检索结果-内蒙古大学图书馆

Intelligent weed management using aerial image processing and precision herbicide spraying: An overview

CROP PROTECTION 2025年 194卷

作者： Ehrampoosh, Armin Hettiarachchi, Pushpika Koirala, Anand Hassan, Jahan Islam, Nahina Ray, Biplob Nabi, Md Nurun Tolba, Mohamed Mazid, Abdul Md Xu, Cheng-Yuan Ashwath, Nanjappa Dzitac, Pavel Moore, Steven Cent Queensland Univ Sch Engn & Technol Norman Gardens Australia Cent Queensland Univ Sch Hlth Med & Appl Sci Norman Gardens Australia Cent Queensland Univ Ctr Machine Learning Networking & Educ Technol CML Norman Gardens Australia Cent Queensland Univ Ctr Reg Econ & Supply Chains Norman Gardens Australia Charles Darwin Univ Res Inst Environm & Livelihoods Casuarina Australia Res Inst Northern Agr Casuarina Australia Leica Biosyst Mt Waverley Australia

Modern agriculture is increasingly adopting intelligent technologies to enhance productivity while minimizing production costs and reducing adverse environmental impacts. A prime example of this synergy is the use of image processing to identify weeds, enabling targeted herbicide spraying with autonomous devices such as robots and drones. This approach not only reduces production costs but also ensures sustainable farming while minimizing negative environmental impacts. Designing an intelligent weed management system requires a multidisciplinary approach, combining agriculture, big data processing, machine learning, computer science, robotics, and plant science. Currently, independent studies have focused on some of these aspects, but few have taken a holistic approach to address the issue. This paper highlights the approach taken in developing innovative and ecologically sustainable weed management systems for agriculture. It also presents a comprehensive overview of a weed management system that integrates coordinated weed detection and spraying, detailing its unique components. The paper reviews and contrasts various image analysis techniques used in weed detection, particularly those employing artificial intelligence and imagery captured by unmanned aerial vehicles (UAVs). Furthermore, the paper highlights recent advancements in image processing platforms, such as the shift towards local and edge computing, and the growing need for near-real-time processing in agricultural applications. It also explores the development of commercial weed-spraying drones and discusses various aspects of an autonomous weed control system, including design, navigation, and spraying mechanisms for targeted application. Finally, the paper identifies key research needs for developing an AI-based, targeted herbicide spraying system that could significantly contribute to sustainable, economically viable, and efficient agricultural practices.

关键词： aerial image processing Artificial intelligence Blanket spraying Cloud and edge computing Deep learning Machine learning Precision herbicide spraying Smart farming Sprayer-drones UAVs-based spot spraying Weed detection Weed management

来源：评论

学校读者我要写书评

暂无评论

Paper: Method to Generate Building Damage Maps by Combining aerial image processing and Crowdsourcing

引用

JOURNAL OF DISASTER RESEARCH 2021年第5期16卷 827-839页

作者： Shishido, Hidehiko Kobayashi, Koyo Kameda, Yoshinari Kitahara, Itaru Univ Tsukuba Ctr Computat Sci CCS 1-1-1 Tennodai Tsukuba Ibaraki 3058577 Japan Univ Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki 3058577 Japan

Building damage maps that show the damage status of buildings are an essential information source for various disaster countermeasures, such as evacuation, rescue, and reconstruction. Therefore, they must be generated as quickly as possible. However, to generate a building damage map, it is necessary to collect disaster information and estimate the damage situation over a wide area, which is time consuming. (In this paper, we consider disaster information collection as capturing aerial images.) In recent years, crowdsourcing has been widely used to understand the damage situation. Crowdsourcing achieves large-scale work by dividing it into microtasks that can be solved by anyone and by distributing the microtasks among an unspecified number of workers. We believe that crowdsourcing is suitable for gathering information and assessing damage situations as it can adjust the type and number of workers in a scalable manner and allocate resources according to the size of the disaster. Therefore, crowdsourcing has been used for gathering information and assessing the situation during disaster management. However, usually, the two types of crowdsourcing tasks (i.e., gathering information and assessing the damage) are performed independently;consequently, the collected information is often not utilized effectively. More efficient work can be expected by linking the two crowdsourcing tasks. This paper proposes a framework for efficiently generating a building damage map by combining the two methods of information collection on disaster areas and assessment of disaster situations using aerial image processing. The results of an experiment using a prototype of our proposed framework clarify the range of applications in the collection and assessment crowdsourcing tasks. The experimental results indicate the feasibility of understanding disaster situations using our method. In addition, it is possible to install artificial intelligence workers that can support human workers to es

