检索结果-内蒙古大学图书馆

An Oriented object Detector for Hazy Remote Sensing Images

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

作者： Liu, Bo Chen, Si-Bao Wang, Jia-Xin Tang, Jin Luo, Bin Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat MOE Key Lab ICSPIMIS Lab Anhui ProvZenmorn AHU A Hefei 230601 Peoples R China Anhui Univ Sci & Technol Huainan 232002 Peoples R China

Currently, a lot of work is focused on aerial object detection and has achieved good results. Though these methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality images captured in adverse weather conditions. Currently, there are limited approaches that combine aerial object detection with hazy conditions, and there are few publicly available datasets for real hazy weather based on aerial images. For this purpose, we propose a dataset HRSI, hazy remote sensing images in the real world, which is mainly divided into three categories: airport, large vehicle, and ship. All images in HRSI are from real hazy conditions. In addition, we propose an object detection model DFENet, a dehazing feature enhancement model for hazy remote sensing images, which is suitable for hazy weather. DFENet consists of a two-branch and a dehazing module. The two-branch structure helps to fully learn hazy and dehazing features. In order to avoid the impact of noise caused by the dehezing module, we also designed a haze-predict module (HPM) to predict the information containing haze in the image. We introduce the cross-fuse module (CFM) to utilize the information of haze to guide the feature fusion of two branches. By utilizing the information of haze, DFENet can dynamically adjust the feature weight in the two-branch to avoid the impact of noise generated by the dehazing module. Compared with traditional object detection methods, DFENet not only has good performance in hazy conditions but also improves performance in clear conditions. We tested DFENet on DOTA, HRSI, and Foggy-DOTA to demonstrate that DFENet performs better under hazy conditions.

关键词： object detection Feature extraction Remote sensing Adaptation models Atmospheric modeling Meteorology Training aerial object detection hazy object detection weakly supervised

来源：评论

学校读者我要写书评

暂无评论

Rebalancing Gaussian Location Loss for High-Precision detection on Remote Sensing Images

引用

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

作者： Li, Zhonghua Hou, Biao Wu, Zitong Guo, Xianpeng Ren, Bo Ren, Zhongle Yang, Chen Jiao, Licheng Minist Educ China Key Lab Intelligent Percept & Image Understanding Xian Peoples R China Xidian Univ Joint Int Res Lab Intelligent Percept & Computat Xian 710071 Peoples R China

aerial image objects are usually orientated arbitrarily, with a large scale range, and densely distributed. Traditional horizontal bounding box (HBB) detectors tend to filter out densely distributed objects leading to missed detections, such as ship (SH) and vehicle. Therefore, oriented object detection has become a mainstream solution in recent years. The 2-D Gaussian distribution representation of the oriented bounding boxes (OBBs) solves the problem of angular discontinuity and boundary discontinuity and thus gets more attention. However, as the aspect ratio of the object gradually decreases, its predicted angular performance continues to decrease. We find that the angular gradient of an object decreases sharply as the aspect ratio decreases, resulting in a large gradient gap between a small aspect ratio object (SARO) and a large aspect ratio object (LARO). It makes the detector prefer to ignore SARO during training, which weakens the high precision performance of SARO. We call this phenomenon shape imbalance. To solve the problem, we proposed a simple gradient rebalancing strategy named shape balance. Since the shape imbalance is only related to the aspect ratio of the object, we designed a modulation function with an inverse aspect ratio to calculate the balance coefficient. The principle of the function is that the larger the aspect ratio, the smaller the balance coefficient;the smaller the aspect ratio, the larger the balance coefficient. We aim to get the balance coefficients for objects with different aspect ratios. Location loss multiplied by a balance coefficient can directly adjust the gradient gap between objects with different aspect ratios to achieve a rebalancing effect. Extensive experiments conducted on DOTA-v1.0 dataset and DIOR-R dataset verify the effectiveness of our proposed method. Our method improves the detection performance of Gaussian location loss by an average of 2.08%/1.01%(AP(75)/mAP) metrics on the DOTA-v1.0 dataset and 1.17%/0.82%(A

关键词： Shape Detectors Measurement Location awareness Gaussian distribution Probability distribution Remote sensing object detection Airplanes Visualization aerial object detection oriented object detection shape imbalance

