相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Geochemistry & Geophysics
Wenxuan Han et al.
Summary: This paper proposes a multi-vision small object detector for accurate and rapid detection of airplanes, cars, and ships in remote sensing images. The method improves the feature representation ability of convolutional neural networks by introducing multiscale residual blocks, multiscale receptive field enhancement modules, and a multi-vision network. Experimental results demonstrate significant detection performance of the proposed method.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Wen Tao Li et al.
Summary: This article proposes an efficient oriented bounding box (OBB) detection technique for remote sensing images, and introduces a new backbone network to address the issue of small and multiscale object features being lost in deep networks. Experimental results demonstrate the superiority of the proposed method.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Jingyu Wang et al.
Summary: This letter proposes an end-to-end feature-reflowing pyramid network (FRPNet) for geospatial object detection. The network incorporates a nonlocal block and a feature-reflowing pyramid structure to improve detection accuracy for multiscale and multiclass objects.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Ke Zhang et al.
Summary: This paper proposes a semantic context-aware network (SCANet) model for multiscale object detection, with the use of receptive field-enhancement module (RFEM) and semantic context fusion module (SCFM) to enhance performance. Experimental results show that SCANet achieves superior detection results on the DOTA-v1.5 dataset compared to state-of-the-art approaches.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Leyang Li et al.
Summary: The letter proposes a simple convolutional neural network for object detection in aerial images, which shows good performance in efficiency and model size for resource-limited satellite networks.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Jing Bai et al.
Summary: This study proposes a method for object detection in large-scale remote-sensing images with complex backgrounds, which combines time-frequency analysis and deep learning for feature optimization, effectively addressing the challenges of large-scale images and complex backgrounds.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Tianyang Zhang et al.
Summary: The proposed refined rotation detector, the Foreground Refinement Network (FoRDet), leverages foreground region information to alleviate the high background complexity in remote sensing images.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Tao Xu et al.
Summary: The study introduces an efficient feature aligned single-shot detector to address the feature misalignment issue in object detection, achieving promising experimental results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Wenping Ma et al.
Summary: In this study, a scale-aware network called SME-Net is proposed for remote sensing object detection. It consists of the FSM module, OER module, and OSE strategy to address the challenges of large and small object detection balance, feature inconsistency, and noise interference in high-resolution remote sensing images. The effectiveness of the algorithm has been demonstrated on multiple datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Zhanchao Huang et al.
Summary: Object detection is an important task in computer vision and has wide applications in remote sensing. However, the complexity, large-scale variation, and dense instances in remote sensing pose significant challenges for object detection. To address these challenges, a novel Nonlocal-aware Pyramid and Multiscale Multitask Refinement Detector is proposed, which utilizes nonlocal-aware pyramid attention and multiscale refinement feature pyramid network to improve detection performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Runmin Cong et al.
Summary: This article proposes a relational reasoning network (RRNet) with parallel multiscale attention (PMA) for salient object detection (SOD) in optical remote sensing images (RSIs). By integrating the spatial and channel dimensions and utilizing high-level encoder features, the RRNet infers semantic relationships and generates more complete detection results. The PMA module effectively restores detailed information and addresses scale variation of salient objects.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Tong Zhang et al.
Summary: This article proposes a powerful one-stage detector named MSFC-Net for optical remote sensing object detection, which aims to improve performance through semantic fusion and novel convolution layer design. Experimental results demonstrate that MSFC-Net outperforms other state-of-the-art one-stage detectors on the DOTA and DIOR datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Zhanchao Huang et al.
Summary: In this article, the authors propose a lightweight oriented object detector (LO-Det) for remote sensing object detection. They design a channel separation-aggregation (CSA) structure and a dynamic receptive field (DRF) mechanism to optimize efficiency and accuracy. They also introduce a diagonal support constraint head (DSC-Head) component to accurately and stably constrain the shape of oriented bounding boxes (OBBs). Experimental results demonstrate that LO-Det achieves fast runtime and competitive accuracy on embedded devices.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Guanqun Wang et al.
Summary: The paper introduces a novel one-stage object detection network, which has achieved good performance in processing optical remote sensing images. By utilizing the improved multiscale enhancement network and scale-invariant regression layers, the network effectively enhances the accuracy of object detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Yuanxin Ye et al.
Summary: For remote sensing object detection, the existing convolutional neural networks face the challenge of automatically fusing optimal feature information and overcoming sensitivity to adapt to multi-scale objects. In this study, a convolutional network model with an adaptive attention fusion mechanism is proposed, which addresses these challenges by using a stitcher to handle multi-scale objects and introducing a spatial attention model. Experimental results demonstrate that the proposed model improves accuracy and has stronger robustness compared to other state-of-the-art detectors.
Article
Environmental Sciences
Jiahang Liu et al.