关键词： crowdsourcing aerial image processing bullet-time video building damage map

来源：评论

学校读者我要写书评

暂无评论

ECDet: efficient oriented object detection on the aerial image with cross-layer attention

引用

JOURNAL OF REAL-TIME image processing 2025年第1期22卷 1-13页

作者： Lyu, Xueqiang Tian, Lianghai Teng, Shangzhi Beijing Informat Sci & Technol Univ Beijing Key Lab Internet Culture Digital Dissemina Beijing 100192 Peoples R China

With advancements in horizontal object detection models, oriented object detection models have also made significant strides. Yet existing rotated object detectors often struggle to maintain high accuracy while processing high-resolution remote sensing images in real-time. To address these challenges, we propose a new lightweight model specifically for oriented object detection, named the efficient cross-layer attention detector (ECDet). ECDet integrates several efficient modules, including an efficient reparameterized Transformer-like backbone (ERepViT) to reduce computational costs, and the efficient cross-layer fusion neck (CLF-Neck), a lightweight alternative to traditional pyramid networks for feature fusion with attention mechanism. Additionally, we introduce the lightweight task interaction decoupled (LTID) head, which enhances task-specific performance by providing more detailed, task-aligned information for classification and regression with minimal computational cost. Furthermore, an ensemble loss combined with the phase shifting coder (PSC) mitigates the angle discontinuity issue in regression-based methods. Evaluations on the DOTAv1 and HRSC datasets show that ECDet runs 32% faster than RTMDet-S with higher accuracy, demonstrating its strong potential for practical application. The source code will be release at https://***/tianlianghai/ECDet.

关键词： Rotated object detection Lightweight neural network aerial image processing Cross-layer attention RTMDet

来源：评论

学校读者我要写书评

暂无评论

A Confounder-Free Fusion Network for aerial image Scene Feature Representation

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 5440-5454页

作者： Xiong, Wei Xiong, Zhenyu Cui, Yaqi Naval Aviat Univ Res Inst Informat Fus Yantai 264001 Peoples R China

The increasing number and complex content of aerial images have made some recent methods based on deep learning not fit well with different aerial image processing tasks. The coarse-grained feature representation proposed by these methods is not discriminative enough. Besides, the confounding factors in the datasets and long-tailed distribution of the training data will lead to biased and spurious associations among the objects of aerial images. This study proposes a confounder-free fusion network (CFF-NET) to address the challenges. Global and local feature extraction branches are designed to capture comprehensive and fine-grained deep features from the whole image. Specifically, to extract the discriminative local feature and explore the contextual information across different regions, the models based on gated recurrent units are constructed to extract features of the image region and output the important weight of each region. Furthermore, the confounder-free object feature extraction branch is proposed to generate reasonable visual attention and provide more multigrained image information. It also eliminates the spurious and biased visual relationships of the image on the object level. Finally, the output of the three branches is combined to obtain the fusion feature representation. Extensive experiments are conducted on the three popular aerial image processing tasks: 1) image classification, 2) image retrieval, and 3) image captioning. It is found that the proposed CFF-NET achieves reasonable and state-of-the-art results, including high-level tasks such as aerial image captioning.

