检索结果-内蒙古大学图书馆

YOLO-OHFD: A YOLO-Based oriented Hair Follicle detection Method for Robotic Hair Transplantation

APPLIED SCIENCES-BASEL 2025年第6期15卷 3208-3208页

作者： Wang, Hui Liu, Xin Cent South Univ Sch Automat Changsha 410083 Peoples R China

Hair loss affects over 30% of the global population, impacting psychological well-being and social interactions. Robotic hair transplantation has emerged as a pivotal solution, requiring precise hair follicle detection for effective treatment. Traditional methods utilizing horizontal bounding boxes (HBBs) often misclassify due to the follicles' elongated shapes and varied orientations. This study introduces YOLO-OHFD, a novel YOLO-based method using oriented bounding boxes (OBBs) for improved hair follicle detection in dermoscopic images, addressing the limitations of traditional HBB approaches by enhancing detection accuracy and computational efficiency. YOLO-OHFD incorporates the ECA-Res2Block in its feature extraction network to manage occlusions and hair follicle orientation variations effectively. A Feature Alignment Module (FAM) is embedded within the feature fusion network to ensure precise multi-scale feature integration. We utilize angle classification over regression for robust angle prediction. The method was validated using a custom dataset comprising 500 dermoscopic images with detailed annotations of hair follicle orientations and classifications. The proposed YOLO-OHFD method outperformed existing techniques, achieving a mean average precision (mAP) of 87.01% and operating at 43.67 frames per second (FPS). These metrics attest to its efficacy and real-time application potential. The angle classification component particularly enhanced the stability and precision of orientation predictions, critical for the accurate positioning required in robotic procedures. YOLO-OHFD represents a significant advancement in robotic hair transplantation, providing a robust framework for precise, efficient, and real-time hair follicle detection. Future work will focus on refining computational efficiency and testing in dynamic surgical environments to broaden the clinical applicability of this technology.

关键词： hair follicle detection deep learning oriented object detection hair transplantation

来源：评论

学校读者我要写书评

暂无评论

Cell tracking-by-detection using elliptical bounding boxes

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2025年 108卷

作者： Kirsten, Lucas N. Jung, Claudio R. Univ Fed Rio Grande do Sul Inst Informat Porto Alegre RS Brazil

Cell detection and tracking are crucial for bio-analysis. Current approaches rely on the tracking-by-model evolution paradigm, where end-to-end deep learning models are trained for cell detection and tracking. However, such methods require extensive amounts of annotated data, which is time-consuming and often requires specialized annotators. The proposed method involves approximating cell shapes as oriented ellipses and utilizing generic-purpose-oriented object detectors for cell detection to alleviate the requirement of annotated data. A global data association algorithm is then employed to explore temporal cell similarity using probability distance metrics, considering that the ellipses relate to two-dimensional Gaussian distributions. The results of this study suggest that the proposed tracking-by-detection paradigm is a viable alternative for cell tracking. The method achieves competitive results and reduces the dependency on extensive annotated data, addressing a common challenge in current cell detection and tracking approaches. Our code is publicly available at https://***/LucasKirsten/Deep-Cell-Tracking-EBB.

关键词： Cell tracking Cell detection oriented object detection

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Adaption on Transformer-Based oriented object Detector for Satellite Onboard Processing of Remote Sensing Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

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

Deep learning models in satellite onboard enable real-time interpretation of remote sensing images, reducing the need for data transmission to the ground and conserving communication resources. As satellite numbers and observation frequencies increase, the demand for satellite onboard real-time image interpretation grows, highlighting the expanding importance and development of this technology. However, updating the extensive parameters of models deployed on the satellites for spaceborne object detection model is challenging due to the limitations of uplink bandwidth in wireless satellite communications. To address this issue, this article proposes a method based on parameter-efficient fine-tuning (PEFT) technology with a low-rank adaptation module. It involves training low-rank matrix parameters and integrating them with the original model's weight matrix through multiplication and summation, thereby fine-tuning the model parameters to adapt to new data distributions with minimal weight updates. The proposed method combines PEFT with full fine-tuning in the parameter update strategy of the oriented object detection algorithm architecture. This strategy enables model performance improvements close to full fine-tuning effects with minimal parameter updates. In addition, the low-rank approximation is conducted to explore the intrinsic dimensions of parameter matrices in normal-size models. Extensive experiments conducted on the DOTAv1.0, HRSC2016, and DIOR-R datasets verify the effectiveness of the proposed method. By fine-tuning and updating only 12.4% of the model's total parameters, it is able to achieve 97%-100% of the performance of full fine-tuning models. In addition, the reduced number of trainable parameters accelerates model training iterations and enhances the generalization and robustness of the oriented object detection model. The source code is available at: https://***/fudanxu/LoRA-Det.