Summary: This article proposes an object detection algorithm for remote sensing images based on multi-receptive-field features and relation-connected attention. The algorithm utilizes dilated convolution to aggregate context information from different receptive fields, allowing for better adaptation to object scale changes in complex scenarios. The inclusion of a relation-connected attention module, which combines both global and local attention, enhances feature discriminability and detector robustness. Experimental results demonstrate that these modules effectively improve the performance of basic deep CNNs and achieve better results in multi-scale object detection in complex backgrounds.
Article
Computer Science, Information Systems
Jinkang Wang et al.
Summary: In this paper, an end-to-end multi-size object detection method based on a dual attention mechanism is proposed to address the challenges of object detection in remote sensing images. The method effectively utilizes attention mechanisms, feature fusion, and adaptive loss functions to accurately detect multi-type, multi-size, and multi-posture targets in complex scenes.
Article
Computer Science, Artificial Intelligence
Dongjun Zhu et al.
Summary: A novel remote sensing image object detection method was proposed in this paper, which utilizes a spatial hierarchy perception component and hard samples metric learning to extract features under different spatial hierarchies, reduce feature differences of hard samples in the same category, and strengthen object feature learning by decoupling complex backgrounds. Experimental results demonstrate that the proposed method outperforms several state-of-the-art object detection methods in terms of detection performance.
APPLIED INTELLIGENCE
(2022)
Article
Geochemistry & Geophysics
Yuan Cheng et al.
Summary: This letter presents a novel transmitted scheme for a multisubcarrier frequency MIMO-SAR system, aiming to suppress intrapulse repeater mainlobe-jamming and greatly improve receiver's dynamic range. The proposed scheme separates mixed signals containing true target signal and repeater jamming using a well-designed spatial-frequency filter. Accurate estimation of range and direction of arrival information is achieved without interrupting radar's normal operation. Additionally, a phase-coded LFM waveform pair is designed to improve transmitted waveform orthogonality, and an ADMM-based optimization method is used to handle the resulting NP-hard problem.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Yulin Wu et al.
Summary: The paper introduces a novel global context-weaving network (GCWNet) for object detection in remote sensing images, with two novel modules for feature extraction and refinement - the global context aggregation module (GCAM) and the feature refinement module (FRM. It also addresses the sample imbalanced problem during training using focal loss and balanced L1 loss to improve object classification and regression.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Yanfeng Liu et al.
Summary: In this article, we propose an adaptive balanced network (ABNet) to address the challenges of remote sensing object detection. Our approach utilizes an enhanced effective channel attention mechanism (EECA), an adaptive feature pyramid network (AFPN) and a context enhancement module (CEM) to improve feature representation and capture more discriminative features. Experimental results demonstrate the superior performance of our approach.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Ying Yu et al.
Summary: This article proposes a novel cascade rotated anchor-aided detection network for high-precision performance in detecting arbitrary-oriented ships in high-resolution remote sensing images. The network overcomes the limitations of state-of-the-art object detection methods applied directly to real ship detection through data preprocessing and a rotated anchor-aided detection module. Experimental results on challenging datasets demonstrate that the proposed method outperforms other methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Gong Cheng et al.
Summary: There are many groundbreaking object detection frameworks used in natural scene images, but applying them directly to remote sensing images is not very effective. This paper proposes an end-to-end cross-scale feature fusion (CSFF) framework to address the challenges of object detection in optical remote sensing images, achieving a 3.0% improvement in mAP on the DIOR dataset compared to Faster R-CNN with FPN.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Environmental Sciences
Wei Huang et al.
Summary: With the advancements in remote sensing technology, the interest in remote sensing target detection has grown. Traditional multi-scale detection methods have limitations and a new approach is needed to tackle the challenges posed by variations in object size.
Article
Chemistry, Analytical
Lei Lang et al.
Summary: The study introduces a lightweight object detection method for remote sensing images, achieving high-speed and high-accuracy detection through efficient channel attention layers and differential evolution algorithm. Experimental results show that the network outperforms existing lightweight models in accuracy and performs well on embedded boards.
Article
Engineering, Electrical & Electronic
Nanqing Liu et al.
Summary: In this article, a more accurate and faster detector named AFDet is proposed for object detection in remote sensing imagery. AFDet consists of a backbone pretrained on ImageNet and a head that includes a center prediction branch, semantic supervision branch, and boundary estimation branch, achieving state-of-the-art results on widely used optical remote sensing object detection datasets.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Geography, Physical
Ke Li et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Article
Environmental Sciences
Xiaoliang Qian et al.
Article
Geography, Physical
Haoran Wei et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Proceedings Paper
Geosciences, Multidisciplinary
Hao Su et al.
2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019)
(2019)
Article
Geochemistry & Geophysics
Yang Long et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2017)
Article
Remote Sensing
Zhifeng Xiao et al.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2015)
