Image Segmentation Techniques for Remote Sensing Satellite Images

Bhadoria, Priyanka; Agrawal, Shikha; Pandey, Rajeev

doi:10.1088/1757-899x/993/1/012050

Cited by 10 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional segmentation methods of remote sensing involve pixel-based segmentation (Bhadoria et al 2020) object-based analysis (José et al 2013), and random forest segmentation (Fei et al 2015). The analysis of pixel-based segmentation aims only at the color information among pixels, ignoring the semantic information of the classified objects, giving a poor performance in multi-object classification (Zhang et al 2020c).…”

Section: Introductionmentioning

confidence: 99%

Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery

Zhang

et al. 2021

J. For. Res.

View full text Add to dashboard Cite

Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. Semantic segmentation normally excels in medical and building classification, but its usefulness in mixed forest-grassland ecosystems in semi-arid to semi-humid climates is unknown. This study proposes a new semantic segmentation network of LResU-net in which residual convolution unit (RCU) and loop convolution unit (LCU) are added to the U-net framework to classify images of different land covers generated by UAV high resolution. The selected model enhanced classification accuracy by increasing gradient mapping via RCU and modifying the size of convolution layers via LCU as well as reducing convolution kernels. To achieve this objective, a group of orthophotos were taken at an altitude of 260 m for testing in a natural forest-grassland ecosystem of Keyouqianqi, Inner Mongolia, China, and compared the results with those of three other network models (U-net, ResU-net and LU-net). The results show that both the highest kappa coefficient (0.86) and the highest overall accuracy (93.7%) resulted from LResU-net, and the value of most land covers provided by the producer’s and user’s accuracy generated in LResU-net exceeded 0.85. The pixel-area ratio approach was used to calculate the real areas of 10 different land covers where grasslands were 67.3%. The analysis of the effect of RCU and LCU on the model training performance indicates that the time of each epoch was shortened from U-net (358 s) to LResU-net (282 s). In addition, in order to classify areas that are not distinguishable, unclassified areas were defined and their impact on classification. LResU-net generated significantly more accurate results than the other three models and was regarded as the most appropriate approach to classify land cover in mixed forest-grassland ecosystems.

show abstract

Section: Introductionmentioning

confidence: 99%

Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery

Zhang

et al. 2021

J. For. Res.

View full text Add to dashboard Cite

show abstract

“…To further enhance the performance of our system, we intend to explore various attention mechanisms and evaluate their suitability for improving the results obtained from our baseline approach. By doing so, we hope to mitigate the shortcomings associated with other existing methods [31] and ultimately yield improved detection rates and spatial precision. Ultimately, our goal is to develop an effective solution for monitoring and managing the growing problem of marine pollution.…”

mentioning

confidence: 99%

Marine Debris Detection in Satellite Surveillance Using Attention Mechanisms

Shen,

Zhu,

Angelov

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Marine debris poses a critical threat to environmental ecosystems, necessitating effective methods for its detection and localization. This study addresses the existing limitations in the literature by proposing an innovative approach that combines the instance segmentation capabilities of YOLOv7 with various attention mechanisms to enhance efficiency and broaden applicability. The primary contribution lies in the exploration and comparison of three attentional models: lightweight coordinate attention, CBAM (combining spatial and channel focus), and bottleneck transformer based on selfattention. Leveraging a meticulously labeled dataset of satellite images containing ocean debris, the study conducts a comprehensive assessment of box detection and mask evaluation. The results demonstrate that CBAM emerges as the standout performer, achieving the highest F1 score (77%) in box detection, surpassing coordinate attention (71%) and YOLOv7/bottleneck transformer (both around 66%). In mask evaluation, CBAM continues to lead with an F1 score of 73%, while coordinate attention and YOLOv7 exhibit comparable performances (around F1 scores of 68% and 69%), and bottleneck transformer lags behind at an F1 score of 56%. This compelling evidence underscores CBAM's superior suitability for detecting marine debris compared to existing methods. Notably, the study reveals an intriguing aspect of the bottleneck transformer, which, despite lower overall performance, successfully detected areas overlooked by manual annotation. Moreover, it demonstrated enhanced mask precision for larger debris pieces, hinting at potentially superior practical performance in certain scenarios. This nuanced finding underscores the importance of considering specific application requirements when selecting a detection model, as the bottleneck transformer may offer unique advantages in certain contexts.

show abstract