来源：评论

学校读者我要写书评

暂无评论

MStrans: Multiscale Vision Transformer for aerial objects detection

引用

IEEE ACCESS 2022年 10卷 75971-75985页

作者： Lu, Guanlin He, Xiaohui Wang, Qiang Shao, Faming Wang, Jinkang Hao, Likai PLA Army Engn Univ Dept Mech Engn Coll Field Engn Nanjing 210007 Peoples R China

Detecting objects in aerial images is a challenging task due to the large-scale variations and arbitrary orientations with tiny instances. A new multi-scale transformer-based aerial objects detector called MStrans is proposed in this paper to deal with the challenges in aerial detection. To detect remote instances, MStrans adopts a multi-scale patch embedding transformer (MViT) to extract the global features of the image effectively. Furthermore, to capture the different discriminant features for classification and regression branch tasks, the partial interactive fusion module (PIFM) is designed to enhance the semantic expression of the key features of classification and regression tasks by using the strategy of interactive modeling of adjacent layer features. In addition, considering that the transformer may worsen the local feature details while capturing long-distance feature dependencies, this paper designs a global to local interactive fusion module (GLIFM). It uses the advantage of convolution to extract local features to enrich the detailed information in the transformer. Experiments were carried out on DOTA and DIOR datasets, and the MStrans achieves superior detection performances compared with other approaches.

关键词： object detection Transformers Feature extraction Task analysis Detectors Convolution Autonomous aerial vehicles aerial object detection deep learning multiscale object detection transformer CNN

来源：评论

学校读者我要写书评

暂无评论

Zoom-and-Reasoning: Joint Foreground Zoom and Visual-Semantic Reasoning detection Network for aerial Images

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 2572-2576页

作者： Ge, Zuhao Qi, Lizhe Wang, Yuzheng Sun, Yunquan Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

aerial image object detection remains rather challenging, due to the small object gathering and confusion of inter-class similarities and intra-class diversity. Confronting such challenges, we propose a two-stage framework, 'Zoom & Reasoning Det,' which performs detection in a foreground highlight manner and leverages contextual relations to assist detection. In the coarse foreground zoom stage, different from earlier works that divide original images into patches and perform detection on each patch separately, we design Foreground Zoom Strategy (FZS), which zooms foreground dense regions from a coarse detector and packs them into one image. In the fine reasoning detect stage, motivated by a human visual mechanism that can achieve correct recognition by reasoning through context, we present Visual-Semantic Reasoning Network (VSRNet), consisting of Visual Reasoning Graph (VRG) and Semantic Reasoning Graph (SRG), simultaneously considering local visual and global semantic contextual relational information for each instance. Each instance feature representation is further refined by aggregating the outputs of VSRNet. Comprehensive experiments conducted on two challenging aerial image datasets, VisDrone and UAVDT, demonstrate the advantage of our method over the state-of-the-art.

关键词： Cognition Detectors Visualization Semantics Feature extraction object detection Pipelines aerial object detection contextual relation graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

LENet: Lightweight and Effective Detector for aerial object

引用

UNMANNED SYSTEMS 2024年第6期12卷 1105-1121页

作者： Zhou, Xunkuai Li, Li Chen, Ben M. Tongji Univ Sch Elect & Informat Engn Shanghai Peoples R China Chinese Univ Hong Kong Dept Mech & Automat Engn Hong Kong Peoples R China

aerial object detection is crucial in various computer vision tasks, including video monitoring, early warning systems, and visual tracking. While current methods can accurately detect normal-sized objects, they face challenges distinguishing small objects from cluttered backgrounds. Developing methods that can be deployed on edge devices to achieve fast, accurate, and energy-efficient performance is also an urgent challenge. This paper proposes a network for aerial object detection by incorporating an attention mechanism to enhance feature extraction and elevate the accuracy of aerial moving object detection. Additionally, we optimize the channel dimensions of the feature extraction framework, resulting in a reduction in model parameters, acceleration of inference speed, and alleviation of the computational burden. Ulteriorly, we optimize the Spatial Pyramid Pooling (SPP) module to enhance detection accuracy and processing speed. Inspired by the ResNet and RepVGG structures, we design a feature fusion module to combine early-extracted features, improving speed and accuracy. Based on the design mentioned above principles, we develop a neural network method with an impressively small model size of only 4.5M. The proposed approach achieves state-of-the-art performance on five benchmark datasets. Besides its superior performance, our method demonstrates excellent throughput on edge computing devices. Experimental results show that even when running on low-performance computing devices, the CPU and GPU temperatures remain below 50 degrees C and achieve a detection speed of 14.8 frames per second (fps) and power consumption of only 2.9W. These findings suggest that a high-accuracy, low-power, low-latency, and low-memory footprint aerial object detection solution is achievable.

