Object-Based Convolutional Neural Networks for Cloud and Snow Detection in High-Resolution Multispectral Imagers

An Improved YOLOv8n Used for Fish Detection in Natural Water Environments

To improve detection efficiency and reduce cost consumption in fishery surveys, target detection methods based on computer vision have become a new method for fishery resource surveys. However, the specialty and complexity of underwater photography result in low detection accuracy, limiting its use in fishery resource surveys. To solve these problems, this study proposed an accurate method named BSSFISH-YOLOv8 for fish detection in natural underwater environments. First, replacing the original convolutional module with the SPD-Conv module allows the model to lose less fine-grained information. Next, the backbone network is supplemented with a dynamic sparse attention technique, BiFormer, which enhances the model's attention to crucial information in the input features while also optimizing detection efficiency. Finally, adding a 160 × 160 small target detection layer (STDL) improves sensitivity for smaller targets. The model scored 88.3% and 58.3% in the two indicators of mAP@50 and mAP@50:95, respectively, which is 2.0% and 3.3% higher than the YOLOv8n model. The results of this research can be applied to fishery resource surveys, reducing measurement costs, improving detection efficiency, and bringing environmental and economic benefits.

CME-YOLOv5: An Efficient Object Detection Network for Densely Spaced Fish and Small Targets

Fish are indicative species with a relatively balanced ecosystem. Underwater target fish detection is of great significance to fishery resource investigations. Traditional investigation methods cannot meet the increasing requirements of environmental protection and investigation, and the existing target detection technology has few studies on the dynamic identification of underwater fish and small targets. To reduce environmental disturbances and solve the problems of many fish, dense, mutual occlusion and difficult detection of small targets, an improved CME-YOLOv5 network is proposed to detect fish in dense groups and small targets. First, the coordinate attention (CA) mechanism and cross-stage partial networks with 3 convolutions (C3) structure are fused into the C3CA module to replace the C3 module of the backbone in you only look once (YOLOv5) to improve the extraction of target feature information and detection accuracy. Second, the three detection layers are expanded to four, which enhances the model’s ability to capture information in different dimensions and improves detection performance. Finally, the efficient intersection over union (EIOU) loss function is used instead of the generalized intersection over union (GIOU) loss function to optimize the convergence rate and location accuracy. Based on the actual image data and a small number of datasets obtained online, the experimental results showed that the mean average precision (mAP@0.50) of the proposed algorithm reached 94.9%, which is 4.4 percentage points higher than that of the YOLOv5 algorithm, and the number of fish and small target detection performances was 24.6% higher. The results show that our proposed algorithm exhibits good detection performance when applied to densely spaced fish and small targets and can be used as an alternative or supplemental method for fishery resource investigation.

An Automated Snow Mapper Powered by Machine Learning

Snow preserves fresh water and impacts regional climate and the environment. Enabled by modern satellite Earth observations, fast and accurate automated snow mapping is now possible. In this study, we developed the Automated Snow Mapper Powered by Machine Learning (AutoSMILE), which is the first machine learning-based open-source system for snow mapping. It is built in a Python environment based on object-based analysis. AutoSMILE was first applied in a mountainous area of 1002 km2 in Bome County, eastern Tibetan Plateau. A multispectral image from Sentinel-2B, a digital elevation model, and machine learning algorithms such as random forest and convolutional neural network, were utilized. Taking only 5% of the study area as the training zone, AutoSMILE yielded an extraordinarily satisfactory result over the rest of the study area: the producer’s accuracy, user’s accuracy, intersection over union and overall accuracy reached 99.42%, 98.78%, 98.21% and 98.76%, respectively, at object level, corresponding to 98.84%, 98.35%, 97.23% and 98.07%, respectively, at pixel level. The model trained in Bome County was subsequently used to map snow at the Qimantag Mountain region in the northern Tibetan Plateau, and a high overall accuracy of 97.22% was achieved. AutoSMILE outperformed threshold-based methods at both sites and exhibited superior performance especially in handling complex land covers. The outstanding performance and robustness of AutoSMILE in the case studies suggest that AutoSMILE is a fast and reliable tool for large-scale high-accuracy snow mapping and monitoring.