关键词： Adaptation models Satellites object detection Remote sensing Transformers Uplink Training Data models Computational modeling Feature extraction Low-rank adaption (LoRA) oriented object detection parameter efficient fine-tuning (PEFT)

来源：评论

学校读者我要写书评

暂无评论

oriented object Detector With Gaussian Distribution Cost Label Assignment and Task-Decoupled Head

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Huang, Qiangqiang Yao, Ruilin Lu, Xiaoqiang Zhu, Jishuai Xiong, Shengwu Chen, Yaxiong Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572000 Peoples R China Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Wuhan Huaxia Inst Technol Sch Informat Engn Wuhan 430223 Peoples R China Qiongtai Normal Univ Sch Informat Sci & Technol Haikou 571127 Peoples R China Wuhan Univ Technol Chongqing Res Inst Chongqing 401122 Peoples R China Fuzhou Univ Coll Phys & Informat Engn Fuzhou 350108 Peoples R China Hainan Chang Guang Satellite Informat Technol Co L Hainan 571152 Peoples R China

Recently, oriented object detection in remote sensing images has garnered significant attention due to its broad range of applications. Early-oriented object detection adhered to the established general object detection frameworks, utilizing the label assignment strategy based on the horizontal bounding box (HBB) annotations or rotation-agnostic cost function. Such a strategy may not reflect the large aspect ratio and rotation of arbitrary-oriented objects in remote sensing images and require high parameter-tuning efforts in the training process, which will eventually harm the detector performance. Furthermore, the localization quality of oriented objects depends on precise rotation angle prediction, exacerbating the inconsistency between classification and regression tasks in oriented object detection. To address these issues, we propose the Gaussian distribution cost optimal transport assignment (GCOTA) and decoupled layer attention angle head (DLAAH). Specifically, GCOTA utilizes a Gaussian distribution-based cost function for the optimal transport (OT) label assignment in the training process, alleviating the impact of rotation angle and large aspect ratio in remote sensing images. DLAAH predicts rotation angle independently and incorporates layer attention to obtain the task-specific features based on the shared FPN features, enhancing the angle prediction and improving consistency across different tasks. Based on these proposed components, we present an anchor-free oriented detector, namely, Gaussian distribution and task-decoupled head oriented detector (GTDet) and a multiclass ship detection dataset in real scenarios (CGWX), which provides a benchmark for fine-grained object recognition in remote sensing images. Comprehensive experiments are conducted on CGWX and several public challenging datasets, including DOTAv1.0, and HRSC2016, to demonstrate that our method achieves superior performance on oriented object detection tasks. The code is available at https

关键词： Anchor-free detector deep convolution neural networks oriented object detection remote sensing images

来源：评论

学校读者我要写书评

暂无评论

oriented Bounding Box Representation Based on Continuous Encoding in oriented SAR Ship detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6350-6362页

作者： Li, Peng Feng, Cunqian Feng, Weike Hu, Xiaowei Air Force Engn Univ Air & Missile Def Coll Xian 710051 Peoples R China

Ship detection of synthetic aperture radar (SAR) images holds significant value for both civilian and military applications. Compared to horizontal ship detection, oriented ship detection based on oriented bounding boxes can capture the orientation and aspect ratio of ships, thus receiving increasing attention. However, in oriented ship detection, when ships rotate near the specific angles, the angle prediction result obtained by the deep learning network may have a severe mutation, which is the well-known boundary discontinuity problem. To address the issue of boundary discontinuity in SAR ship detection, researchers have proposed numerous methods. However, through our systematic analysis, we found that these methods do not fundamentally solve the problem. To this end, we first clarified the reasons for the existence of boundary discontinuity and how it affects the detection network. Based on this, we proposed the conditions that the encoding methods and loss functions of the detection network must satisfy to address the issue of boundary discontinuity. In line with these conditions, we designed a continuous encoding method called coordinate decomposition method (CDM). In addition, we also analyzed the impact of different optimization methods on the detection network and, based on this, presented a joint optimization paradigm based on continuous encoding. Experimental results on two commonly used SAR ship detection datasets demonstrate that our proposed CDM encoding method effectively addresses the boundary discontinuity issue and enhances the detection performance. Compared to the state-of-the-art methods, the fully convolutional one-stage network using the CDM-based joint optimization achieves optimal detection results without employing any additional techniques.

