Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm

Liu, Man; Fu, Bolin; Xie, Shaofeng; He, Hongchang; Lan, Feiwu; Li, Yuyang; Lou, Peiqing; Fan, Donglin

doi:10.1016/j.ecolind.2021.107562

Cited by 68 publications

(24 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wetlands are one of the world's major ecosystems that play an important role in the global carbon cycle and ecological equilibrium (Hu et al, 2017 ; Liu et al, 2021 ). Marsh is a type of wetland ecosystem, which is crucial for regulating the regional climate and carbon cycle (Shen et al, 2020 ; Rietl et al, 2021 ; Wang et al, 2022a ).…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Variation in Aboveground Biomass and Its Response to Climate Change in the Marsh of Sanjiang Plain

et al. 2022

View full text Add to dashboard Cite

The Sanjiang Plain has the greatest concentration of freshwater marshes in China. Marshes in this area play a key role in adjusting the regional carbon cycle. As an important quality parameter of marsh ecosystems, vegetation aboveground biomass (AGB) is an important index for evaluating carbon stocks and carbon sequestration function. Due to a lack of in situ and long-term AGB records, the temporal and spatial changes in AGB and their contributing factors in the marsh of Sanjiang Plain remain unclear. Based on the measured AGB, normalized difference vegetation index (NDVI), and climate data, this study investigated the spatiotemporal changes in marsh AGB and the effects of climate variation on marsh AGB in the Sanjiang Plain from 2000 to 2020. Results showed that the marsh AGB density and annual maximum NDVI (NDVImax) had a strong correlation, and the AGB density could be accurately calculated from a power function equation between NDVImax and AGB density (AGB density = 643.57 × NDVImax4.2474). According to the function equation, we found that the AGB density significantly increased at a rate of 2.47 g·C/m2/a during 2000–2020 in marshes of Sanjiang Plain, with the long-term average AGB density of about 282.05 g·C/m2. Spatially, the largest increasing trends of AGB were located in the north of the Sanjiang Plain, and decreasing trends were mainly found in the southeast of the study area. Regarding climate impacts, the increase in precipitation in winter could decrease the marsh AGB, and increased temperatures in July contributed to the increase in the marsh AGB in the Sanjiang Plain. This study demonstrated an effective approach for accurately estimating the marsh AGB in the Sanjiang Plain using ground-measured AGB and NDVI data. Moreover, our results highlight the importance of including monthly climate properties in modeling AGB in the marshes of the Sanjiang Plain.

show abstract

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Variation in Aboveground Biomass and Its Response to Climate Change in the Marsh of Sanjiang Plain

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In experiment 1, our proposed model, MAs-FC-DenseNet, is compared against the traditional FC-DenseNet models including FC-DenseNet56 [11] and FC-DenseNet67 [11]. In experiment 2, our proposed model is compared against other end-to-end models, including DeeplabV3+ [20] and PSPNet [21] models.…”

Section: Resultsmentioning

confidence: 99%

An Automatic Detection Model of Microaneurysms Based on Improved FC-Densenet

Wang¹,

Yao²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a common eye disease, which leads cause of blindness all around the world. Microaneurysms (MAs) is one of the early symptoms of DR. Accurate and effective MAs detection and segmentation is an important step for the diagnosis and treatment of DR. In this paper, we propose an automatic model for detection of MAs in fluorescein fundus angiography (FFA) images. The model mainly consists of two steps. The first step is pre-processing of FFA images, where the quality of FFA images is improved by Histogram Stretching and Gaussian Filtering algorithm. The second step is to detect MAs regions, where the MAs regions are detected by improved FC-DenseNet. We compare the proposed model with traditional FC-DenseNet model and other previously published models. The experimental result shows that our proposed model has the highest scores on evaluation metrics of pixel accuracy (PA), mean pixel accuracy (MPA), precision (Pre), recall (Re), F1-score (F1) and mean intersection over union (MIoU), which are 99.97%, 94.19%, 88.40%, 89.70%, 88.98% and 90.14%, respectively. The result suggests that the performance of our proposed model is closer to the ground truth of MAs detection. Our proposed model would be helpful for ophthalmologists to find the symptoms more quickly and to take better treatment measures in the screening process of diabetic retinopathy.

show abstract

“…Moreover, these techniques are not robust to the extensive variations in the size, color, and shapes of leaf plant diseases. Therefore, there is a need of more robust approach employing the latest approaches to improve the recognition accuracy of several Plant leaf diseases [33,34].…”

Section: Related Workmentioning

confidence: 99%

A novel deep learning method for detection and classification of plant diseases

Albattah

Nawaz

Javed

et al. 2021

Complex Intell. Syst.

120

View full text Add to dashboard Cite

The agricultural production rate plays a pivotal role in the economic development of a country. However, plant diseases are the most significant impediment to the production and quality of food. The identification of plant diseases at an early stage is crucial for global health and wellbeing. The traditional diagnosis process involves visual assessment of an individual plant by a pathologist through on-site visits. However, manual examination for crop diseases is restricted because of less accuracy and the small accessibility of human resources. To tackle such issues, there is a demand to design automated approaches capable of efficiently detecting and categorizing numerous plant diseases. Precise identification and classification of plant diseases is a tedious job due because of the occurrence of low-intensity information in the image background and foreground, the huge color resemblance in the healthy and diseased plant areas, the occurrence of noise in the samples, and changes in the position, chrominance, structure, and size of plant leaves. To tackle the above-mentioned problems, we have introduced a robust plant disease classification system by introducing a Custom CenterNet framework with DenseNet-77 as a base network. The presented method follows three steps. In the first step, annotations are developed to get the region of interest. Secondly, an improved CenterNet is introduced in which DenseNet-77 is proposed for deep keypoints extraction. Finally, the one-stage detector CenterNet is used to detect and categorize several plant diseases. To conduct the performance analysis, we have used the PlantVillage Kaggle database, which is the standard dataset for plant diseases and challenges in terms of intensity variations, color changes, and differences found in the shapes and sizes of leaves. Both the qualitative and quantitative analysis confirms that the presented method is more proficient and reliable to identify and classify plant diseases than other latest approaches.

show abstract

Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm

Cited by 68 publications

References 70 publications

Spatiotemporal Variation in Aboveground Biomass and Its Response to Climate Change in the Marsh of Sanjiang Plain

Spatiotemporal Variation in Aboveground Biomass and Its Response to Climate Change in the Marsh of Sanjiang Plain

An Automatic Detection Model of Microaneurysms Based on Improved FC-Densenet

A novel deep learning method for detection and classification of plant diseases

Contact Info

Product

Resources

About