A Deep Learning Method for Near-Real-Time Cloud and Cloud Shadow Segmentation from Gaofen-1 Images

In this study, an essential application of remote sensing using deep learning functionality is presented. Gaofen-1 satellite mission, developed by the China National Space Administration (CNSA) for the civilian high-definition Earth observation satellite program, provides near-real-time observations for geographical mapping, environment surveying, and climate change monitoring. Cloud and cloud shadow segmentation are a crucial element to enable automatic near-real-time processing of Gaofen-1 images, and therefore, their performances must be accurately validated. In this paper, a robust multiscale segmentation method based on deep learning is proposed to improve the efficiency and effectiveness of cloud and cloud shadow segmentation from Gaofen-1 images. The proposed method first implements feature map based on the spectral-spatial features from residual convolutional layers and the cloud/cloud shadow footprints extraction based on a novel loss function to generate the final footprints. The experimental results using Gaofen-1 images demonstrate the more reasonable accuracy and efficient computational cost achievement of the proposed method compared to the cloud and cloud shadow segmentation performance of two existing state-of-the-art methods.

An Effective Cloud Detection Method for Gaofen-5 Images via Deep Learning

Recent developments in hyperspectral satellites have dramatically promoted the wide application of large-scale quantitative remote sensing. As an essential part of preprocessing, cloud detection is of great significance for subsequent quantitative analysis. For Gaofen-5 (GF-5) data producers, the daily cloud detection of hundreds of scenes is a challenging task. Traditional cloud detection methods cannot meet the strict demands of large-scale data production, especially for GF-5 satellites, which have massive data volumes. Deep learning technology, however, is able to perform cloud detection efficiently for massive repositories of satellite data and can even dramatically speed up processing by utilizing thumbnails. Inspired by the outstanding learning capability of convolutional neural networks (CNNs) for feature extraction, we propose a new dual-branch CNN architecture for cloud segmentation for GF-5 preview RGB images, termed a multiscale fusion gated network (MFGNet), which introduces pyramid pooling attention and spatial attention to extract both shallow and deep information. In addition, a new gated multilevel feature fusion module is also employed to fuse features at different depths and scales to generate pixelwise cloud segmentation results. The proposed model is extensively trained on hundreds of globally distributed GF-5 satellite images and compared with current mainstream CNN-based detection networks. The experimental results indicate that our proposed method has a higher F1 score (0.94) and fewer parameters (7.83 M) than the compared methods.

Cloud detection methodologies: variants and development—a review

Cloud detection is an essential and important process in satellite remote sensing. Researchers proposed various methods for cloud detection. This paper reviews recent literature (2004–2018) on cloud detection. Literature reported various techniques to detect the cloud using remote-sensing satellite imagery. Researchers explored various forms of Cloud detection like Cloud/No cloud, Snow/Cloud, and Thin Cloud/Thick Cloud using various approaches of machine learning and classical algorithms. Machine learning methods learn from training data and classical algorithm approaches are implemented using a threshold of different image parameters. Threshold-based methods have poor universality as the values change as per the location. Validation on ground-based estimates is not included in many models. The hybrid approach using machine learning, physical parameter retrieval, and ground-based validation is recommended for model improvement.

Automated Glacier Extraction Index by Optimization of Red/SWIR and NIR /SWIR Ratio Index for Glacier Mapping Using Landsat Imagery

Glaciers are recognized as key indicators of climate change on account of their sensitive reaction to minute climate variations. Extracting more accurate glacier boundaries from satellite data has become increasingly popular over the past decade, particularly when glacier outlines are regarded as a basis for change assessment. Automated multispectral glacier mapping methods based on Landsat imagery are more accurate, efficient and repeatable compared with previous glacier classification methods. However, some challenges still exist in regard to shadowed areas, clouds, water, and debris cover. In this study, a new index called the automated glacier extraction index (AGEI) is proposed to reduce water and shadow classification errors and improve the mapping accuracy of debris-free glaciers using Landsat imagery. Four test areas in China were selected and the performances of four commonly used methods: Maximum-likelihood supervised classification (ML), normalized difference snow and ice index (NDSI), single-band ratios Red/SWIR, and NIR/SWIR, were compared with the AGEI. Multiple thresholds identified by inspecting the shadowed glacier areas were tested to determine an optimal threshold. The confusion matrix, sub-pixel analysis, and plot-scale validation were calculated to evaluate the accuracies of glacier maps. The overall accuracies (OAs) created by AGEI were the highest compared to the four existing automatic methods. The sub-pixel analysis revealed that AGEI was the most accurate method for classifying glacier edge mixed pixels. Plot-scale validation indicated AGEI was good at separating challenging features from glaciers and matched the actual distribution of debris-free glaciers most closely. Therefore, the AGEI with an optimal threshold can be used for mapping debris-free glaciers with high accuracy, particularly in areas with shadows and water features.