关键词： aerial object detection energy-efficient edge computing deep learning

来源：评论

学校读者我要写书评

暂无评论

DSENET: AN object-WISE DENSITY-INFORMED COARSE-TO-FINE object DETECTOR FOR aerial IMAGE

DSENET: AN OBJECT-WISE DENSITY-INFORMED COARSE-TO-FINE OBJEC...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jiang, Haoran Wang, Xiangjie Zhang, Junjie Zhang, Jian Zeng, Dan Shanghai Univ Shanghai Peoples R China Univ Technol Sydney Sydney NSW Australia

ISBN: (纸本)9798350390155;9798350390162

object detection in aerial images remains formidable due to substantial object scale variations, and uneven object distributions. Previous methods widely adopt the coarse-tofine methodology where detectors focus on large-scale objects coarsely. Sub-regions that contain densely distributed small ones are captured and detected finely. However, two pivotal assessment factors of sub-regions, positional precision, and detection difficulty, deserve further consideration. In this paper, we propose an object-wise density-informed DSENet including consecutive stages termed "Discernment, Selection, Elevation". Specifically, the sophisticated objectwise density map that considers both object scales and angles, helps discern more positional-precise sub-regions. Then subregions with high detection difficulty are selected based on density intensities and coarse detections collaboratively. Finally, the fine detector head instead of the full detector, finetuned with selected sub-regions efficiently, elevates what and where coarse detections are mediocre. Extensive experiments show that DSENet achieves state-of-the-art performance on two popular aerial image datasets, VisDrone and DOTA-V1.5.

关键词： aerial object detection Discernment Selection Elevation DOTA-V1.5 VisDrone

来源：评论

学校读者我要写书评

暂无评论

Active Interactive Labelling Massive Samples for object detection 23

Active Interactive Labelling Massive Samples for Object Dete...

引用

11th ACM Symposium on Spatial User Interaction (SUI)

作者： Zhang, Jingwei Zhang, Mingguang Guo, Yi Qiu, Mengyu Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Xian Peoples R China

ISBN: (纸本)9798400702815

aerial object detection is the process of detecting objects in remote sensing images, such as aerial or satellite imagery. However, due to the unique characteristics and challenges of remote sensing images, such as large image sizes and dense distribution of small objects, annotating the data is time-consuming and costly. Active learning methods can reduce the cost of labeling data and improve the model's generalization ability by selecting the most informative and representative unlabeled samples. In this paper, we studied how to apply active learning techniques to remote sensing object detection tasks and found that traditional active learning frameworks are not suitable. Therefore, we designed a remote sensing task-oriented active learning framework that can more efficiently select representative samples and improve the performance of remote sensing object detection tasks. In addition, we proposed an adaptive weighting loss to further improve the generalization ability of the model in unlabeled areas. A large number of experiments conducted on the remote sensing dataset DOTA-v2.0 showed that applying various classical active learning methods to the new active learning framework can achieve better performance.

关键词： aerial object detection active learning aerial remote sensing image

来源：评论

学校读者我要写书评

暂无评论

FastAER Det: Fast aerial Embedded Real-Time detection

引用

REMOTE SENSING 2021年第16期13卷 3088-3088页

作者： Wolf, Stefan Sommer, Lars Schumann, Arne Fraunhofer IOSB Inst Optron Syst Technol & Image Exploitat Fraunhoferstr 1 D-76131 Karlsruhe Germany Karlsruhe Inst Technol KIT Vis & Fus Lab Technologiefabrik Haid und Neu Str 7 D-76131 Karlsruhe Germany Fraunhofer Gesell Forderung Angewandten Forsch eV Fraunhofer Ctr Machine Learning Hansastr 27 c D-80686 Munich Germany

