检索结果-内蒙古大学图书馆

3d-NOd: 3d new organ detection in plant growth by a spatiotemporal point cloud deep segmentation framework

PLANT PHENOMICS 2025年第1期7卷

作者： Li, dawei Ahmed, Foysal Wang, Zhanjiang Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China Donghua Univ State Key Lab Adv Fiber Mat SKLAFM Shanghai 201620 Peoples R China Donghua Univ Engn Res Ctr Digitized Text & Fash Technol Minist Educ Shanghai 201620 Peoples R China

Automatic plant growth monitoring is an important task in modern agriculture for maintaining high crop yield and boosting the breeding procedure. The advancement of 3d sensing technology has made 3d point clouds to be a better data form on presenting plant growth than images, as the new organs are easier identified in 3d space and the occluded organs in 2d can also be conveniently separated in 3d. despite the attractive characteristics, analysis on 3d data can be quite challenging. We present 3d-NOd, a framework to detect new organs from time-series 3d plant data by spatiotemporal point cloud deep semantic segmentation. The design of 3d-NOd framework drew inspiration from how a well-experienced human utilizes spatiotemporal information to identify growing buds from a plant at two different growth stages. In the training phase, by introducing the Backward & Forward Labeling, the Registration & Mix-up, and the Humanoid data Augmentation step, our backbone network can be trained to recognize growth events with organ correlation from both temporal and spatial domains. In testing, 3dNOd has shown better sensitivity at segmenting new organs against the conventional way of using a network to conduct direct semantic segmentation. On a time-series dataset containing multiple species, Our method reached a mean F1-measure at 88.13 % and a mean IoU at 80.68% on detecting both new and old organs with the dGCNN backbone.

关键词： 3d semantic segmentation Growth event detection Point cloud registration Plant phenotyping deep neural network

来源：评论

学校读者我要写书评

暂无评论

Uni-to-Multi Modal Knowledge distillation for Bidirectional LidAR-Camera semantic segmentation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS ANd MACHINE INTELLIGENCE 2024年第12期46卷 11059-11072页

作者： Sun, Tianfang Zhang, Zhizhong Tan, Xin Peng, Yong Qu, Yanyun Xie, Yuan East China Normal Univ Sch Comp Sci & Technol Shanghai 200060 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai 200240 Peoples R China Cent South Univ Sch Traff & Transportat Engn Changsha 410017 Peoples R China Xiamen Univ Dept Comp Sci & Technol Xiamen 361005 Peoples R China

Combining LidAR points and images for robust semantic segmentation has shown great potential. However, the heterogeneity between the two modalities (e.g. the density, the field of view) poses challenges in establishing a bijective mapping between each point and pixel. This modality alignment problem introduces new challenges in network design and data processing for cross-modal methods. Specifically, 1) points that are projected outside the image planes;2) the complexity of maintaining geometric consistency limits the deployment of many data augmentation techniques. To address these challenges, we propose a cross-modal knowledge imputation and transition approach. First, we introduce a bidirectional feature fusion strategy that imputes missing image features and performs cross-modal fusion simultaneously. This allows us to generate reliable predictions even when images are missing. Second, we propose a Uni-to-Multi modal Knowledge distillation (U2MKd) framework, leveraging the transfer of informative features from a single-modality teacher to a cross-modality student. This overcomes the issues of augmentation misalignment and enables us to train the student effectively. Extensive experiments on the nuScenes, Waymo, and semanticKITTI datasets demonstrate the effectiveness of our approach. Notably, our method achieves an 8.3 mIoU gain over the LidAR-only baseline on the nuScenes validation set and achieves state-of-the-art performance on the three datasets.