关键词： Marine vehicles Encoding Optimization Synthetic aperture radar Measurement Predictive models Accuracy Remote sensing Radar imaging Earth Boundary discontinuity joint optimization oriented object detection ship detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Aerial Data Exploration: An in-Depth Study From Horizontal to oriented Viewpoint

引用

IEEE ACCESS 2024年 12卷 37799-37824页

作者： Vo, Nguyen D. Ngo, Huong-Giang Le, Toan Nguyen, Quang Doan, Danh-Du Nguyen, Binh Le-Huu, Do Le-Duy, Nguyen Tran, Huy Nguyen, Khanh-Duy Nguyen, Khang Univ Informat Technol Fac Software Engn Ho Chi Minh City 720400 Vietnam Vietnam Natl Univ Ho Chi Minh City 721400 Vietnam

The development of technological devices, such as satellites and drones, has made it easier to collect images and videos from the air. From these vast data sources, the problem of detecting objects in aerial images is formed to serve situations: rescue missions, social scenarios, security needs, and more. This issue attracts a lot of attention from researchers in computer vision because of its high applicability in real life. However, this problem faces many significant challenges due to the complex factors of the environment. To overcome these difficulties, many studies focus on developing effective models for detecting and tracking objects from UAV systems. In this paper, our primary emphasis is a comprehensive survey of methodologies about horizontal and oriented object detection. After researching many practical and innovative techniques in different approaches, we have carefully selected 15 methods for horizontal object detection and 18 for oriented object detection that were recently researched and developed to conduct classifications, surveys, and assessments. We also provide a taxonomy mind map to assist readers in gaining an overview of the methods we surveyed. Additionally, we examine 17 aerial image datasets collected from platforms and in various locations worldwide. These are typical datasets widely used to serve two primary tasks: horizontal object detection and oriented object detection. Then, we compared the experimental results of the previously introduced methods on four typical datasets: VisDrone, UAVDT, DOTAv1.0, and HRSC2016. The above datasets present diversity in the number of classes and the complexity of real-life conditions. Furthermore, they have been tested with various methods and shown remarkable results. For the reasons mentioned, we believe that updating and synthesizing the latest research will provide complete and comprehensive information, helping researchers to have more survey material for the development of the field of object d

关键词： object detection Task analysis Drones Surveys Autonomous aerial vehicles Urban areas Transformers Satellite images Image processing Aerial dataset aerial image object detection oriented object detection horizontal object detection

来源：评论

学校读者我要写书评

暂无评论

ORION: Orientation-Sensitive object detection 5th

ORION: Orientation-Sensitive Object Detection

引用

5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Xia, Jingran Kuang, Guowen Wang, Xu Chen, Zhibin Yang, Jinfeng Shenzhen Polytech Inst Appl Artificial Intelligence Guangdong Hong Shenzhen 518055 Peoples R China Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan 114045 Liaoning Peoples R China

ISBN: (纸本)9783031189159;9783031189166

object detection is of great importance to intelligent stock-breeding applications, but currently, basic tools like models and datasets are still in shortage in specific livestock breeding circumstances. In this paper, we build a cattle object detection dataset with real oriented bounding box (ROBB) annotation. In particular, this dataset is single-category, multiple-instance per frame, and has body-direction-aligned orientation and non-rigid targets. Benchmark models are investigated with our proposed orientation-sensitive IOU algorithm COS-IOU and angle-related loss CosAngleLoss. The combination of these two modules outperforms baseline IOU algorithms and MSE angle loss in a more strict angle-confined criterion. This work is a pioneering exploration in non-rigid oriented object detection with orientation in [0, 2 pi), it will shed light on similar issues with single-category, non-rigid, oriented object detection in the stockbreeding and manufacturing industry. Code is available at https://***/guowenk/cattle-robb and the dataset will be released to the public later.

