检索结果-南通市图书馆

Neighborhood co-occurrence modeling in 3D point cloud segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第2期8卷 303-315页

作者： Jingyu Gong Zhou Ye Lizhuang Ma Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Shanghai CLS Fintech Co. LTDShanghai 200030China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong UniversityShanghai 200240China

A significant performance boost has been achieved in point cloud semantic segmentation by utilization of the encoder-decoder architecture and novel convolution operations for point ***,co-occurrence relationships within a local region which can directly influence segmentation results are usually ignored by current *** this paper,we propose a neighborhood co-occurrence matrix(NCM)to model local co-occurrence relationships in a point *** generate target NCM and prediction NCM from semantic labels and a prediction map ***,Kullback-Leibler(KL)divergence is used to maximize the similarity between the target and prediction NCMs to learn the co-occurrence ***,for large scenes where the NCMs for a sampled point cloud and the whole scene differ greatly,we introduce a reverse form of KL divergence which can better handle the difference to supervise the prediction *** integrate our method into an existing backbone and conduct comprehensive experiments on three datasets:semantic3D for outdoor space segmentation,and S3DIS and ScanNet v2 for indoor scene *** indicate that our method can significantly improve upon the backbone and outperform many leading competitors.

关键词： 3D vision point cloud co-occurrence relation modeling semantic segmentation

Causal reasoning in typical computer vision tasks

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第1期67卷 105-120页

作者： ZHANG KeXuan SUN QiYu ZHAO ChaoQiang TANG Yang Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air based Information Perception and Fusion Luoyang 471000China Luoyang Institute of Electro Optical Equipment of Avic Luoyang 471000China

Deep learning has revolutionized the field of artificial *** on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing *** being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled *** the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious *** a result,researchers are now trying to enhance deep learningbased methods with causal *** theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious *** paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image *** advantages of causality and the approaches for building causal paradigms will be *** roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

关键词： causal reasoning computer vision tasks vision-language tasks semantic segmentation object detection

同方期刊数据库

Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2022年第3期33卷 923-936页

作者： Chong Zhang Li Zhang Bessie Y.J.Zhang Jingqian Sun Shikui Dong Xueyan Wang Yaxin Li Jian Xu Wenkai Chu Yanwei Dong Pei Wang College of Science Beijing Forestry UniversityBeijing100083People’s Republic of China College of Grassland Science Beijing Forestry UniversityBeijing100083People’s Republic of China Xing’an League Grassland Workstation Inner Mongolia Autonomous Region137400People’s Republic of China Mathematical and Computational Science Department Stanford UniversityStanfordCA94305USA

Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. semantic segmentation normally excels in medical and building classification, but its usefulness in mixed forest-grassland ecosystems in semi-arid to semi-humid climates is unknown. This study proposes a new semantic segmentation network of LResU-net in which residual convolution unit (RCU) and loop convolution unit (LCU) are added to the U-net framework to classify images of different land covers generated by UAV high resolution. The selected model enhanced classification accuracy by increasing gradient mapping via RCU and modifying the size of convolution layers via LCU as well as reducing convolution kernels. To achieve this objective, a group of orthophotos were taken at an altitude of 260 m for testing in a natural forest-grassland ecosystem of Keyouqianqi, Inner Mongolia, China, and compared the results with those of three other network models (U-net, ResU-net and LU-net). The results show that both the highest kappa coefficient (0.86) and the highest overall accuracy (93.7%) resulted from LResU-net, and the value of most land covers provided by the producer’s and user’s accuracy generated in LResU-net exceeded 0.85. The pixel-area ratio approach was used to calculate the real areas of 10 different land covers where grasslands were 67.3%. The analysis of the effect of RCU and LCU on the model training performance indicates that the time of each epoch was shortened from U-net (358 s) to LResU-net (282 s). In addition, in order to classify areas that are not distinguishable, unclassified areas were defined and their impact on classification. LResU-net generated significantly more accurate results than the other three models and was regarded as the most appropriate approach to classify land cover in mixed forest-grassland ecosystems.

