Arbitrary-Oriented Ship Detection via Feature Fusion and Visual Attention for High-Resolution Optical Remote Sensing Imagery

Gong, Wenbin; Shi, Zhangsong; Wu, Zedong; Luo, Junren

doi:10.1080/01431161.2020.1856965

Cited by 8 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of ten GEE clusters were identified, and these included papers related to tidal flats, Landsat time series, land surface temperature, wetlands, the recursive hierarchical segmentation method (RHSEG), central Asia, land-use change, nighttime lights, the NDVI, and yield estimation. The clustering results suggested that GE was widely applied as a virtual Earth in studies on ship detection [77][78][79][80][81][82][83], land-conversion mapping [84][85][86], glacial geomorphology [6,[87][88][89][90][91], and the Earth's lithosphere [92].…”

Section: Knowledge Base Analysismentioning

confidence: 99%

Progress and Trends in the Application of Google Earth and Google Earth Engine

Zhao

et al. 2021

Remote Sensing

127

View full text Add to dashboard Cite

Earth system science has changed rapidly due to global environmental changes and the advent of Earth observation technology. Therefore, new tools are required to monitor, measure, analyze, evaluate, and model Earth observation data. Google Earth (GE) was officially launched by Google in 2005 as a ”geobrowser”, and Google Earth Engine (GEE) was released in 2010 as a cloud computing platform with substantial computational capabilities. The use of these two tools or platforms in various applications, particularly as used by the remote sensing community, has developed rapidly. In this paper, we reviewed the applications and trends in the use of GE and GEE by analyzing peer-reviewed articles, dating up to January 2021, in the Web of Science (WoS) core collection using scientometric analysis (i.e., by using CiteSpace) and meta-analysis. We found the following: (1) the number of articles describing the use of GE or GEE increased substantially from two in 2006 to 530 in 2020. The number of GEE articles increased much faster than those concerned with the use of GE. (2) Both GE and GEE were extensively used by the remote sensing community as multidisciplinary tools. GE articles covered a broader range of research areas (e.g., biology, education, disease and health, economic, and information science) and appeared in a broader range of journals than those concerned with the use of GEE. (3) GE and GEE shared similar keywords (e.g., “land cover”, “water”, “model”, “vegetation”, and “forest”), which indicates that their application is of great importance in certain research areas. The main difference was that articles describing the use of GE emphasized its use as a visual display platform, while those concerned with GEE placed more emphasis on big data and time-series analysis. (4) Most applications of GE and GEE were undertaken in countries, such as the United States, China, and the United Kingdom. (5) GEE is an important tool for analysis, whereas GE is used as an auxiliary tool for visualization. Finally, in this paper, the merits and limitations of GE and GEE, and recommendations for further improvements, are summarized from an Earth system science perspective.

show abstract

Section: Knowledge Base Analysismentioning

confidence: 99%

Progress and Trends in the Application of Google Earth and Google Earth Engine

Zhao

et al. 2021

Remote Sensing

127

View full text Add to dashboard Cite

show abstract

“…The specific identification of vessels is also one of the areas of most significant interest. Being able to identify vessels with images from different angles [ 21 , 28 ], as well as recognizing their identification numbers [ 41 ], are key factors to be able to keep statistics on port arrivals and traffic control. Researchers have been experimenting with deep learning methods, specifically those developed with networks that allow real-time detection, such as YoloV3, to solve this problem [ 21 ].…”

Section: Resultsmentioning

confidence: 99%

Industry 4.0 Technologies Applied to Inland Waterway Transport: Systematic Literature Review

Restrepo-Arias

Bedoya

Zapata-Cortés

et al. 2022

Sensors

View full text Add to dashboard Cite

The focus of this article is inland waterway transport. Different problems in this domain have been studied due to the increase in waterway traffic globally. Industry 4.0 technologies have become an alternative for the possible solution of these problems. For this reason, this paper aims to answer the following research questions: (1) What are the main problems in transporting cargo by inland waterway? (2) What technological strategies are being studied to solve these problems? (3) What technologies from Industry 4.0 are used within the technological strategies to solve the exposed problems? This study adopts a Systematic Literature Review (SLR) approach. For this work, were recovered 645 articles, 88 of which were eligible, from which we could identify five domains corresponding to (1) traffic monitoring, (2) smart navigation, (3) emission reduction, (4) analytics with big data, and (5) cybersecurity. The strategies currently being considered combine navigation technologies, such as AIS (Automatic Identification System), which offers a large amount of data, with Industry 4.0 tools and mainly machine learning techniques, to take advantage of data collected over a long time. This study is, to our knowledge, one of the first to show how Industry 4.0 technologies are currently being used to tackle inland waterway transport problems and current application trends in the scientific community, which is a first step for the development of future studies and more advanced solutions.

show abstract

“…For example, Patel et al [44] compared the detection capabilities of different versions of the YOLO algorithm. Gong et al [45] integrated the shallow features of SSD and introduced context information, improving the detection accuracy. Wu et al [46] employed RetinaNet as the backbone and proposed the hierarchical atrous spatial pyramid to obtain larger receptive fields.…”

Section: Featuresmentioning

confidence: 99%

Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances

Zhao,

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Ship detection aims to automatically identify whether there are ships in the images, precisely classifies and localizes them. Regardless of whether utilizing early manually designed methods or deep learning technology, ship detection is dedicated to exploring the inherent characteristics of ships to enhance recall. Nowadays, high-precision ship detection plays a crucial role in civilian and military applications. In order to provide a comprehensive review of ship detection in optical remote-sensing images (SDORSIs), this paper summarizes the challenges as a guide. These challenges include complex marine environments, insufficient discriminative features, large scale variations, dense and rotated distributions, large aspect ratios, and imbalances between positive and negative samples. We meticulously review the improvement methods and conduct a detailed analysis of the strengths and weaknesses of these methods. We compile ship information from common optical remote sensing image datasets and compare algorithm performance. Simultaneously, we compare and analyze the feature extraction capabilities of backbones based on CNNs and Transformer, seeking new directions for the development in SDORSIs. Promising prospects are provided to facilitate further research in the future.

show abstract

Arbitrary-Oriented Ship Detection via Feature Fusion and Visual Attention for High-Resolution Optical Remote Sensing Imagery

Cited by 8 publications

References 39 publications

Progress and Trends in the Application of Google Earth and Google Earth Engine

Progress and Trends in the Application of Google Earth and Google Earth Engine

Industry 4.0 Technologies Applied to Inland Waterway Transport: Systematic Literature Review

Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances

Contact Info

Product

Resources

About