Edge Detection Based on Remote Sensing Data

Dear Colleagues,

Edges is an important geometrical feature of objects present in any images and data, including the remote sensing data, and, therefore, has become the centre for processing the remote sensing data in various target applications such as object (boundary) extraction and 3D modelling, segmentation and classification, and registration and fusion of data from different data sources. Over the last few decades, there have been several attempts, for example, through the application of traditional operators (e.g., Canny and Sobel) and mathematical theories (e.g., wavelet and morphology), and the combination of the traditional and mathematical algorithms, to extract edges reliably from remote sensing data.

However, the success of efficient and effective edge extraction is still an unrealised goal due to one or more of the following reasons. Firstly, there are ample amount of texture details and noises present in the data. This leads to any involved edge detection algorithm extracting incomplete or missing edges. Secondly, because of unpredictable weather and lighting conditions, image quality may vary for the same scene even if images are captured by the same sensor, but at different dates and times. So, when the same edge detection algorithm is applied to two different sets of data of the same scene, the outcomes may well be different. Thirdly, data captured by different sensors are different in resolution and accuracy. Thus, the choice of a set of reliable algorithmic parameters is hard to achieve. Finally, the advancement of the recent remote sensing technology offers big data (high resolution / density data) which obviously make any algorithms extremely time-consuming and, thereby, less applicable in applications that require real-time data processing. Consequently, the usefulness of the existing edge detection algorithm from the remote sensing data is limited in any aforementioned target applications.

Therefore, intelligent and innovative new edge detection algorithms are in dire need for the success of any methods designed for the target applications. This special issue will focus on the newly-developed algorithms for edge detection from remote sensing data, as well as their successful applications to object extraction and modelling, segmentation and classification, and registration and fusion of data from different sources. It will cover the following topics, but not be limited to:

• Edge detection from one or a combination of the aerial and/or satellite data (VHR, hyperspectral, SAR, LiDAR, UAV, thermal imagery, oblique imagery, etc.);
• Application of the edge detection algorithms to successful object (e.g., buildings, roads, power line) extraction, segmentation and classification; and
• Registration and fusion of various remote sensing data, e.g., LiDAR and multispectral imagery.

Moreover, we cordially welcome application papers on other areas such as object boundary extraction and regularisation, change detection, urban growth monitoring, coastline extraction, biomass estimation, and technical reviews.

Dr. Mohammad Awrangjeb
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.