Rotated region based CNN for ship detection

Liu, Zikun; Hu, Jingao; Weng, Lubin; Yang, Yiping

doi:10.1109/icip.2017.8296411

Cited by 230 publications

(145 citation statements)

References 8 publications

Supporting

Mentioning

145

Contrasting

Order By: Relevance

“…The HRoI based method exists a problem of misalignment between region feature and instance. The RRoI based methods [9,10] usually use a Rotated RoI Warping to extract feature from a RRoI, and regress position offsets relative to the RRoI, which can avoid the problem of misalignment in a certain. However, the RRoI based method involves generating a lot of rotated proposals.…”

Section: Oriented Bounding Box Regressionmentioning

confidence: 99%

“…However, the RRoI based method involves generating a lot of rotated proposals. The [10] adopted the method in [8] for rotated proposals. The SRBBS [8] is difficult to be embedded in the neural network, which would cost extra time for rotated proposal generation.…”

Section: Oriented Bounding Box Regressionmentioning

confidence: 99%

“…detection in aerial images. These problems have been often approached by an oriented and densely packed object detection task [5][6][7], which is new while well-grounded and have attracted much attention in the past decade [8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Ding

Xue

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

962

661

View full text Add to dashboard Cite

Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. Although rotated anchors have been used to tackle this problem, the design of them always multiplies the number of anchors and dramatically increases the computational complexity. In this paper, we propose a RoI Transformer to address these problems. More precisely, to improve the quality of region proposals, we first designed a Rotated RoI (RRoI) learner to transform a Horizontal Region of Interest (HRoI) into a Rotated Region of Interest (RRoI). Based on the RRoIs, we then proposed a Rotated Position Sensitive RoI Align (RPS-RoI-Align) module to extract rotation-invariant features from them for boosting subsequent classification and regression. Our RoI Transformer is with light weight and can be easily embedded into detectors for oriented object detection. A simple implementation of the RoI Transformer has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer. The results demonstrate that it can be easily integrated with other detector architectures and significantly improve the performances.

show abstract

Section: Oriented Bounding Box Regressionmentioning

confidence: 99%

Section: Oriented Bounding Box Regressionmentioning

confidence: 99%

See 1 more Smart Citation

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Ding

Xue

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

962

661

View full text Add to dashboard Cite

show abstract

“…Instead of fine-tuning the model based on a pre-trained model, RRD is trained from scratch. Even so, RRD easily surpasses others with a promotion around 8.6 points in mAP reaching peak at 84.3 [30]. Thus, it is obvious that RRD is not only suitable for scene text detection, but also skilled in other oriented object detection.…”

Section: Results On the Ship Collection Benchmarkmentioning

confidence: 95%

“…SRBBS(Ship Rotated Bounding Boxes Space) means labeling of ships is rotated polygon; RBB(Rotated Bounding Boxes) extends Fast-RCNN to a method capable of regressing rotated bounding boxes; RRoI(Rotated Region of Interest) pooling layer is implemented based on original RoI pooling, which is specially designed for rotated bounding boxes. For detailed description, refer to[30]…”

mentioning

confidence: 99%

Rotation-Sensitive Regression for Oriented Scene Text Detection

Liao

Zhu

Shi

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

498

227

View full text Add to dashboard Cite

Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a classification problem disregarding text orientation; 2) oriented bounding box regression, which concerns about text orientation. Previous methods rely on shared features for both tasks, resulting in degraded performance due to the incompatibility of the two tasks. To address this issue, we propose to perform classification and regression on features of different characteristics, extracted by two network branches of different designs. Concretely, the regression branch extracts rotation-sensitive features by actively rotating the convolutional filters, while the classification branch extracts rotation-invariant features by pooling the rotationsensitive features. The proposed method named Rotationsensitive Regression Detector (RRD) achieves state-of-theart performance on three oriented scene text benchmark datasets, including ICDAR 2015, MSRA-TD500, RCTW-17 and COCO-Text. Furthermore, RRD achieves a significant improvement on a ship collection dataset, demonstrating its generality on oriented object detection.

show abstract

Bibliography

2021

Deep Learning for the Earth Sciences

View full text Add to dashboard Cite

Rotated region based CNN for ship detection

Cited by 230 publications

References 8 publications

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Rotation-Sensitive Regression for Oriented Scene Text Detection

Bibliography

Contact Info

Product

Resources

About