An Improved Adaptive Spatial Preprocessing Method for Remote Sensing Images

Zheng, Li; Xu, Wei

doi:10.3390/s21175684

Cited by 11 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [8] proposed a preprocessing algorithm that both smooths noise and enhances edges. It consists of an improved adaptive spatially-weighted filter that can achieve both of the above functions.…”

Section: Preprocessing Methods For Ship Detectionmentioning

confidence: 99%

Saliency Guided DNL-Yolo for Optical Remote Sensing Images for Off-Shore Ship Detection

Guo

Wang

2022

Applied Sciences

View full text Add to dashboard Cite

The complexity of changeable marine backgrounds makes ship detection from satellite remote sensing images a challenging task. The ubiquitous interference of cloud and fog led to missed detection and false-alarms when using imagery-based optical satellite remote sensing. An off-shore ship detection method with scene classification and a saliency-tuned YOLONet is proposed to solve this problem. First, the image blocks are classified into four categories by a density peak clustering algorithm (DPC) according to their grayscale histograms, i.e., cloudless areas, thin cloud areas, scattered clouds areas, and thick cloud areas. Secondly, since the ships can be regarded as salient objects in a marine background, the spectral residue saliency detection method is used to extract prominent targets from different image blocks. Finally, the saliency tuned YOLOv4 network is designed to quickly and accurately detect ships from different marine backgrounds. We validated the proposed method using more than 2000 optical remote sensing images from the GF-1 satellite. The experimental results demonstrated that the proposed method obtained a better detection performance than other state-of-the-art methods.

show abstract

Section: Preprocessing Methods For Ship Detectionmentioning

confidence: 99%

Saliency Guided DNL-Yolo for Optical Remote Sensing Images for Off-Shore Ship Detection

Guo

Wang

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In the real sense preprocessing refers to radiometric and geometric correction of remotely sensed data. Various preprocessing methods suitable for remote sensing data are given in the research articles [90][91][92].…”

Section: Image Classification Techniques In Remote Sensingmentioning

confidence: 99%

A Systematic Review of Machine Learning Applications in Land Use Land Cover Change Detection using Remote Sensing

Sumangala

Kini²

2022

IJAEML

View full text Add to dashboard Cite

Background/Purpose: The objective of this literature review is to explore different land use and land cover methods using machine learning techniques and also their applications in change detection. Reviewing various methods adopted in this domain opens up a new path for taking up further research by extending the current approaches. Design/Methodology/Approach: The research findings presented in various scholarly articles are collected from secondary resources including scholarly journal publications. These articles are analyzed, and the interpretations are highlighted in this review paper. Findings/Result: This research provides insight into various techniques used to classify remote sensing imagery. The gaps identified during the analysis with different approaches have helped to get a clear picture when formulating research questions in the remote sensing geographic information systems domain. Research limitations/implications: This study has surveyed various applications of remote sensing in GIS. This study is limited to a review of the various machine-learning approaches used for implementing change detection. The various deep learning architectures for image classification could be further explored. Originality/Value: The articles selected for review in this study are from scholarly research journals and are cited by other authors in their publications. The papers selected for review are relevant to the research work and research proposal presented in this paper. Paper Type: Literature review paper.

show abstract

“…Thus, in [61], the YOLOv4 Model combined Attention Mechanism and DeblurGanv2 is used for real-time gesture recognition. [62] used deblurring methods for remote sensing tasks. [63] introduces a twophase framework of deblurring and object detection, by adopting a slimmed version of the deblurring generative adversarial network model and a YOLOv2 detector.…”

Section: Introductionmentioning

confidence: 99%

Identification and Classification of Mechanical Damage During Continuous Harvesting of Root Crops Using Computer Vision Methods

et al. 2022

View full text Add to dashboard Cite

Detecting sugar beetroot crops with mechanical damage using machine learning methods is necessary for fine-tuning beet harvester units. The Agrifac HEXX TRAXX harvester with an installed computer vision system was investigated. A video camera (24 fps) was installed above the turbine, which receives the dug-out beets after the digger and is connected to a single-board computer. At the preprocessing stage, static and insignificant image details were revealed. Canny edge detector and excess green minus excess red (ExGR) method were used. The identified areas were excluded from the image. The remaining areas were glued with similar areas of another image. As a result, the number of images entering the second stage of preprocessing was reduced by half. Then Otsu's binarization was used. The main stage of image processing is divided into two sub-stages: detection and classification. The improved YOLOv4tiny method was chosen for root crop detection using a single-board computer (SBC). This method allows processing up to 14 images of 416 × 416 pixels with 86% precision and 91% recall. To classify root crop damage, we considered two algorithms as candidates: 1. bag of visual words (BoVW) with a support vector machine (SVM) classifier using histogram of oriented gradients (HOG) and scale-invariant feature transform (SIFT) descriptors; 2. convolutional neural networks (CNN). Under normal lighting conditions, CNN showed the best accuracy, which ranged from 97% to 100%, depending on the damage class. The implemented methods were used to detect and classify blurred images of sugar beetroots, which were previously rejected. For improved YOLOv4-tiny precision was 74% and recall was 70%. CNN classification accuracy ranged from 90% to 95% depending on the root crops damage class.

show abstract

An Improved Adaptive Spatial Preprocessing Method for Remote Sensing Images

Cited by 11 publications

References 27 publications

Saliency Guided DNL-Yolo for Optical Remote Sensing Images for Off-Shore Ship Detection

Saliency Guided DNL-Yolo for Optical Remote Sensing Images for Off-Shore Ship Detection

A Systematic Review of Machine Learning Applications in Land Use Land Cover Change Detection using Remote Sensing

Identification and Classification of Mechanical Damage During Continuous Harvesting of Root Crops Using Computer Vision Methods

Contact Info

Product

Resources

About