关键词： 3d semantic segmentation cross-modal feature imputing cross-modal fusion cross-modal knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

deep learning based 3d segmentation in computer vision: A survey

引用

INFORMATION FUSION 2025年 115卷

作者： He, Yong Yu, Hongshan Liu, Xiaoyan Yang, Zhengeng Sun, Wei Anwar, Saeed Mian, Ajmal Hunan Univ Quanzhou Inst Ind Design & Machine Intelligence In Coll Elect & Informat Engn Sch Robot Lushan South Rd Changsha 410082 Hunan Peoples R China Hunan Normal Univ Lushan South Rd Changsha 410081 Hunan Peoples R China Australian Natl Univ Canberra ACT 2600 Australia Univ Western Australia 35 Stirling Hwy Perth WA 6009 Australia

3d segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the computer vision, graphics and machine learning communities. Conventional methods for 3d segmentation, based on hand-crafted features and machine learning classifiers, lack generalization ability. driven by their success in 2d computer vision, deep learning techniques have recently become the tool of choice for 3d segmentation tasks. This has led to an influx of many methods in the literature that have been evaluated on different benchmark datasets. Whereas survey papers on RGB-d and point cloud segmentation exist, there is a lack of a recent in-depth survey that covers all 3d data modalities and application domains. This paper fills the gap and comprehensively surveys the recent progress in deep learning-based 3d segmentation techniques. We cover over 230 works from the last six years, analyze their strengths and limitations, and discuss their competitive results on benchmark datasets. The survey provides a summary of the most commonly used pipelines and finally highlights promising research directions for the future.

关键词： Computer vision deep learning deep neural network 3d semantic segmentation 3d instance segmentation 3d part segmentation

来源：评论

学校读者我要写书评

暂无评论

A domain adaptation framework for cross-modality SAR 3d reconstruction point clouds segmentation utilizing LidAR data

引用

INTERNATIONAL JOURNAL OF APPLIEd EARTH OBSERVATION ANd GEOINFORMATION 2024年 133卷

作者： Wang, Muhan Qiu, Xiaolan Zhang, Zhe Gao, Silin Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China China Natl Key Lab Microwave Imaging Beijing 100190 Peoples R China Key Lab Technol Geospatial Informat Proc & Applica Beijing 100090 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100094 Peoples R China Suzhou Key Lab Microwave Imaging Proc & Applicat T Suzhou 215128 Peoples R China Suzhou Aerosp Informat Res Inst Suzhou 215128 Peoples R China

Synthetic aperture radar (SAR) 3d point clouds reconstruction can eliminate the problems of layover in 2d SAR image projections, the recognition of the reconstructed point cloud can significantly enhance target identification and information extraction. Current SAR 3d point cloud segmentation methods, based on traditional machine learning clustering approaches, suffer from poor automation and accuracy. However, the absence of publicly labeled SAR datasets impedes the progress of deep learning-based SAR 3d point cloud segmentation methods. To tackle the aforementioned challenges, we introduce, for the first time, an alternative training approach for SAR 3d point cloud segmentation using LidAR annotated data, which offers a more abundant sample pool, thus alleviating the lack of training sets. Nevertheless, a segmentation model trained on LidAR point clouds exhibits a significant decline in performance when directly applied to SAR 3d reconstructed point clouds due to the cross-domain discrepancy. This research presents a pioneering domain adaptation 3d semantic segmentation framework to implement cross-modal learning for SAR point clouds. In our scheme, a simple yet effective technique is developed to achieve segmentation of SAR double-bounce scattering regions called SARdBS-Mix, which employs a mixing strategy, to capture the distinctive reflection characteristics of SAR data. Furthermore, we implement approaches including center alignment and normalization, local augmentation, and weighted cross entropy to mitigate LidAR and SAR domain gap and class imbalances. The experimental results validate the feasibility and effectiveness of the proposed method for SAR 3d reconstructed point cloud segmentation.

关键词： Synthetic aperture radar (SAR) Point cloud 3d semantic segmentation domain adaptation Cross-modal learning

来源：评论

学校读者我要写书评

暂无评论

3d multi-scale feature extraction and recalibration network for spinal structure and lesion segmentation

引用

ACTA RAdIOLOGICA 2023年第12期64卷 3015-3023页

作者： Wang, Hongjie Chen, Yingjin Jiang, Tao Bian, Huwei Shen, Xing Nanjing Univ Aeronaut & Astronaut State Key Lab Mech & Control Mech Struct Nanjing Peoples R China Changzhou Tradit Chinese Med Hosp Dept Orthopaed Changzhou Jiangsu Peoples R China