关键词： UAV images semantic segmentation LResU-net Land cover classification

Preserving details in semantics-aware context for scene parsing

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第2期63卷 79-92页

作者： Shuai MA Yanwei PANG Jing PAN Ling SHAO Tianjin Key Laboratory of Brain-Inspired Intelligence Technology School of Electrical and Information EngineeringTianjin University School of Electronic Engineering Tianjin University of Technology and Education

Great success of scene parsing(also known as, semantic segmentation) has been achieved with the pipeline of fully convolutional networks(FCNs). Nevertheless, there are a lot of segmentation failures caused by large similarities between local appearances. To alleviate the problem, most of existing methods attempt to improve the global view of FCNs by introducing different contextual modules. Though the reconstructed high resolution output of these methods is of rich semantics, it cannot faithfully recover the fine image details owing to lack of desired precise low-level information. To overcome the problem, we propose to improve the spatial decoding process through embedding possibly lost low-level information in a principled way. To this end, we make the following three contributions. First, we propose a semantics conformity module to make low-level features variations agnostic. Second, we introduce semantics into the conformed low level features through guidance from semantically aware features. Finally, we institute the availability of various possible contextual features at feature fusion to enrich context information. The proposed approach demonstrates competitive performance on challenging PASCAL VOC 2012, Cityscapes,and ADE20K benchmarks in comparison to the state-of-the-art methods.

关键词： fully convolutional networks semantic segmentation cityscapes semantic-aware context

Feature context learning for human parsing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第12期62卷 6-19页

作者： Tengteng HUANG Yongchao XU Song BAI Yongpan WANG Xiang BAI School of Electronic Information and Communications Huazhong University of Science and Technology Alibaba Group

Parsing inconsistency, referring to the scatters and speckles in the parsing results as well as imprecise contours, is a long-standing problem in human parsing. It results from the fact that the pixel-wise classification loss independently considers each pixel. To address the inconsistency issue, we propose in this paper an end-to-end trainable, highly flexible and generic module called feature context module(FCM).FCM explores the correlation of adjacent pixels and aggregates the contextual information embedded in the real topology of the human body. Therefore, the feature representations are enhanced and thus quite robust in distinguishing semantically related parts. Extensive experiments are done with three different backbone models and four benchmark datasets, suggesting that FCM can be an effective and efficient plug-in to consistently improve the performance of existing algorithms without sacrificing the inference speed too much.

关键词： human parsing context learning fully convolutional networks graph convolutional network semantic segmentation

DSN-BR-Based Online Inspection Method and Application for Surface Defects of Pharmaceutical Products in Aluminum-Plastic Blister Packages

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2024年第4期37卷 194-214页

作者： Mingzhou Liu Yu Gong Xiaoqiao Wang Conghu Liu Jing Hu School of Mechanical Engineering Hefei University of TechnologyHefei 230009China School of Mechanical and Electronic Engineering Suzhou UniversitySuzhou 234000China

Ensuring high product quality is of paramount importance in pharmaceutical drug manufacturing,as it is subject to rigorous regulatory *** study presents a research focused on the development of an on-line detection method and system for identifying surface defects in pharmaceutical products packaged in aluminum-plastic ***,the aluminum-plastic blister packages exhibit multi-scale features and inter-class *** address this,the deep semantic network with boundary refinement(DSN-BR)model is proposed,which leverages semantic segmentation domain knowledge,to accurately segment the defects in pixel ***,a specialized image acquisition module that minimizes the impact of ambient light is established,ensuring high-quality image ***,the image acquisition module,image detection module,and data management module are designed to construct a comprehensive online surface defect detection *** validate the effectiveness of our approach,we employ a real dataset for instance verification on the implemented *** experimental results substantiate the outstanding performance of the DSN-BR,achieving the mean intersection over union(MIoU)of 90.5%.Furthermore,the proposed system achieves an inference speed of up to 14.12 f/s,while attaining an F1-Score of 98.25%.These results demonstrate that the system meets the actual needs of the enterprise and provides theoretical and methodological support for intelligent inspection of product surface *** standardizing the control process of pharmaceutical manufacturing and improving the management capability of the manufacturing process,our approach holds significant market application prospects.