Automated detection of objects in aerial imagery is the basis for many applications, such as search and rescue operations, activity monitoring or mapping. However, in many cases it is beneficial to employ a detector on-board of the aerial platform in order to avoid latencies, make basic decisions within the platform and save transmission bandwidth. In this work, we address the task of designing such an on-board aerial object detector, which meets certain requirements in accuracy, inference speed and power consumption. For this, we first outline a generally applicable design process for such on-board methods and then follow this process to develop our own set of models for the task. Specifically, we first optimize a baseline model with regards to accuracy while not increasing runtime. We then propose a fast detection head to significantly improve runtime at little cost in accuracy. Finally, we discuss several aspects to consider during deployment and in the runtime environment. Our resulting four models that operate at 15, 30, 60 and 90 FPS on an embedded Jetson AGX device are published for future benchmarking and comparison by the community.

关键词： aerial object detection deep learning based detection embedded platforms runtime optimization

来源：评论

学校读者我要写书评

暂无评论

SAFDet: A Semi-Anchor-Free Detector for Effective detection of Oriented objects in aerial Images

引用

REMOTE SENSING 2020年第19期12卷 3225-3225页

作者： Fang, Zhenyu Ren, Jinchang Sun, He Marshall, Stephen Han, Junwei Zhao, Huimin Guangdong Polytech Normal Univ Sch Comp Sci Guangzhou 510665 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow G1 1XQ Lanark Scotland Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Northwestern Polytech Univ Sch Automat Xian 710109 Peoples R China

An oriented bounding box (OBB) is preferable over a horizontal bounding box (HBB) in accurate object detection. Most of existing works utilize a two-stage detector for locating the HBB and OBB, respectively, which have suffered from the misaligned horizontal proposals and the interference from complex backgrounds. To tackle these issues, region of interest transformer and attention models were proposed, yet they are extremely computationally intensive. To this end, we propose a semi-anchor-free detector (SAFDet) for object detection in aerial images, where a rotation-anchor-free-branch (RAFB) is used to enhance the foreground features via precisely regressing the OBB. Meanwhile, a center-prediction-module (CPM) is introduced for enhancing object localization and suppressing the background noise. Both RAFB and CPM are deployed during training, avoiding increased computational cost of inference. By evaluating on DOTA and HRSC2016 datasets, the efficacy of our approach has been fully validated for a good balance between the accuracy and computational cost.

关键词： rotate region convolutional neural network anchor free aerial object detection

来源：评论

学校读者我要写书评

暂无评论

DCEF²-YOLO: aerial detection YOLO with Deformable Convolution-Efficient Feature Fusion for Small Target detection

引用

REMOTE SENSING 2024年第6期16卷 1071页

作者： Shin, Yeonha Shin, Heesub Ok, Jaewoo Back, Minyoung Youn, Jaehyuk Kim, Sungho Yeungnam Univ Dept Elect Engn Adv Visual Intelligence Lab 280 Daehak Ro Gyongsan 38541 South Korea LIG Nex1 Co Ltd Yongin 16911 South Korea

Deep learning technology for real-time small object detection in aerial images can be used in various industrial environments such as real-time traffic surveillance and military reconnaissance. However, detecting small objects with few pixels and low resolution remains a challenging problem that requires performance improvement. To improve the performance of small object detection, we propose DCEF (2)-YOLO. Our proposed method enables efficient real-time small object detection by using a deformable convolution (DFConv) module and an efficient feature fusion structure to maximize the use of the internal feature information of objects. DFConv preserves small object information by preventing the mixing of object information with the background. The optimized feature fusion structure produces high-quality feature maps for efficient real-time small object detection while maximizing the use of limited information. Additionally, modifying the input data processing stage and reducing the detection layer to suit small object detection also contributes to performance improvement. When compared to the performance of the latest YOLO-based models (such as DCN-YOLO and YOLOv7), DCEF (2)-YOLO outperforms them, with a mAP of +6.1% on the DOTA-v1.0 test set, +0.3% on the NWPU VHR-10 test set, and +1.5% on the VEDAI512 test set. Furthermore, it has a fast processing speed of 120.48 FPS with an RTX3090 for 512 x 512 images, making it suitable for real-time small object detection tasks.

关键词： aerial object detection small target detection real-time object detection DCN deformable convolution feature fusion

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：