关键词： oriented object detection oriented bounding box Orientation-sensitive detector

来源：评论

学校读者我要写书评

暂无评论

MMRotate: A Rotated object detection Benchmark using PyTorch 22

MMRotate: A Rotated Object Detection Benchmark using PyTorch

引用

30th ACM International Conference on Multimedia (MM)

作者： Zhou, Yue Yang, Xue Zhang, Gefan Wang, Jiabao Liu, Yanyi Hou, Liping Jiang, Xue Liu, Xingzhao Yan, Junchi Lyu, Chengqi Zhang, Wenwei Chen, Kai Shanghai Jiao Tong Univ Dept EE Shanghai Peoples R China Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence Shanghai Peoples R China Northwestern Polytech Univ Xian Peoples R China Northeastern Univ Shenyang Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Shanghai AI Lab Shanghai Peoples R China Nanyang Technol Univ Singapore Singapore SenseTime Res Shanghai Peoples R China Cowa Robot Co Ltd Wuhu Anhui Peoples R China

ISBN: (纸本)9781450392037

We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning. MMRotate implements 18 state-of-the-art algorithms and supports the three most frequently used angle definition methods. To facilitate future research and industrial applications of rotated object detection-related problems, we also provide a large number of trained models and detailed benchmarks to give insights into the performance of rotated object detection. MMRotate is publicly released at https://***/open-mmlab/mmrotate.

关键词： open source rotation detection oriented object detection

来源：评论

学校读者我要写书评

暂无评论

PCBSSD: Self-supervised symmetry-aware detector for PCB displacement and orientation inspection

引用

MEASUREMENT 2025年 243卷

作者： Li, Jingxuan Da, Feipeng Yu, Yi Southeast Univ Sch Automat Nanjing 210096 Jiangsu Peoples R China Minist Educ Key Lab Measurement & Control Complex Syst Engn Nanjing 210096 Jiangsu Peoples R China

Component displacement or orientation frequently impacts the electrical properties of high-density printed circuit boards (PCB), while current methods heavily depend on supervised learning. Diverging from these methods, we introduce a novel self-supervised symmetry-aware detector (PCBSSD), aiming at transitioning from supervised to unsupervised learning for detecting the displacement in symmetric devices. Specifically, a view-transform based paradigm is proposed to exploit symmetry in visual objects through consistencies across different views. Through self-supervision, PCBSSD detects device displacement from their rotational symmetry and orientations from reflective symmetry. To validate PCBSSD, we present a real-world dataset named PCBMO. Experiments show that our method, without any manual annotation, achieves performance comparable to state-of-the-art supervised methods as to accuracy and speed. To our best knowledge, PCBSSD is the first unsupervised displacement inspection approach harnessing the symmetry of devices. It offers a competitive alternative, particularly effective for symmetric objects that widely present in PCB.

关键词： oriented object detection Defect detection Self-supervised learning Printed circuit boards Automated optical inspection

来源：评论

学校读者我要写书评

暂无评论

Point-Based Weakly Semisupervised oriented Vehicle detection in Optical Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 15635-15650页

作者： Tan, Ziqian Wu, Chen Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430079 Peoples R China

Vehicle detection is vital for urban planning and traffic management. Optical remote sensing imagery, known for its high resolution and extensive coverage, is ideal for this task. Traditional horizontal bounding box (HBB) annotations often include excessive background, leading to reduced accuracy, whereas oriented bounding box (OBB) annotations are more precise but costly and prone to human error. To address these issues, we propose the oriented Group R-CNN + Student Model (OGR-SM) framework, a weakly semisupervised oriented vehicle detection method based on single-point annotations. It leverages a small amount of OBB annotations along with a large quantity of single-point annotations for training, achieving performance comparable to fully supervised learning with 100% complete annotations. Specifically, we train the teacher model (OGR) using a small set of accurately annotated OBBs and their corresponding single-point annotations. This model employs an instance-point driven proposal grouping strategy and a group-based proposal assignment strategy enhanced with point location to generate pseudo-OBBs from a large set of weakly annotated single-point data. We then utilize conventional oriented detectors as student models to perform the vehicle detection task in a standard manner. Extensive experiments on two datasets show that our framework, using limited accurate OBBs and many pseudo-OBBs, can achieve or surpass the accuracy of fully supervised models. Our method balances high-quality annotations with data availability, enhancing scalability and robustness for vehicle detection in remote sensing applications.

关键词： Annotations Remote sensing Vehicle detection Accuracy Task analysis Detectors Proposals Optical remote sensing images oriented object detection point-based supervised vehicle detection weakly semisupervised learning

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：