关键词： Surface defect detection system Deep learning semantic segmentation Aluminum-plastic blister packages identification

Irregular scene text detection via attention guided border labeling

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第12期62卷 33-43页

作者： Jie CHEN Zhouhui LIAN Yizhi WANG Yingmin TANG Jianguo XIAO Wangxuan Institute of Computer Technology Peking University Center For Chinese Font Design and Research Peking University

Scene text detection plays an important role in many computer vision applications. With the help of recent deep learning techniques, multi-oriented text detection that was considered to be quite challenging has been solved to some extent. However, most existing methods still perform poorly for curved text detection, mainly due to the limitation of their text representations(e.g., horizontal boxes, rotated rectangles or quadrangles). To solve this problem, we propose a novel method to detect irregular scene texts based on instance-aware segmentation. The key idea is to design an attention guided semantic segmentation model to precisely label the weighted borders of text regions. Experiments conducted on several widely-used benchmarks demonstrate that our method achieves superior results on curved text datasets(i.e., with F-score80.1% and 78.8% for the CTW1500 and Total-Text, respectively) and obtains comparable performance on multi-oriented text datasets compared to the state-of-the-art approaches.

关键词： scene text detection weighted border attention mechanisms curved text semantic segmentation

A Computer-Aided System for Ocular Myasthenia Gravis Diagnosis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2021年第5期26卷 749-758页

作者： Guanjie Liu Yan Wei Yunshen Xie Jianqiang Li Liyan Qiao Ji-jiang Yang the Faculty of Information Technology Beijing University of TechnologyBeijing 100124China the Neurology Department The Second Affiliated Hospital of Tsinghua UniversityBeijing 100040China the Department of Automation Tsinghua UniversityBeijing 100084China

The current mode of clinical aided diagnosis of Ocular Myasthenia Gravis(OMG)is time-consuming and laborious,and it lacks quantitative *** aided diagnostic system for OMG is proposed to solve this *** values calculated by the system include three clinical indicators:eyelid distance,sclera distance,and palpebra superior fatigability test *** the first two indicators,the semantic segmentation method was used to extract the pathological features of the patient's eye image and a semantic segmentation model was *** patient eye image was divided into three regions:iris,sclera,and *** indicators were calculated based on the position of the pixels in the segmentation *** the last indicator,a calculation method based on the Eyelid Aspect Ratio(EAR)is proposed;this method can better reflect the change of eyelid distance over *** system was evaluated based on the collected patient *** results show that the segmentation model achieves a mean Intersection-Over-Union(mIoU)value of 86.05%.The paired-sample T-test was used to compare the results obtained by the system and doctors,and the p values were all greater than ***,the system can reduce the cost of clinical diagnosis and has high application value.

关键词： ocular myasthenia gravis computer-aided system semantic segmentation eyelid aspect ratio

CNN-based segmentation frameworks for structural component and earthquake damage determinations using UAV images

在线全文

学校读者我要写书评

暂无评论

Earthquake Engineering and Engineering Vibration 2023年第2期22卷 359-369页

作者： Taisei Saida Muhammad Rashid Yudai Nemoto Shota Tsukamoto Takehiko Asai Mayuko Nishio Graduate School of Science and Technology University of TsukubaTsukubaJapan Faculty of Engineering Information and SystemsUniversity of TsukubaTsukubaJapan

Buildings undergo various kinds of structural damage during earthquakes,and damage detection and functional assessment of these structures in the aftermath of the events have been challenging *** these circumstances,computer vision techniques offer a promising solution by automating the inspection *** study presents an effective methodology for automatic structural components and damage detection using unmanned aerial vehicle(UAV)images of damaged *** types of neural network architectures are considered for appropriate feature extractions in different task *** feature pyramid network(FPN)is employed for crack,spall,rebar,and component damage segmentation,while the UNet++network is utilized for the damage *** network training and validation,a total of 3805 original images of size 1920×1080 pixels are processed by the proposed method and reduced the image *** the FPN,the achieved highest intersection over unions(IoUs)were 0.59,0.93,0.42,and 0.99 for crack,spall,rebar,and components,*** predicted labels were found in close agreement with the ***,the UNet++recognized the semantic information and damage state with an IoU of *** demonstrated the applicability of the proposed method for automated post-earthquake building inspection process accurately without information loss from the original images.

关键词： computer vision semantic segmentation component segmentation damage evaluation FPN UNet++