectively enhances abnormalities by comparing visual and semantic information between normal and abnormal cases using a triplet network. Specifically, triplets including normal and abnormal cases are first constructed. Then, visual tokens of the chest X-ray are extracted and fed to the Transformer to generate an associated report. During training, comparisons between normal and abnormal cases are conducted via contrasting: 1) the visual embedding of the chest X-ray image encoded by the Transformer encoder, and 2) the semantic embedding of the generated report encoded by a pre-trained textual encoder. Comprehensive experiments on two publicly-available databases have shown the good performance of our method. (C) 2022 Published by Elsevier B.V.

关键词： Chest X-ray report generation Data bias Triplet network Contrastive learning Transformer Textual encoder encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

OverSegNet: A convolutional encoder-decoder network for image over-segmentation

引用

COMPUTERS & ELECTRICAL ENGINEERING 2023年第1期107卷

作者： Li, Peng Ma, Wei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes a fully convolutional deep network, named OverSegNet, for image over-segmentation. OverSegNet consists of an encoder and a decoder, which are designed for the two core parts of over-segmentation, i.e., feature representation and pixel-superpixel association, respectively. To obtain edge -sensitive and noise-insusceptible feature representation, the encoder is endowed with rich over-segmentation-specific convolutional kernels via over-parametrization followed by task -driven neural network search (NAS). The decoder adopts a multi-scale convolutional structure with cross-large-scale connections, to achieve pixel-superpixel association in a coarse-to-fine feed-forward manner while eliminating accumulation errors. We conduct rich ablation studies to verify the effectiveness of the specially designed encoder and decoder. Experiments on both the BSDS500 dataset and NYUv2 dataset show that the proposed OverSegNet is fast, obtains state-of-the-art accuracy and has good generalization ability. Using semantic segmentation and disparity estimation as examples, we also verify the proposed OverSegNet in downstream applications.

关键词： Image over-segmentation Superpixel segmentation encoder-decoder architecture NAS encoder Non-iterative deep clustering

来源：评论

学校读者我要写书评

暂无评论

Automatic delamination segmentation for bridge deck based on encoder-decoder deep learning through UAV-based thermography

引用

NDT & E INTERNATIONAL 2020年 116卷 102341-102341页

作者： Cheng, Chongsheng Shang, Zhexiong Shen, Zhigang Univ Nebraska Durham Sch Architectural Engn & Construct 122 NH Lincoln NE 68588 USA Univ Nebraska Durham Sch Architectural Engn & Construct 113 NH Lincoln NE 68588 USA

Concrete deck delamination often demonstrates strong variations in size, shape, and temperature distribution under the influences of outdoor weather conditions. The strong variations create challenges for pure analytical solutions in infrared image segmentation of delaminated areas. The recently developed supervised deep learning approach demonstrated the potentials in achieving automatic segmentation of RGB images. However, its effectiveness in segmenting thermal images remains under-explored. The main challenge lies in the development of specific models and the generation of a large range of labeled infrared images for training. To address this challenge, a customized deep learning model based on encoder-decoder architecture is proposed to segment the delaminated areas in thermal images at the pixel level. Data augmentation strategies were implemented in creating the training data set to improve the performance of the proposed model. The deep learning generated model was deployed in a real-world project to further evaluate the model's applicability and robustness. The results of these experimental studies supported the effectiveness of the deep learning model in segmenting concrete delamination areas from infrared images. It also suggested that data augmentation is a helpful technique to address the small size issue of training samples. The field test with validation further demonstrated the generalizability of the proposed framework. Limitations of the proposed approach were also briefed at the end of the paper.

关键词： Concrete delamination Thermography Nondestructive evaluation Deep learning encoder-decoder architecture Semantic segmentation UAV

来源：评论

学校读者我要写书评

暂无评论

Diverter transformer-based multi-encoder-multi-decoder network model for medical retinal blood vessel image segmentation

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 93卷

作者： Wu, Chengwei Guo, Min Ma, Miao Wang, Kaiguang Shaanxi Normal Univ Sch Comp Sci Minist Educ Key Lab Modern Teaching Technol Xian 710119 Peoples R China

The retinal blood vessel is an essential part of the fundus structure. It is important to accurately analyze the structure and distribution of retinal vessels, which can help make accurate medical diagnoses. However, it is still challenging to extract detailed information due to the problems of fuzzy edges, low resolution, and lots of noise in retinal blood vessel medical images. To extract the image detail information effectively, we propose a new diverter transformer -based multi -encoder -multi -decoder network model in this paper. The network model consists of a feature encoder module and a feature decoder module. Among them, the feature encoding module consists of a diverter transformer with a diverter adaptive mechanism, three encoder units with a convolution layer and max -pooling layer, and the two decoder units in the feature decoding module consist of an inverse convolution layer and an up -sampling layer, respectively. The Local Context Module (LCNet Module) in the feature encoding module learns richer local context feature information layer by layer through changing the width of the network while downsampling;the Global encoder Module1 (G -encoder Module1) and the Global encoder Module2 (G -encoder Module2) extract the global feature representation of retinal blood vessel images by performing a max -pooling operation to transform the input data into a vector of fixed dimensions, thus helping the network model to better understand and extract the global feature representation of retinal blood vessel images. The two decoder units in the feature decoding module receive local and global feature information from three encoder units, LCNet Module, G -encoder Module1 and G -encoder Module2, respectively. decoder Module1 generates segmentation prediction by layer -by -layer up -sampling operation, and decoder Module2 recovers the feature information by downsampling and decoding operations and fuses the recovered feature information to output, obtaining the final

关键词： Medical image processing encoder-decoder architecture Local context Retinal vessel segmentation

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：