Dynamic monitoring algorithm of natural resources in scenic spots based on MODIS Remote Sensing technology

Li, Maolin

doi:10.15446/esrj.v25n1.93869

Cited by 4 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers are increasingly applying deep learning technology to remote sensing problems. The semantic segmentation of remote sensing data has been an important topic for decades and applied in many fields [7], such as environmental monitoring [8,9], crop cover and analysis [10][11][12], the detection of land cover and land use changes [13], the inventory and management of natural resources [14,15], etc. The complexity of the geographical scene has considerably affected the accuracy of geographic feature classification [16][17][18][19], and the representativeness and quality of training samples have an important role in the performance of deep learning models for the semantic segmentation of remote sensing images [20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias

He,

Li,

Gao

2024

Remote Sensing

View full text Add to dashboard Cite

Challenges in enhancing the multiclass segmentation of remotely sensed data include expensive and scarce labeled samples, complex geo-surface scenes, and resulting biases. The intricate nature of geographical surfaces, comprising varying elements and features, introduces significant complexity to the task of segmentation. The limited label data used to train segmentation models may exhibit biases due to imbalances or the inadequate representation of certain surface types or features. For applications like land use/cover monitoring, the assumption of evenly distributed simple random sampling may be not satisfied due to spatial stratified heterogeneity, introducing biases that can adversely impact the model’s ability to generalize effectively across diverse geographical areas. We introduced two statistical indicators to encode the complexity of geo-features under multiclass scenes and designed a corresponding optimal sampling scheme to select representative samples to reduce sampling bias during machine learning model training, especially that of deep learning models. The results of the complexity scores showed that the entropy-based and gray-based indicators effectively detected the complexity from geo-surface scenes: the entropy-based indicator was sensitive to the boundaries of different classes and the contours of geographical objects, while the Moran’s I indicator had a better performance in identifying the spatial structure information of geographical objects in remote sensing images. According to the complexity scores, the optimal sampling methods appropriately adapted the distribution of the training samples to the geo-context and enhanced their representativeness relative to the population. The single-score optimal sampling method achieved the highest improvement in DeepLab-V3 (increasing pixel accuracy by 0.3% and MIoU by 5.5%), and the multi-score optimal sampling method achieved the highest improvement in SegFormer (increasing ACC by 0.2% and MIoU by 2.4%). These findings carry significant implications for quantifying the complexity of geo-surface scenes and hence can enhance the semantic segmentation of high-resolution remote sensing images with less sampling bias.

show abstract

Section: Introductionmentioning

confidence: 99%

Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias

He,

Li,

Gao

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

Archaeological cognition of the Eastern mausoleum of Qin state using integrated space-ground observation tools

Luo,

Chen,

Gao

et al. 2024

Herit Sci

View full text Add to dashboard Cite

The Eastern Mausoleum of Qin State is a significant component of the Qin Dynasty's royal tombs, reflecting the social development level during the Warring States period (475 BC ~ 221 BC) in China. At the onset of our investigation, we mapped the site's boundaries utilizing Corona satellite imagery and employed the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Moisture Index (NDMI) to identify archaeological features. Additionally, this study is the first to propose the use of thermal infrared band data from the SDGSAT-1 satellite to explore thermal archaeological traces, demonstrating their viability for archaeological site analysis. Subsequently, electromagnetic (EM) prospection was utilized to validate the presence of an ancient burial chamber passage. Landscape monitoring and analysis of the No.1 Mausoleum were performed using Corona and Google Earth images, revealing the accuracy of the Geomancy Theory of Chinese mausoleums through dynamic remote sensing of surface changes. Furthermore, our employment of space-to-ground observational modalities and resultant Digital Elevation Models (DEM) have been used to provided new insights into the application of Remote Sensing (RS) and Geomancy in archaeology, thereby emphasizing the pivotal role of site selection in heritage preservation. This research underscores the promise of synergistic space-ground observations in both exploiting the archaeological riches of cultural heritage sites and ensuring the enduring conservation of these irreplaceable patrimonial assets.

show abstract

Archaeological cognition of the Eastern Mausoleum of Qin State using integrated space-ground observation tools

Luo,

Chen,

Gao

et al. 2023

Preprint

View full text Add to dashboard Cite

As a significant component of the Qin Dynasty's royal tombs, the ruins from the Eastern Mausoleum of the Qin State would be mirrored to present the social development level during the Warring States period (475 BC ~ 221 BC) in China. In this study, we applied multi-mode space-ground observations and derivative Digital Elevation Models to assess the plausibility of Remote Sensing (RS) in archaeology and to uncover the hitherto poorly understood conditions/situations for heritage conservation. We first applied the ‘Normalized Difference Vegetation Index’ and the ‘Normalized Difference Moisture Index’ to highlight archaeological traces. Additionally, for the first time, we proposed utilizing thermal infrared band data from the SDGSAT-1 satellite for the exploration of thermal archaeological traces, revealing an enhancement in archaeological signs. Subsequently, we use electromagnetic prospecting to confirm the presence of an ancient tomb passage. The landscape analysis reveals the hold of the Chinese Geomancy Theory on the site selection for royal tombs, this philosophy in turn is significant for heritage conservation from the natural force of surface erosion. The RS-based change detection using CORONA and Google Earth images reveals negligible surface erosion traces along with the mitigated anthropogenic disturbance. This study implies the potential of multi-mode space-ground observations for the cultural heritage archaeological value exploitation as well as the sustainable conservation of these irreplaceable properties.

show abstract

Dynamic monitoring algorithm of natural resources in scenic spots based on MODIS Remote Sensing technology

Cited by 4 publications

References 19 publications

Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias

Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias

Archaeological cognition of the Eastern mausoleum of Qin state using integrated space-ground observation tools

Archaeological cognition of the Eastern Mausoleum of Qin State using integrated space-ground observation tools

Contact Info

Product

Resources

About