关键词： Feature extraction Task analysis image processing image classification Semantics image retrieval Visualization aerial image processing causal inference feature representation visual attention

来源：评论

学校读者我要写书评

暂无评论

Automatic Rooftop Extraction in Nadir aerial imagery of Suburban Regions Using Corners and Variational Level Set Evolution

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2013年第1期51卷 313-328页

作者： Cote, Melissa Saeedi, Parvaneh Simon Fraser Univ Sch Engn Sci Lab Robot Vis Burnaby BC V5A 1S6 Canada

Building profile extraction from aerial imagery constitutes a key element in numerous geospatial applications. Rooftop detection has been addressed through a variety of approaches that are, however, rarely capable of coping with conditions such as arbitrary illumination, variant reflections, and complex building profiles. This paper proposes a new method for extracting 2-D rooftop footprints from nadir aerial imagery through a fully automatic approach that handles arbitrary illumination, variant reflections, and complex building profiles without shape priors. The proposed method combines the strength of energy-based approaches with distinctiveness of corners. Corners are assessed using multiple color and color-invariance spaces. A rooftop outline is generated from selected corner candidates and further refined to fit the best possible boundaries through level-set curve evolution that is enhanced via a mean squared error map. Experimental results confirm the ability of the presented system to effectively extract rooftop profiles with an overall average shape accuracy of 84%, correctness of 94%, completeness of 92%, and quality of 88%.

关键词： aerial image processing boundary detection building extraction level set evolution

来源：评论

学校读者我要写书评

暂无评论

Vision-based Human Identification with Face and Nametape Recognition in aerial Casualty Monitoring System 32

Vision-based Human Identification with Face and Nametape Rec...

引用

32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

作者： Lee, Jaeyeon Quist, Ethan Chambers, Jonathan Peel, Justin Roman, Kelly Fisher, Nathan TATRC Ft Detrick MD 21702 USA Arete Arlington VA USA

ISBN: (纸本)9798350336702

In emergency rescue scenarios, rapid identification of human casualties is a critical first step in enhancing emergency medical response. This task can be limited by the physical and cognitive capacity of rescue personnel, who are exposed to significant risk. The use of small unmanned aerial systems (sUAS) equipped with autonomous casualty assessment abilities can reduce these limitations and risks by enabling remote casualty detection, identification, and vitals assessment, providing standoff protection, and eliminating the need for human personnel to access the potentially hazardous scene. This paper presents a vision-based casualty assessment framework and specifically discusses our casualty identification software, which is designed to recognize the faces of casualties and identify their nametapes in images captured by sUAS under realistic conditions. Our approach addresses the limitations of the sUAS-captured long-distance images to enable accurate identification in challenging casualty monitoring situations. The face and nametape recognition algorithms will be integrated into the larger casualty perception framework and embedded into sUAS platforms to assist with emergency rescue operations. The total casualty perception system will detect, identify, and evaluate the condition of casualties from a remote location, providing standoff protection to first responders and rapid information to inform a suitable medical treatment plan.

关键词： aerial image processing Neural network Face and text recognitions Synthetic text data Human detection identification monitoring Unmanned aerial Systems

来源：评论

学校读者我要写书评

暂无评论

A new method to combine detection and tracking algorithms for fast and accurate human localization in UAV-based SAR operations

A new method to combine detection and tracking algorithms fo...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Lygouras, Eleftherios Gasteratos, Antonios Democritus Univ Thrace Dept Prod & Management Engn Xanthi Greece

ISBN: (纸本)9781728142784

This paper presents the study and the evaluation of GPS/GNSS techniques combined with advanced image processing algorithms for the precise detection, positioning and tracking of distressed humans. In particular, the issue of human detection on both terrestrial and marine environments, as the human silhouette in a marine environment may differ substantially from a land one, is addressed. A robust approach, including an adaptive distressed human detection algorithm running every N input image frames combined with a much faster human tracking algorithm, is proposed. Real time or near-real-time distressed human detection rates, under several illumination and background conditions, can be achieved using a single, low cost day/night NIR camera. It is mounted onboard a fully autonomous UAV for Search and Rescue (SAR) missions. Moreover, the collection of a novel dataset, suitable for training the computer vision algorithms is also presented. Details about both hardware and software configuration as well as the assessment of the proposed approach performance are discussed. Last, a comparison of the proposed approach to other human detection methods used in the literature is presented.