Background Automatic segmentation has emerged as a promising technique for the diagnosis of spinal conditions. Purpose To design and evaluate a deep convolution network for segmenting the intervertebral disc, spinal canal, facet joint, and herniated disk on magnetic resonance imaging (MRI) scans. Material and Methods MRI scans of 70 patients with disc herniation were gathered and manually annotated by radiologists. A novel deep neural network was developed, comprising 3d squeeze-and-excitation blocks and multi-scale feature extraction blocks for automated segmentation of spinal structure and lesion. To address the issue of class imbalance, a weighted cross-entropy loss was introduced for training. In addition, semi-supervision segmentation was accomplished to reduce annotation labor cost. Results The proposed model achieved 77.67% mean intersection over union, with 9.56% and 11.11% gains over typical V-Net and U-Net respectively, outperforming the other models in ablation experiments. In addition, the semi-supervision segmentation method was proven to work. Conclusion The 3d multi-scale feature extraction and recalibration network achieved an excellent segmentation performance of intervertebral disc, spinal canal, facet joint, and herniated disk, outperforming typical encoder-decoder networks.

关键词： deep learning 3d semantic segmentation lumbar spine magnetic resonance imaging 3d V-Net SE block atrous convolution

来源：评论

学校读者我要写书评

暂无评论

dPRNet: deep 3d Point Based Residual Network for semantic segmentation and Classification of 3d Point Clouds

引用

IEEE ACCESS 2019年 7卷 68892-68904页

作者： Arshad, Saira Shahzad, Muhammad Riaz, Qaiser Fraz, Muhammad Moazam Natl Univ Sci & Technol Sch Elect Engn & Comp Sci Islamabad 44000 Pakistan Natl Ctr Artificial Intelligence Deep Learning Lab Islamabad 44000 Pakistan Univ Warwick Dept Comp Sci Coventry CV4 7AL W Midlands England Alan Turing Inst British Lib London NW1 2DB England

Point clouds are an important type of geometric data obtained from a variety of 3d sensors. They do not have an explicit neighborhood structure and therefore several researchers often perform a voxelization step to obtain structured 3d neighborhood. This, however, comes with certain disadvantages, e.g., it makes the data unnecessarily voluminous, enforces additional computation effort and can potentially introduce quantization errors that may not only hinder in extracting implicit 3d shape information but also in capturing the essential data invariances for the required segmentation and recognition task. In this context, this paper addresses the highly challenging problem of semantic segmentation and 3d object recognition using raw unstructured 3d point cloud data. Specifically, the deep network architecture has been proposed which consists of a cascaded combination of 3d point-based residual networks for simultaneous semantic scene segmentation and object classification. It exploits the 3d point-based convolutions for representational learning from raw unstructured 3d point cloud data. The proposed architecture has a simple design, easier implementation, and the performance which is better than the existing state-of-the architectures particularly for semantic scene segmentation over three public datasets. The implementation and evaluation are made public here https://***/saira05/dPRNet.

关键词： Object recognition 3d point cloud deep residual learning 3d semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

ECLAIR: A High-Fidelity Aerial LidAR dataset for semantic segmentation

ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Se...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Melekhov, Iaroslav Umashankar, Anand Kim, Hyeong-Jin Serkov, Vladislav Argyle, dusty Sharper Shape Salt Lake City UT 84115 USA Aalto Univ Espoo Finland

ISBN: (纸本)9798350365474

We introduce ECLAIR (Extended Classification of Lidar for AI Recognition), a new outdoor large-scale aerial LidAR dataset designed specifically for advancing research in point cloud semantic segmentation. As the most extensive and diverse collection of its kind to date, the dataset covers a total area of 10km(2) with close to 600 million points and features eleven distinct object categories. To guarantee the dataset's quality and utility, we have thoroughly curated the point labels through an internal team of experts, ensuring accuracy and consistency in semantic labeling. The dataset is engineered to move forward the fields of 3d urban modeling, scene understanding, and utility infrastructure management by presenting new challenges and potential applications. As a benchmark, we report qualitative and quantitative analysis of a voxel-based point cloud segmentation approach based on the Minkowski Engine. We release the dataset as open-source and it can be accessed at https:// ***/SharperShape/eclairdataset

关键词： 3d semantic segmentation deep learning Lidar dataset minkowski engine pointcloud data

