检索结果-内蒙古大学图书馆

instance segmentation from particle holograms

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第3期36卷 035211-035211页

作者： Senger, Corey Hong, Jiarong Comp Sci & Engn 100 Union St SE Minneapolis MN 55455 USA Mech Engn 111 Church St SE Minneapolis MN 55455 USA St Anthony Falls Lab 2 3rd Ave SE Minneapolis MN 55414 USA

Holographic microscopy has emerged as a low-cost and highly compact technique for 3D imaging of microscopic particles in suspension. However, its broad application is largely limited by the inclusion of multiple steps in extracting the particles from the hologram image, which can be computationally expensive and often involves human intervention. We introduce HoloDINO, a transformative model that leverages instance segmentation for streamlined, end-to-end particle detection and contour extraction. By pre-training a data-intensive transformer model on synthetic particle contours and fine-tuning it on experimental data, our approach demonstrates robust performance across synthetic holograms of varying particle concentration, morphology, and optical properties, as well as experimental holograms of dental aerosols and water spray droplets. HoloDINO surpasses conventional methods, which typically involve multiple steps-such as reconstruction, autofocusing, and segmentation-by consolidating these into a single, efficient process that delivers precise morphological data for each particle in one forward pass. This advancement not only facilitates real-time applications but also significantly enhances the generalization capabilities across diverse settings, paving the way for broader adoption of holography in particle analysis.

关键词： holographic microscopy instance segmentation particle detection synthetic dataset

来源：评论

学校读者我要写书评

暂无评论

instance segmentation XXL-CT Challenge of a Historic Airplane

引用

JOURNAL OF NONDESTRUCTIVE EVALUATION 2025年第1期44卷 1-14页

作者： Gruber, Roland Engster, Johann Christopher Michen, Markus Blum, Nele Stille, Maik Gerth, Stefan Wittenberg, Thomas Fraunhofer Inst Integrated Circuits IIS Div Dev Ctr X Ray Technol Fraunhofer IIS Furth Germany Friedrich Alexander Univ Erlangen Nurnberg Chair Visual Comp Erlangen Germany Fraunhofer Res Inst Individualized & Cell Based Me Dept Diagnost Fraunhofer IMTE Lubeck Germany Univ Lubeck Inst Med Engn Lubeck Germany

instance segmentation of compound objects in XXL-CT imagery poses a unique challenge in non-destructive testing. This complexity arises from the lack of known reference segmentation labels, limited applicable segmentation tools, as well as partially degraded image quality. To asses recent advancements in the field of machine learning-based image segmentation, the 'instance segmentation XXL-CT Challenge of a Historic Airplane' was conducted. The challenge aimed to explore automatic or interactive instance segmentation methods for an efficient delineation of the different aircraft components, such as screws, rivets, metal sheets or pressure tubes. We report the organization and outcome of this challenge and describe the capabilities and limitations of the submitted segmentation methods.

关键词： Challenge instance segmentation Computed tomography Non-destructive testing Neural networks Machine learning

来源：评论

学校读者我要写书评

暂无评论

instance segmentation of reinforced concrete bridge point clouds with transformers trained exclusively on synthetic data

引用

AUTOMATION IN CONSTRUCTION 2025年 173卷

作者： Rahman, Asad Ur Hoskere, Vedhus Univ Houston Dept Civil & Environm Engn 4226 MLK Blvd Houston TX 77204 USA Univ Houston Dept Elect & Comp Engn 4226 MLK Blvd Houston TX 77204 USA

Bridges in the United States require element-level inspections every 24 months, typically relying on laborious manual assessments. Three-dimensional (3D) point clouds from LiDAR or photogrammetry can facilitate these inspections, but are difficult to leverage without automatically identifying individual structural elements. Existing research focuses on semantic segmentation, which classifies points into broader categories rather than identifying each element instance. A major bottleneck is the difficulty of producing instance-level annotations. To address this gap, the paper proposes and evaluates three synthetic data generation approaches to produce automatically labeled point clouds of bridges with element instance-level annotations. An occlusion technique is introduced to increase realism. The synthetic data is then evaluated for training Mask3D transformer model for instance segmentation of field-collected point clouds, achieving mean Average Precision (mAP) scores of 91.7 % on LiDAR data and 63.8 % on photogrammetry. These results demonstrate the potential to enhance element-level bridge inspections and improve overall infrastructure management.

