A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines

By Zikun Liu, Liu Yuan, Lubin Weng, Yiping Yang. International Conference on Pattern Recognition Applications and Methods, 2017

685 citations recorded by the source corpus.

Institute of Automation Chinese Academy of Sciences, 95 Zhongguancun East Road, 100190, Beijing, China

Subfields: Computer Vision and Pattern Recognition, Media Technology, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/e6a32b4df848fd74b43486c5232ebd362eb90416

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Junchi Yan
3. Fahad Shahbaz Khan
4. Qi Tian
5. Xue Yang
6. Luc Van Gool
7. Jianke Zhu
8. Ming-Hsuan Yang

In Media Technology

1. Fahad Shahbaz Khan
2. Guisong Xia
3. Bo Du
4. Salman Hameed Khan
5. Xue Yang
6. Junchi Yan
7. Qi Ming
8. Wentong Li

In Ocean Engineering

1. Wentong Li
2. Dacheng Tao
3. Feng Xu
4. Qi Tian
5. Bo Du
6. Jiaming Han
7. Jing Zhang
8. Salman Hameed Khan

Citations in the corpus

• An Empirical Study of Remote Sensing Pretraining (2022, methodology): “These models are trained for 12 and 36 epochs with a batchsize of 2 on DOTA and HRSC2016 scenes, respectively.”
• Arbitrary-Oriented Object Detection with Circular Smooth Label (2020, background): “In order to further verify that CSL-based method is a better baseline model, we have also verified it in other datasets, including the text dataset ICDAR2015, MLT, and another remote sensing dataset HRSC2016.”
• SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing (2020, background): “ome common aspects for robust object detection in the wild: small size, cluttered arrangement and arbitrary orientations. These challenges are especially pronounced for aerial image [10], [11], [12], [13] which has become an important area for detection in practice, for its various civil application”
• RemoteCLIP: A Vision Language Foundation Model for Remote Sensing (2023, methodology): “We combined six remote sensing datasets with object detection annotation, including DOTA [75], DIOR [76], HRRSD [77], RSOD [78], LEVIR [79], and HRSC [80].”
• RBox-CNN: rotated bounding box based CNN for ship detection in remote sensing image (2018, methodology): “Liu et al. [7] released a public dataset called HRSC2016 annotated with RBox for ship detection and proposed a baseline model.”
• Transformers in Remote Sensing: A Survey (2022, methodology): “RSP [7] Classification, Segmentation, Detection MillionAID [33], Potsdam [70], iSAID [80], HRSC2016 [81], DOTA [49], CCD [82], LEVIR [61] Overall classification accuracy, mAP, F1 score Investigates pre-training transformers on a large-scale remote sensing dataset.”
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss (2021, background): “HRSC2016 [33] contains images from two scenarios including ships on sea and ships close inshore.”
• Oriented RepPoints for Aerial Object Detection (2021, background): “Results on HRSC2016.”
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (2021, background): “HRSC2016 contains images from two scenarios including ships on sea and ships close inshore.”
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, methodology): “The HRSC2016 dataset [35] is the most used dataset for ship detection in remote sensing images, which contains 22 classes of ships but only has 1061 images.”
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection (2021, methodology): “With the development of general object detection, many well-designed methods have been proposed for oriented object detection [1, 7, 24, 35, 38, 40, 42], showing promising performance on challenging datasets [21, 35].”
• Poly Kernel Inception Network for Remote Sensing Detection (2024, methodology): “5 [64], HRSC2016 [41], and DIOR-R [3] demonstrate the effectiveness of our method.”