Remote Sensing Image Object Detection Based on Angle Classification

Shi, Pengfei; Zhao, Zhijun; Fan, Xiaopeng; Yan, Xijun; Yan, Wei; Xin, Yuanxue

doi:10.1109/access.2021.3107358

Cited by 15 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RODFormer is compared with 12 rotating object detection methods (RRPN [ 3 ], R 2 CNN [ 4 ], RoI-Transformers [ 5 ], CADNet [ 31 ], DRN [ 32 ], ICN [ 33 ], RADet [ 34 ], SCRDet [ 6 ], MFIAR-Net [ 22 ], IRetinaNet [ 35 ], PolarDet [ 20 ] and S 2 A-Net [ 21 ]) to verify its detection accuracy. Table 4 summarizes the detection results of different models for 15 categories in the DOTA dataset.…”

Section: Methodsmentioning

confidence: 99%

RODFormer: High-Precision Design for Rotating Object Detection with Transformers

Dai

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Aiming at the problem of Transformers lack of local spatial receptive field and discontinuous boundary loss in rotating object detection, in this paper, we propose a Transformer-based high-precision rotating object detection model (RODFormer). Firstly, RODFormer uses a structured transformer architecture to collect feature information of different resolutions to improve the collection range of feature information. Secondly, a new feed-forward network (spatial-FFN) is constructed. Spatial-FFN fuses the local spatial features of 3 × 3 depthwise separable convolutions with the global channel features of multilayer perceptron (MLP) to solve the deficiencies of FFN in local spatial modeling. Finally, based on the space-FFN architecture, a detection head is built using the CIOU-smooth L1 loss function and only returns to the horizontal frame when the rotating frame is close to the horizontal, so as to alleviate the loss discontinuity of the rotating frame. Ablation experiments of RODFormer on the DOTA dataset show that the Transformer-structured module, the spatial-FFN module and the CIOU-smooth L1 loss function module are all effective in improving the detection accuracy of RODFormer. Compared with 12 rotating object detection models on the DOTA dataset, RODFormer has the highest average detection accuracy (up to 75.60%), that is, RODFormer is more competitive in rotating object detection accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

RODFormer: High-Precision Design for Rotating Object Detection with Transformers

Dai

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The arbitrary orientation of objects means that traditional horizontal bounding boxes cannot guarantee accurate predictions by the model. To address this, Shi et al [17] integrate a search framework (NAS-FPN) into a dense detector (RetinaNet) based on angle classification to capture target motion information and trajectories.…”

Section: Introductionmentioning

confidence: 99%

Research on Bidirectional Multi-Span Feature Pyramid and Key Feature Capture Object Detection Network

Zhang,

Shao,

et al. 2024

Drones

View full text Add to dashboard Cite

UAV remote sensing (RS) image object detection is a very valuable and challenging technology. This article discusses the importance of key features and proposes an object detection network (URSNet) based on a bidirectional multi-span feature pyramid and key feature capture mechanism. Firstly, a bidirectional multi-span feature pyramid (BMSFPN) is constructed. In the process of bidirectional sampling, bicubic interpolation and cross layer fusion are used to filter out image noise and enhance the details of object features. Secondly, the designed feature polarization module (FPM) uses the internal polarization attention mechanism to build a powerful feature representation for classification and regression tasks, making it easier for the network to capture the key object features with more semantic discrimination. In addition, the anchor rotation alignment module (ARAM) further refines the preset anchor frame based on the key regression features extracted by FPM to obtain high-quality rotation anchors with a high matching degree and rich positioning visual information. Finally, the dynamic anchor optimization module (DAOM) is used to improve the ability of feature alignment and positive and negative sample discrimination of the model so that the model can dynamically select the candidate anchor to capture the key regression features so as to further eliminate the deviation between the classification and regression. URSNet has conducted comprehensive ablation and SOTA comparative experiments on challenging RS datasets such as DOTA-V2.0, DIOR and RSOD. The optimal experimental results (87.19% mAP, 108.2 FPS) show that URSNet has efficient and reliable detection performance.

show abstract

“…The HBB annotation method uses the minimum bounding rectangle to enclose the object area, while the OBB annotation method uses the minimum bounding rectangle to enclose the object area at an angle. Compared to HBB, OBB has better object representation capabilities, as it can contain information on the angle and shape of the object 42 – 44 Additionally, OBB contains less background, and the distinguishability between the object and background is higher.…”

Section: Introductionmentioning

confidence: 99%

“…Compared to HBB, OBB has better object representation capabilities, as it can contain information on the angle and shape of the object. [42][43][44] Additionally, OBB contains less background, and the distinguishability between the object and background is higher. When annotating objects in dense scenes, there will be less mutual occlusion and interference between anchor boxes, indirectly improving the object detection accuracy.…”

Section: Introductionmentioning

confidence: 99%

Optimized anchor-free network for dense rotating object detection in remote sensing images

Yan,

Zhang,

Hong

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

Extracting dense rotating objects accurately from remote sensing images is an emerging task in object detection. To increase the applicability of existing algorithms in the above tasks, an optimized anchor-free network optimized by a dual attention mechanism (DAM) and gate multiscale feature fusion (GMFF) is designed. The DAM module is composed of two attention mechanisms with different functions. This part can enhance the backbone network's ability to extract and model information at different levels and reduce the accuracy loss caused by object density changes in the image. The GMFF module uses the gating structure to realize adaptive transmission and integration of multiscale information. Through this module, the useless information in features will be filtered, and the key information will be retained. Several experiments are designed to verify the feasibility of the algorithm. Compared with the baseline model, adding DAM and GMFF to the dense rotating object extraction task in remote sensing images improves the model accuracy by 3.5% and 2.1%, respectively, while adding two modules simultaneously, and the accuracy increases from 79.1% to 84.3%. In conventional object extraction tasks, such as dataset for object detection in aerial images and HRSC2016, our method has the highest accuracy compared to other similar algorithms, with 76.5% and 90.3%, respectively.

show abstract

Remote Sensing Image Object Detection Based on Angle Classification

Cited by 15 publications

References 29 publications

RODFormer: High-Precision Design for Rotating Object Detection with Transformers

RODFormer: High-Precision Design for Rotating Object Detection with Transformers

Research on Bidirectional Multi-Span Feature Pyramid and Key Feature Capture Object Detection Network

Optimized anchor-free network for dense rotating object detection in remote sensing images

Contact Info

Product

Resources

About