关键词： Synthetic point clouds Reinforced concrete bridges instance segmentation Deep learning Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Tuning a SAM-Based Model With Multicognitive Visual Adapter to Remote Sensing instance segmentation

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 2737-2748页

作者： Zheng, Linghao Pu, Xinyang Zhang, Su Xu, Feng Fudan Univ Sch Informat Sci & Technol Minist Educ Key Lab Informat Sci Electromagnet Waves Shanghai 200433 Peoples R China

The segment anything model (SAM), a foundational model designed for promptable segmentation tasks, demonstrates exceptional generalization capabilities, making it highly promising for natural scene image segmentation. However, SAM's lack of pretraining on massive remote sensing images and its interactive structure limit its automatic mask prediction capabilities. In this article, a multicognitive SAM-based instance segmentation model (MC-SAM SEG) is introduced to employ SAM on remote sensing domain. The SAM-multicognitive visual adapter (Mona) encoder utilizing the Mona is conducted to facilitate SAM's transfer learning in remote sensing applications. The proposed method named MC-SAM SEG extracts high-quality features by fine-tuning the SAM-Mona encoder along with a feature aggregator. Subsequently, a pixel decoder and transformer decoder are designed for prompt-free mask generation and instance classification. The comprehensive experiments are conducted on the HRSID and WHU datasets for instance segmentation tasks on synthetic aperture radar images and optical remote sensing images, respectively. The evaluation results indicate the proposed method surpasses other deep learning algorithms and verify its effectiveness and generalization.

关键词： Remote sensing instance segmentation Feature extraction Image segmentation Adaptation models Computational modeling Decoding Visualization Radar polarimetry Marine vehicles remote sensing images segment anything model (SAM) transfer learning

来源：评论

学校读者我要写书评

暂无评论

Break Adhesion: Triple adaptive-parsing for weakly supervised instance segmentation

引用

NEURAL NETWORKS 2025年 186卷 107215页

作者： Xu, Jingting Cao, Rui Luo, Peng Mu, Dejun Northwestern Polytech Univ Sch Automat Xian 710129 Peoples R China Northwest Univ Sch Comp Sci & Technol Xian 710127 Peoples R China Northwestern Polytech Univ Res & Dev Inst Shenzhen 518057 Peoples R China

Weakly supervised instance segmentation (WSIS) aims to identify individual instances from weakly supervised semantic segmentation precisely. Existing WSIS techniques primarily employ a unified, fixed threshold to identify all peaks in semantic maps. It may lead to potential missed or false detections due to the same category but with diverse visual characteristics. Moreover, previous methods apply a fixed augmentation strategy to broadly propagate peak cues to contributing regions, resulting in instance adhesion. To eliminate these manually fixed parsing patterns, we propose a triple adaptive-parsing network. Specifically, an adaptive Peak Perception Module (PPM) employs the average degree of feature as a learning base to infer the optimal threshold. Simultaneously, we propose the Shrinkage Loss function (SL) to minimize outlier responses that deviate from the mean. Finally, by eliminating uncertain adhesion, our method effectively obtains Reliable Inter-instance Relationships (RIR), enhancing the representation of instances. Extensive experiments on the Pascal VOC and COCO datasets show that the proposed method improves the accuracy by 2.1% and 4.3%, achieving the latest performance standard and significantly optimizing the instance segmentation task. The code is available at https://***/Elaineok/TAP.

关键词： instance segmentation Class-level supervision Adaptation learning Peak perception Inter-instance relationships

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional instance segmentation of Rooms in Indoor Building Point Clouds Using Mask3D

引用

REMOTE SENSING 2025年第7期17卷 1124-1124页

作者： Brunklaus, Michael Kellner, Maximilian Reiterer, Alexander Univ Freiburg Dept Sustainable Syst Engn INATECH Georges Kohler Allee 10 D-79110 Freiburg Germany Fraunhofer Inst Phys Measurement Tech IPM Georges Kohler Allee 301 D-79110 Freiburg Germany

