MRDet: A Multihead Network for Accurate Rotated Object Detection in Aerial Images

Ran, Qin; Liu, Qingjie; Gao, Guangshuai; Huang, Di; Wang, Yunhong

doi:10.1109/tgrs.2021.3113473

Cited by 25 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This modification provides a more precise localization of rotated ships within a rectangular bounding box that is aligned with the ship's direction. Similar approaches have been reported in [221], [222], [223]. Using SSD, [224] developed a cascade object detection method to identify obscure regions.…”

Section: Other Maritime Sodmentioning

confidence: 80%

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

Rekavandi¹,

Liu²,

Boussaid³

et al. 2022

Preprint

View full text Add to dashboard Cite

Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided.

show abstract

Section: Other Maritime Sodmentioning

confidence: 80%

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

Rekavandi¹,

Liu²,

Boussaid³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Yang et al [37] developed a sampling fusion network and a multi-dimensional attention network for feature fusion and noise suppression. Qin et al [38] used an arbitrary-oriented region proposal network to generate rotated proposals of different scales and then the proposals were fed into the multi-head network for refinement. CAD-Net [39] leveraged a spatial-and-scale-aware attention module to guide the network to focus on the regions with rich information.…”

Section: A Two-stage Methods For Oodmentioning

confidence: 99%

“…[52] 61.24 88.15 71 38. 34.26 51.78 63.78 65.63 71.61 90.11 71.07 73.63 37.62 41.52 48.07 60.53 49.53 Axis Learning [54] 65.98 79.53 77.15 38.59 61.15 67.53 70.49 76.30 89.66 79.07 83.53 47.27 61.01 56.28 66.06 36.05 O 2 -DNet [32] 71.04 89.31 82.14 47.33 61.21 71.32 74.03 78.62 90.76 82.23 81.36 60.93 60.17 58.21 66.98 64.03 ACE [67] 71.70 89.50 76.30 45.10 60.00 77.80 77.10 86.50 90.80 79.50 85.70 47.00 59.40 65.70 71.70 63.90 TricubeNet [68] 75.26 88.75 82.12 49.24 72.98 77.64 74.53 84.65 90.81 86.02 85.38 58.69 63.59 73.82 69.67 71.08 BBAVectors [31] 75.36 88.63 84.06 52.13 69.56 78.26 80.40 88.06 90.87 87.23 86.39 56.11 65.62 67.10 72.08 63.96 GGHL [19] 76.95 89.74 85.63 44.50 77.48 76.72 80.45 86.16 90.83 88.18 86.25 67.07 69.40 73.38 68.45 70.14 PolarDet [55] 76.64 89.65 87.07 48.14 70.97 78.53 80.34 87.45 90.76 85.63 86.87 61.64 70.32 71.92 73.09 67.15 AMFFNet [64] 77.18 89.84 84.90 51.55 74.42 78.54 83.28 87.36 90.73 87.17 85.70 65.20 62.23 75.56 72.21 69.01 Oriented RepPoints[69] 78.12 88.72 80.56 55.69 75.07 81.84 82.40 87.97 90.80 84.33 87.64 62.80 67.91 77.69 82.94 65.46 DDMNet 78.66 90.16 84.86 52.71 74.21 79.71 85.55 88.71 90.85 88.95 86.07 68.50 68.42 77.25 71.32 72.64…”

mentioning

confidence: 99%

Dual-Resolution and Deformable Multihead Network for Oriented Object Detection in Remote Sensing Images

Liu

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Compared with general object detection, the scale variations, arbitrary orientations, and complex backgrounds of objects in remote sensing images make it more challenging to detect oriented objects. Especially for oriented objects that have large aspect ratios, it is more difficult to accurately detect their boundary. Many methods show excellent performance on oriented object detection, most of which are anchor-based algorithms. To mitigate the performance gap between anchor-free algorithms and anchor-based algorithms, this paper proposes an anchor-free algorithm called dual-resolution and deformable multi-head network (DDMNet) for oriented object detection. Specifically, the dual-resolution network with bilateral fusion is adopted to extract high-resolution feature maps which contain both spatial details and multi-scale contextual information. Then, the deformable convolution is incorporated into the network to alleviate the misalignment problem of oriented object detection. And a dilated feature fusion module is performed on the deformable feature maps to expand their receptive fields. Finally, box boundary-aware vectors instead of the angle are leveraged to represent the oriented bounding box and the multi-head network is designed to get robust predictions. DDMNet is a single-stage oriented object detection method without using anchors and exhibits promising performance on the public challenging benchmarks. DDMNet obtains 90.49%, 93.25%, and 78.66% mean average precision (mAP) on the HRSC2016, FGSD2021, and DOTA datasets. In particular, DDMNet achieves 79.86% at mAP75 and 53.85% at mAP85 on the HRSC2016 dataset, respectively, outperforming the current state-of-the-art methods.

show abstract

“…This paper mainly focuses on anchor-based detectors. Anchor-based detectors can be divided into multi-stage detectors [23][24][25][26][27][28][29][30][31] and one-stage detectors [32][33][34][35][36][37].…”

Section: A Object Detection In Remote Sensing Imagerymentioning

confidence: 99%

Context-Based Oriented Object Detector for Small Objects in Remote Sensing Imagery

et al. 2022

View full text Add to dashboard Cite

Object detection in remote sensing imagery is a challenging task in the field of computer vision and has high research value. To improve the classification accuracy and positioning accuracy of object detection, we propose a new multi-scale oriented object detector suitable for small objects. Firstly, the feature fusion network based on information balance (IBFF) is proposed to reduce the reuse of different layers' features from the backbone network and reduce the interference of redundant information based on the premise that the output features have sufficient information, and retain enough shallow detail information. Secondly, to efficiently utilize deep and shallow features, enhance important features, and reduce background noise interference, different attention-based context feature fusion modules (DACFF) are designed according to the characteristics of different feature fusion stages. Finally, an improved strategy of oriented bounding box regression is proposed to obtain the oriented bounding box with a simpler and more effective strategy. The proposed method was evaluated on two public remote sensing datasets, DOTA and HRSC2016, and their mAP values are 80.96% and 95.01%, respectively, which verified the effectiveness of the proposed algorithm.

show abstract

MRDet: A Multihead Network for Accurate Rotated Object Detection in Aerial Images

Cited by 25 publications

References 49 publications

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

Dual-Resolution and Deformable Multihead Network for Oriented Object Detection in Remote Sensing Images

Context-Based Oriented Object Detector for Small Objects in Remote Sensing Imagery

Contact Info

Product

Resources

About