After the revival of deep learning in computer vision in 2012, SAR ship detection comes into the deep learning era too. The deep learning-based computer vision algorithms can work in an end-to-end pipeline, without the need of designing features manually, and they have amazing performance. As a result, it is also used to detect ships in SAR images. The beginning of this direction is the paper we published in 2017BIGSARDATA, in which the first dataset SSDD was used and shared with peers. Since then, lots of researchers focus their attention on this field. In this paper, we analyze the past, present, and future of the deep learning-based ship detection algorithms in SAR images. In the past section, we analyze the difference between traditional CFAR (constant false alarm rate) based and deep learning-based detectors through theory and experiment. The traditional method is unsupervised while the deep learning is strongly supervised, and their performance varies several times. In the present part, we analyze the 177 published papers about SAR ship detection. We highlight the dataset, algorithm, performance, deep learning framework, country, timeline, etc. After that, we introduce the use of single-stage, two-stage, anchor-free, train from scratch, oriented bounding box, multi-scale, and real-time detectors in detail in the 177 papers. The advantages and disadvantages of speed and accuracy are also analyzed. In the future part, we list the problem and direction of this field. We can find that, in the past five years, the AP50 has boosted from 78.8% in 2017 to 97.8 % in 2022 on SSDD. Additionally, we think that researchers should design algorithms according to the specific characteristics of SAR images. What we should do next is to bridge the gap between SAR ship detection and computer vision by merging the small datasets into a large one and formulating corresponding standards and benchmarks. We expect that this survey of 177 papers can make people better understand these algorithms and stimulate more research in this field.
The Luojia1-01 satellite provides high-resolution, high-sensitivity nighttime light data at a resolution of 130 m. To effectively use the Luojia1-01 nighttime light data for global applications, the problems of relative and absolute positioning accuracy should be solved. This paper proposes a high accuracy regional geometric processing method of nighttime light imagery. We utilized a nighttime light image matching algorithm to obtain tie points, which are used in the planar block adjustment with ground control points. Then, orthorectification of all images is implemented. Finally, we obtain the nighttime light map of China by mosaicking all the nighttime light orthoimages. According to the experimental results for 275 Luojia1-01 images, the root mean square error of the tie points is 0.983 pixels and the root mean square error of independent checkpoints is 195.491 m (less than 1.5 pixels) after the planar block adjustment. The experimental results prove the validity and feasibility of the proposed method.
To ensure the accuracy of large-scale optical stereo image bundle block adjustment, it is necessary to provide well-distributed ground control points (GCPs) with high accuracy. However, it is difficult to acquire control points through field measurements outside the country. Considering the high planimetric accuracy of spaceborne synthetic aperture radar (SAR) images and the high elevation accuracy of satellite-based laser altimetry data, this paper proposes an adjustment method that combines both as control sources, which can be independent from GCPs. Firstly, the SAR digital orthophoto map (DOM)-based planar control points (PCPs) acquisition is realized by multimodal matching, then the laser altimetry data are filtered to obtain laser altimetry points (LAPs), and finally the optical stereo images’ combined adjustment is conducted. The experimental results of Ziyuan-3 (ZY-3) images prove that this method can achieve an accuracy of 7 m in plane and 3 m in elevation after adjustment without relying on GCPs, which lays the technical foundation for a global-scale satellite image process.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.