While most recent work in room instance segmentation relies on orthographic top-down projections of 3D point clouds to 2D density maps, leading to information loss of one dimension, 3D instance segmentation methods based on deep learning were rarely considered. We explore the potential of the general 3D instance segmentation deep learning model Mask3D for room instance segmentation in indoor building point clouds. We show that Mask3D generates meaningful predictions for multi-floor scenes. After hyperparameter optimization, Mask3D outperforms the current state-of-the-art method RoomFormer evaluated in 3D on the synthetic Structured3D dataset. We provide generalization results of Mask3D trained on Structured3D to the real-world S3DIS and Matterport3D datasets, showing a domain gap. Fine-tuning improves the results. In contrast to related work in room instance segmentation, we employ the more expressive mean average precision (mAP) metric, and we propose the more intuitive successfully detected rooms (SDR) metric, which is an absolute recall measure. Our results indicate potential for the digitization of the construction industry.

关键词： Mask3D instance segmentation indoor building point cloud room detection floor plan reconstruction 3D deep learning LiDAR Structured3D S3DIS Matterport3D

来源：评论

学校读者我要写书评

暂无评论

Imaging-Based instance segmentation of Pavement Cracks Using an Improved YOLOv8 Network

引用

STRUCTURAL CONTROL & HEALTH MONITORING 2025年第1期2025卷

作者： Yu, Fei Ye, Guanting Jiang, Qing Yuen, Ka-Veng Chong, Xun Jin, Qiang Xinjiang Agr Univ Coll Hydraul & Civil Engn Urumqi Peoples R China Xinjiang Key Lab Hydraul Engn Secur & Water Disast Urumqi Peoples R China Hefei Univ Technol Sch Civil Engn Hefei Peoples R China Univ Macau State Key Lab Internet Things Smart City Taipa Macao Peoples R China Univ Macau Dept Civil & Environm Engn Taipa Macao Peoples R China Univ Macau Guangdong Hong Kong Macau Joint Lab Smart Cities Taipa Macao Peoples R China

An improved YOLOv8 model, YOLOv8-NETC, is proposed in this study for fine-grained crack recognition through instance segmentation. YOLOv8-NETC is designed and enhanced with four self-developed modules. First, ablation studies were conducted to assess the effectiveness of each module. The model's accuracy and speed were evaluated based on parameters such as mean average precision (mAP50) and model weight (MW). The experimental results show significant improvements in accuracy, storage efficiency, and processing speed. Compared to the original network, YOLOv8-NETC achieved a 6.5% increase in mAP50, a 6.1% average reduction in MW and parameters, and an 8.5% improvement in FPS. Subsequently, YOLOv8-NETC was compared with other state-of-the-art models across three datasets, including the crack type dataset, crack trueness dataset, and the public Crack500 dataset. The experimental results demonstrate that the proposed model achieved the best recognition performance on all datasets. Furthermore, YOLOv8-NETC showed superior robustness against interference and computational efficiency compared to other benchmark models.

关键词： crack identification deep learning instance segmentation You Only Look Once

来源：评论

学校读者我要写书评

暂无评论

Automated Zebrafish Spine Scoring System Based on instance segmentation

引用

IEEE ACCESS 2025年 13卷 18814-18826页

作者： Chen, Wen-Hsin Kuo, Tien-Ying Wei, Yu-Jen Ho, Cheng-Jung Lin, Ming-der Chen, Huan Lin, Wen-Ying Natl Taipei Univ Technol Dept Elect Engn Taipei 10608 Taiwan Tzu Chi Univ Dept Mol Biol & Human Genet Hualien 97004 Taiwan Natl Chung Hsing Univ Dept Comp Sci & Engn Taichung 40202 Taiwan

In studying new medicines for osteoporosis, researchers use zebrafish as animal subjects to test drugs and observe the growth situation of their vertebrae in the spine to confirm the efficacy of new medicines. However, the current method for evaluating efficacy is time-consuming and labor-intensive, requiring manual observation. Taking advantage of advancements in deep learning technology, we propose an automatic method for detecting and recognizing zebrafish vertebrae of the images captured from image sensors to solve this problem. Our method was designed using Mask R-CNN as the instance segmentation backbone, enhanced with a mask enhancement module and a small object preprocessing approach to strengthen its detection abilities. Compared to the original Mask R-CNN architecture, our method improved the mean average precision (mAP) score for vertebra bounding box and mask detection by 7.1% to 97.7% and by 1.2% to 96.6%, respectively. Additionally, we developed a system using these detection algorithms to automatically calculate spinal vertebra growth scores, providing a valuable tool for researchers to assess drug efficacy.

