Building footprint extraction using orthophotos based on Artificial Neural Network and fusion of dense point cloud with Digital Topographic Map — Istanbul, Turkey

Baş, Nuray

doi:10.1007/s12517-022-10365-2

Cited by 2 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Khan et al [14] pro-posed an encoderdecoder framework that automatically extracts building footprints from satellite images, demonstrating superior performance on challenging datasets. Ba¸s [15] explored the fusion of dense point clouds with Digital Topographic Maps for building footprint extraction using Arti cial Neural Networks (ANNs),…”

Section: Related Workmentioning

confidence: 99%

Building Footprint Segmentation Using the Modified YOLOv8 Model

Falahatnejad,

Karami,

Sharifirad

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper proposes an enhanced YOLOv8 model specifically designed for precise building footprint segmentation. The model incorporates several key modifica- tions to achieve superior performance and efficiency. Firstly, a novel fusion layer integrates RGB image information with a Digital Elevation Model (DEM), enrich- ing feature representation and facilitating the distinction of building structures. Secondly, Depthwise Separable Convolution (DSConv) replaces standard convo- lutions throughout the backbone and head, leading to a more compact model with faster inference speed. Thirdly, Varifocal Loss (VFL) is employed as the clas- sification loss function, effectively addressing class imbalance issues prevalent in segmentation tasks. Our proposed model demonstrates significant improvements over three DeepLabv3+, SAM, and the original YOLOv8 state-of-the-art models. We achieve a precision of 91.11%, a recall rate of 89.71%, and a mAP (mean Average Precision) of 87.42%, surpassing all compared models in accuracy. Fur- thermore, the proposed model boasts a remarkably fast inference time of only 45.1 milliseconds per image, making it suitable for real-time applications.

show abstract

Section: Related Workmentioning

confidence: 99%

Building Footprint Segmentation Using the Modified YOLOv8 Model

Falahatnejad,

Karami,

Sharifirad

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…It also supports regional efforts to combat climate change. On the other hand, in Baş, (2022), building footprint extraction is carried out by a combination of highaccuracy Regularize Digital Topographic Map (RDTM) with LiDAR data in the urban areas to reveal the efficiency of orthophoto in building detection using the ANN method. Therefore, the reflections of technological developments on climate, environment, and waste management should be addressed from a social perspective.…”

Section: Introductionmentioning

confidence: 99%

Waste management within the scope of environmental public awareness based on cross-sectional survey and social interviews

Zhou

İnce

Haikun

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Since the natural resources of the world are not unlimited, the effective use of resources and the access of future generations to these resources concern all societies on a global scale. From this point of view, waste management strategies should be examined in terms of medical, household, and other waste types. Thereby, this study aims to examine the level of public awareness in waste management by studying the perception, perspective, practice about waste’s aspects. The survey in this study mentions questions on waste management knowledge, public awareness, and behaviors among social interviews of pharmacy students receiving laboratory training in the field of health. Internal consistency reliability is used to verify the uniformity of questions in this study. Pearson correlation, t-test, and the analysis of variance (ANOVA) are performed to study the differences between groups. The results of the data analysis show that public awareness and waste management knowledge, public awareness, and behaviors have a significant positive correlation, which provides us with a good basis for designing environmental strategies. The first module’s outcomes of the questionnaire reveal a high degree of waste management among students. On the contrary, woman participants demonstrate a higher public awareness and application of the environment. Furthermore, there are significant correlations between the other modules and demographic factors with family education. According to the results, the public awareness of the participants who were members of an environmental organization is different from others. Finally, the participants state that the problem of not managing wastes effectively causes the most damage to the soil and all other natural resources after water.

show abstract

Building footprint extraction using orthophotos based on Artificial Neural Network and fusion of dense point cloud with Digital Topographic Map — Istanbul, Turkey

Cited by 2 publications

References 54 publications

Building Footprint Segmentation Using the Modified YOLOv8 Model

Building Footprint Segmentation Using the Modified YOLOv8 Model

Waste management within the scope of environmental public awareness based on cross-sectional survey and social interviews

Contact Info

Product

Resources

About