关键词： human detection unmanned aerial vehicles (UAVs) search and rescue (SAR) missions aerial image processing

来源：评论

学校读者我要写书评

暂无评论

Automatic Building Detection in aerial and Satellite images

Automatic Building Detection in Aerial and Satellite Images

引用

10th International Conference on Control, Automation, Robotics and Vision

作者： Saeedi, Parvaneh Zwick, Harold Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada Dettwiler & Assoc Ltd Dept Res & Dev MacDonald Richmond BC Canada

ISBN: (纸本)9781424422869

Automatic creation of 3D urban city maps could be an innovative way for providing geometric data for varieties of applications such as civilian emergency situations, natural disaster management, military situations, and urban planning. Reliable and consistent extraction of quantitative information from remotely sensed imagery is crucial to the success of any of the above applications. This paper describes the development of an automated roof detection system from single monocular electro-optic satellite imagery. The system employs a fresh approach in which each input image is segmented at several levels. The border line definition of such segments combined with line segments detected on the original image are used to generate a set of quadrilateral rooftop hypotheses. For each hypothesis a probability score is computed that represents the evidence of true building according to the image gradient field and line segment definitions. The presented results demonstrate that the system is capable of detecting small gabled residential rooftops with variant light reflection properties with high positional accuracies.

关键词： Building extraction satellite image processing aerial image processing photogrammetry computer vision geometrical shape extraction

来源：评论

学校读者我要写书评

暂无评论

aerial monitoring and measurement of forest fires

Aerial monitoring and measurement of forest fires

引用

Enhanced and Synthetic Vision 2002 Conference

作者： Merino, L Gómez-Rodríguez, F Arrue, BC Ollero, A Escuela Super Ingn Seville 41092 Spain

ISBN: (纸本)0819444634

This paper presents a system for forest fire monitoring using aerial images. The system uses the images taken from a helicopter, the GPS position of the helicopter, and information from a Geographic Information System (GIS) to locate the fire and to estimate in real-time their properties. Currently, the images are taken by a non-stabilized camera. Then, image processing for image stabilization and movement estimation is applied to cancel the vibration and to estimate the change in the camera orientation. Another image processing stage is the computation of the fire front and flame height features in the images. This process is based on color processing and thresholding, followed by contour computation. Finally, the fire front is automatically geo-located by projecting the features over the terrain model obtained from the GIS. Furthermore, an estimation of the flame height is obtained. The aerial image processing, automatic georeferencing and measurement has been integrated in a forest fire fire monitoring system in which several moving or fixed visual and infrared cameras can be used. The system provides in real-time the evolution of the fire-front and the flame height, and obtains a 3D perception model of the fire. Moreover, the fire evolution can be also included and represented in the ARC-INFO GIS. The paper shows some results obtained with the application with images taken in real forest-fire experiments, carried out in Gestosa (Portugal) on June 2000 in the framework of the INFLAME project funded by the European Commission.

关键词： aerial image processing automatic georeferencing forest fire fighting data fusion GPS

来源：评论

学校读者我要写书评

暂无评论

Map Generation from Large Scale Incomplete and Inaccurate Data Labels 20

Map Generation from Large Scale Incomplete and Inaccurate Da...

引用

26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Zhang, Rui Albrecht, Conrad Zhang, Wei Cui, Xiaodong Finkler, Ulrich Kung, David Lu, Siyuan IBM TJ Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)9781450379984

Accurately and globally mapping human infrastructure is an important and challenging task with applications in routing, regulation compliance monitoring, and natural disaster response management etc.. In this paper we present progress in developing an algorithmic pipeline and distributed compute system that automates the process of map creation using high resolution aerial images. Unlike previous studies, most of which use datasets that are available only in a few cities across the world, we utilizes publicly available imagery and map data, both of which cover the contiguous United States (CONUS). We approach the technical challenge of inaccurate and incomplete training data adopting state-of-the-art convolutional neural network architectures such as the U-Net and the CycleGAN to incrementally generate maps with increasingly more accurate and more complete labels of man-made infrastructure such as roads and houses. Since scaling the mapping task to CONUS calls for parallelization, we then adopted an asynchronous distributed stochastic parallel gradient descent training scheme to distribute the computational workload onto a cluster of GPUs with nearly linear speed-up.

关键词： remote sensing geo-spatial analysis image segmentation semi-supervised learning aerial image processing map generation deep neural networks U-Net CycleGAN

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：