A hybrid image segmentation method for building extraction from high-resolution RGB images

Hossain, Mohammad Dalower; Chen, Dongmei

doi:10.1016/j.isprsjprs.2022.08.024

Cited by 20 publications

(13 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few years, deep learning approaches have been widely applied in the field of remote sensing, among which the detection and extraction of building footprints has received enormous attention (Guo et al, 2022, Hossain et al, 2022. With their powerful feature learning capabilities, deep convolutional networks are able to cope with complex rural environments and diverse building types.…”

Section: Methodsmentioning

confidence: 99%

A Large-Scale Multipurpose Benchmark Dataset and Real-Time Interpretation Platform Based on Chinese Rural Buildings

Deng,

Xu,

Huang

et al. 2024

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

View full text Add to dashboard Cite

As urbanization accelerates, the evolving dynamics of village growth and decline have garnered widespread attention. Rural housing, as the most significant asset in villages, serves as the primary indicator of socio-economic development in rural areas. However, the extensive scale, diversity, and widespread distribution of villages make conducting a nationwide census of rural buildings a notably costly and time-intensive endeavor. Although deep learning techniques have been successfully applied by numerous researchers to map building footprints, the majority of this work is concentrated in urban areas, leaving large-scale datasets for rural buildings notably lacking. In this article, an exhaustive database of rural architecture has been established, featuring diverse rural building annotations from the majority of provinces in mainland China. Moreover, a realtime online platform for remote sensing image interpretation, integrating instance segmentation and boundary regularization, has been developed to streamline the extraction of building footprints from high-resolution imagery. Experimental results from predicting 43,992 rural building instances nationwide demonstrated that 33,210 were accurately identified, achieving a precision of 0.776, a recall of 0.755, and an F1 score of 0.765. Building upon this work, the maps of rural building areas and quantity are produced to clearly demonstrate the distribution of rural houses in parts of China. These data products can serve as vital supplements to public data products such as nighttime light data, land cover maps, national statistical yearbooks, and road network data, particularly in the field of rural studies.

show abstract

Section: Methodsmentioning

confidence: 99%

A Large-Scale Multipurpose Benchmark Dataset and Real-Time Interpretation Platform Based on Chinese Rural Buildings

Deng,

Xu,

Huang

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…Hybrid methods attempt to combine the strengths of edge-and region-based methods to improve results. This study employed a hybrid segmentation algorithm proposed by Hossain and Chen [16], which combines both edge-based and region-based methods. Initially, segments were generated using an edge-based approach, and subsequently merged using a region-based method.…”

Section: Methodological Framework 21 Image Segmentationmentioning

confidence: 99%

“…Even though those algorithms have been reported to have the highest accuracy, they often generate a salt-and-pepper effect. The pooling operations used in these methods to enhance semantic information create blurred boundaries [16] in classification. By witnessing the success of CNNs, several researchers integrated CNNs with GEOBIA.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Deep Learning (DL)-Based Tabular Models for Building Mapping Using High-Resolution Red, Green, and Blue Imagery and the Geographic Object-Based Image Analysis Framework

Hossain,

Chen

2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Identifying urban buildings in high-resolution RGB images presents challenges, mainly due to the absence of near-infrared bands in UAVs and Google Earth imagery and the diversity in building attributes. Deep learning (DL) methods, especially Convolutional Neural Networks (CNNs), are widely used for building extraction but are primarily pixel-based. Geographic Object-Based Image Analysis (GEOBIA) has emerged as an essential approach for high-resolution imagery. However, integrating GEOBIA with DL models presents challenges, including adapting DL models for irregular-shaped segments and effectively merging DL outputs with object-based features. Recent developments include tabular DL models that align well with GEOBIA. GEOBIA stores various features for image segments in a tabular format, yet the effectiveness of these tabular DL models for building extraction still needs to be explored. It also needs to clarify which features are crucial for distinguishing buildings from other land-cover types. Typically, GEOBIA employs shallow learning (SL) classifiers. Thus, this study evaluates SL and tabular DL classifiers for their ability to differentiate buildings from non-building features. Furthermore, these classifiers are assessed for their capacity to handle roof heterogeneity caused by sun exposure and roof materials. This study concludes that some SL classifiers perform similarly to their DL counterparts, and it identifies critical features for building extraction.

show abstract

“…Stated by study [23] in specific cases, segmenting color images offers greater benefits compared to grayscale images because of the more extensive feature set present in color images. Color images represent each pixel through a combination of 224 color components of R, G, B, covering both chromatic and intensity aspects.…”

Section: 𝑁 (𝑥) ∩ 𝐴𝑖(𝑥) ≠ ømentioning

confidence: 99%

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

Irianto,

Karnila

et al. 2024

IJACSA

View full text Add to dashboard Cite

Degenerative diseases can impact individuals of any age, encompassing children and teenagers; however, they typically tend to affect productive or adult individuals. Globally, conventional and advanced diagnostic methods, including those developed in Indonesia, have emerged to identify and manage these health conditions. Problems in brain tumor detection are the intricate process of precisely and effectively identifying the presence of tumors in the brain. On the other hand, diagnosing brain tumors in the laboratory poses issues related to time consumption, inaccuracy, lack of consistency, and costliness. This study specifically concentrates on the early detection of brain tumors by analyzing images generated through MRI scans. Unlike the traditional method of manual image analysis conducted by seasoned physicians, our approach integrates fuzzy logic to enable the early identification of brain tumors. The principal objective of this research is to enhance understanding and develop an intelligent, swift, and precise application for diagnosing brain tumors using medical imaging. The segmentation technique provides practical technology for the early detection of brain tumors. Utilizing a dataset comprising over 13,000 data points and undergoing a year-long training process with approximately 1,310 MRI images, the research culminates in the creation of a tool or software application system for the analysis of medical images. Despite the impressive precision score of 0.9992, highlighting its exceptional accuracy in correctly identifying positive instances, the recall value of 0.5767 suggests the potential exclusion of a significant number of actual positive instances in its predictions.

show abstract

A hybrid image segmentation method for building extraction from high-resolution RGB images

Cited by 20 publications

References 95 publications

A Large-Scale Multipurpose Benchmark Dataset and Real-Time Interpretation Platform Based on Chinese Rural Buildings

A Large-Scale Multipurpose Benchmark Dataset and Real-Time Interpretation Platform Based on Chinese Rural Buildings

Performance Comparison of Deep Learning (DL)-Based Tabular Models for Building Mapping Using High-Resolution Red, Green, and Blue Imagery and the Geographic Object-Based Image Analysis Framework

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

Contact Info

Product

Resources

About