关键词： Feature extraction Accuracy Micromechanical devices Classification algorithms Object recognition instance segmentation Deep learning Computer architecture Proposals Prediction algorithms machine learning object segmentation image analysis

来源：评论

学校读者我要写书评

暂无评论

IOFusion: instance segmentation and optical-flow guided 3D reconstruction in dynamic scenes

引用

VISUAL COMPUTER 2025年第2期41卷 799-813页

作者： Zhu, Haowei Bai, Suqin Shi, Jinlong Wang, Chenggen Sun, Yunhan Lu, Jiawen Shu, Xin Huang, Shucheng Jiangsu Univ Sci & Technol Sch Comp Sci Changhui Rd Zhenjiang 212114 Jiangsu Peoples R China Civil Aviat Univ China Civil Aviat Smart Airport Theory & Key Lab Xinli Rd Tianjin 300300 Peoples R China Nanjing Univ State Key Lab Novel Software Technol HuNan Rd Nanjing 210008 Jiangsu Peoples R China

To improve the accuracy of camera pose estimation for RGBD-based 3D reconstruction in dynamic scenes, a method based on instance segmentation and optical flow is proposed. Firstly, instance segmentation is used to detect objects, and a semantic map is constructed by removing non-rigid objects. Secondly, motion residual is calculated by optical flow and camera flow to detect dynamic rigid objects, and nonlinear optimization is used to track the dynamic rigid objects extracted from the semantic map. Thirdly, after removing features of non-rigid objects and dynamic rigid ones in each frame, the remaining features are used to optimize the camera pose. Finally, a TSDF model is used to reconstruct the static background, and point clouds are used to reconstruct dynamic rigid objects. Experiments on TUM and Bonn datasets show that the method produces better camera poses than the current state-of-the-art methods in most dynamic scenes. Ablation experiments on Bonn dataset show that retaining features of static rigid objects significantly improves camera pose estimation precision. The annotated datasets and the source code are available at https://***/CodingMaplee/IOFusion/tree/main.

关键词： 3D reconstruction instance segmentation Optical flow Dynamic scene

来源：评论

学校读者我要写书评

暂无评论

A pose estimation approach for discarded stacked smartphones recycling: Based on instance segmentation and point cloud registration

引用

WASTE MANAGEMENT 2025年 194卷 149-157页

作者： Li, Jie Hu, Xuejun Zheng, Hangbin Zhang, Gaohua Donghua Univ Dept Mech Engn Shanghai 201600 Peoples R China Zhejiang Univ Dept Mech Engn ZheJiang 310000 Peoples R China

With the rapid increase in end-of-life smartphones, enhancing the automation and intelligence of their recycling processes has become an urgent challenge. At present, the disassembly of discarded smartphones predominantly relies on manual labor, which is not only inefficient but also associated with environmental pollution and high labor intensity. In the context of end-of-life smartphone recycling, complex situations such as stacking and occlusion are commonly encountered. Accurate pose information can provide critical data for precise robotic grasping, thereby improving the level of automation and efficiency in recycling and disassembly. This research proposes a pose estimation method tailored for stacked discarded smartphones, integrating an improved Mask R-CNN instance segmentation model with Iterative Closest Point (ICP) point cloud registration technology. The method begins by accurately segmenting stacked smartphones using both real and synthetic datasets. Subsequently, pose information is extracted through the proposed estimation approach, providing critical data to guide the robotic arm's grasping actions, thereby improving sorting efficiency and minimizing manual intervention. To enhance its practical applicability, a pose recognition interactive system is developed, enabling visualization and dynamic interaction with pose data. Experimental results demonstrate the effectiveness of the transfer learning algorithm, which leverages a large volume of synthetic data combined with a small batch of real-world data. This research offers valuable theoretical insights and technical solutions for advancing the automation and intelligent disassembly of end-of-life smartphones.

关键词： Stacked smartphones Pose estimation instance segmentation Iterative closest point End-of-life management

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：