来源：评论

学校读者我要写书评

暂无评论

Meta-RangeSeg: LidAR Sequence semantic segmentation Using Multiple Feature Aggregation

引用

IEEE ROBOTICS ANd AUTOMATION LETTERS 2022年第4期7卷 9739-9746页

作者： Wang, Song Zhu, Jianke Zhang, Ruixiang Zhejiang Univ Coll Comp Sci Hangzhou 310027 Peoples R China Alibaba Zhejiang Univ Joint Res Inst Frontier Tec Hangzhou 310027 Peoples R China Hikvis Res Inst Hangzhou 310051 Peoples R China

LidAR sensor is essential to the perception system in autonomous vehicles and intelligent robots. To fulfill the real-time requirements in real-world applications, it is necessary to efficiently segment the LidAR scans. Most of previous approaches directly project 3d point cloud onto the 2d spherical range image so that they can make use of the efficient 2d convolutional operations for image segmentation. Although having achieved the encouraging results, the neighborhood information is not well-preserved in the spherical projection. Moreover, the temporal information is not taken into consideration in the single scan segmentation task. To tackle these problems, we propose a novel approach to semantic segmentation for LidAR sequences named Meta-RangeSeg, where a new range residual image representation is introduced to capture the spatial-temporal information. Specifically, Meta-Kernel is employed to extract the meta features, which reduces the inconsistency between the 2d range image coordinates input and 3d Cartesian coordinates output. An efficient U-Net backbone is used to obtain the multi-scale features. Furthermore, Feature Aggregation Module (FAM) strengthens the role of range channel and aggregates features at different levels. We have conducted extensive experiments for performance evaluation on semanticKITTI and semanticPOSS. The promising results show that our proposed Meta-RangeSeg method is more efficient and effective than the existing approaches.

关键词： 3d semantic segmentation LidAR perception autonomous vehicle

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Refinement for 3d Human Body Parts segmentation 17th

Clustering-Based Refinement for 3D Human Body Parts Segmenta...

引用

17th International Conference on Intelligent Autonomous Systems (IAS)

作者： Barcellona, Leonardo Terreran, Matteo Evangelista, daniele Ghidoni, Stefano Univ Padua Dept Informat Engn DEI Padua Italy

ISBN: (纸本)9783031222153;9783031222160

A common approach to address human body parts segmentation on 3d data involves the use of a 2d segmentation network and 3d projection. Following this approach, several errors could be introduced in the final 3d segmentation output, such as segmentation errors and reprojection errors. Such errors are even more significant when considering very small body parts such as hands. In this paper, we propose a new algorithm that aims to reduce such errors and improve 3d segmentation of human body parts. The algorithm detects noise points and wrong clusters using dBSCAN algorithm, and changes the labels of the points exploiting the shape and position of the clusters. We evaluated the proposed algorithm on the 3dPeople synthetic dataset and on a real dataset, highlighting how it can greatly improve the 3d segmentation of small body parts like hands. With our algorithm we achieved an improvement up to 4.68% of IoU on the synthetic dataset and up to 2.30% of IoU in the real scenario.

关键词： Human parsing 3d semantic segmentation 3d clustering

来源：评论

学校读者我要写书评

暂无评论

Swin3d: A pretrained transformer backbone for 3d indoor scene understanding

引用

Computational Visual Media 2025年第1期11卷 83-101页

作者： Yu-Qi Yang Yu-Xiao Guo Jian-Yu Xiong Yang Liu Hao Pan Peng-Shuai Wang Xin Tong Baining Guo Institute for Advanced Study Tsinghua UniversityBeijing 100084China Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Internet Graphics Group Microsoft Research AsiaBeijing 100080China Wangxuan Institute of Computer Technology Peking UniversityBeijing 100080China

The use of pretrained backbones with finetuning has shown success for 2d vision and natural language processing tasks,with advantages over taskspecific *** this paper,we introduce a pretrained 3d backbone,called Swin3d,for 3d indoor scene *** designed a 3d Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and *** also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network *** pretrained a large Swin3d model on a synthetic Structured3d dataset,which is an order of magnitude larger than the ScanNet *** model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3d point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3dIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3dIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.

关键词： 3d pretraining ponitcloud analysis trans-former backbone Swin Transformer 3d semantic segmentation 3d object detection

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：