A Novel Framework Based on Mask R-CNN and Histogram Thresholding for Scalable Segmentation of New and Old Rural Buildings

Li, Ying; Xu, Weipan; Chen, Haohui; Jiang, Junhao; Li, Xun

doi:10.3390/rs13061070

Cited by 49 publications

(28 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Reference [ 41 ] employed the Mask R-CNN [ 42 ] method to obtain each version of the structure individually. Reference [ 43 ] used the similar strategy to separate ancient and new building types.…”

Section: Literature Reviewmentioning

confidence: 99%

Detecting Buildings and Nonbuildings from Satellite Images Using U-Net

Alsabhan

Alotaiby

Dudin

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Automatic building detection from high-resolution satellite imaging images has many applications. Understanding socioeconomic development and keeping track of population migrations are essential for effective civic planning. These civil feature systems may also help update maps after natural disasters or in geographic regions undergoing dramatic population expansion. To accomplish the desired goal, a variety of image processing techniques were employed. They are often inaccurate or take a long time to process. Convolutional neural networks (CNNs) are being designed to extract buildings from satellite images, based on the U-Net, which was first developed to segment medical images. The minimal number of images from the open dataset, in RGB format with variable shapes, reveals one of the advantages of the U-Net; that is, it develops excellent accuracy from a limited amount of training material with minimal effort and training time. The encoder portion of U-Net was altered to test the feasibility of using a transfer learning facility. VGGNet and ResNet were both used for the same purpose. The findings of these models were also compared to our own bespoke U-Net, which was designed from the ground up. With an accuracy of 84.9%, the VGGNet backbone was shown to be the best feature extractor. Compared to the current best models for tackling a similar problem with a larger dataset, the present results are considered superior.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Detecting Buildings and Nonbuildings from Satellite Images Using U-Net

Alsabhan

Alotaiby

Dudin

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In Score-CAM, the feature maps need to be upsampled to the same shape with the input image according to Equation (14), and the CIC is calculated to measure the correlation of the feature map and the input image. No matter what kind of upsampling method is used, some irrelevant information will be introduced; inevitably, meanwhile, such an upsampling operation is required for every feature map.…”

Section: Self-matching Cammentioning

confidence: 99%

“…In this case, the efficiency will be enhanced dramatically as long as the network is well trained. The convolutional neural network (CNN) is one of the most successful models in various computer vision fields [2,[13][14][15]. The key to its superiority lies in the way it uses local connections and shared weights.…”

Section: Introductionmentioning

confidence: 99%

Self-Matching CAM: A Novel Accurate Visual Explanation of CNNs for SAR Image Interpretation

et al. 2021

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) image interpretation has long been an important but challenging task in SAR imaging processing. Generally, SAR image interpretation comprises complex procedures including filtering, feature extraction, image segmentation, and target recognition, which greatly reduce the efficiency of data processing. In an era of deep learning, numerous automatic target recognition methods have been proposed based on convolutional neural networks (CNNs) due to their strong capabilities for data abstraction and mining. In contrast to general methods, CNNs own an end-to-end structure where complex data preprocessing is not needed, thus the efficiency can be improved dramatically once a CNN is well trained. However, the recognition mechanism of a CNN is unclear, which hinders its application in many scenarios. In this paper, Self-Matching class activation mapping (CAM) is proposed to visualize what a CNN learns from SAR images to make a decision. Self-Matching CAM assigns a pixel-wise weight matrix to feature maps of different channels by matching them with the input SAR image. By using Self-Matching CAM, the detailed information of the target can be well preserved in an accurate visual explanation heatmap of a CNN for SAR image interpretation. Numerous experiments on a benchmark dataset (MSTAR) verify the validity of Self-Matching CAM.

show abstract

“…In this context, a mask is a binary pixel matrix representing the exact location and size of detected objects. Mask R-CNN has been shown to identify and characterize objects in remote-sensing data robustly and successfully, such as identifying buildings from satellite imagery and mapping topographic features captured with lidar data [37,38]. As a result of its computational efficiency and accuracy in object segmentation and classification, the Mask R-CNN is a robust option for identifying and characterizing wind turbine wakes in complex terrain.…”

Section: Introductionmentioning

confidence: 99%

Region-Based Convolutional Neural Network for Wind Turbine Wake Characterization in Complex Terrain

et al. 2021

View full text Add to dashboard Cite

We present a proof of concept of wind turbine wake identification and characterization using a region-based convolutional neural network (CNN) applied to lidar arc scan images taken at a wind farm in complex terrain. We show that the CNN successfully identifies and characterizes wakes in scans with varying resolutions and geometries, and can capture wake characteristics in spatially heterogeneous fields resulting from data quality control procedures and complex background flow fields. The geometry, spatial extent and locations of wakes and wake fragments exhibit close accord with results from visual inspection. The model exhibits a 95% success rate in identifying wakes when they are present in scans and characterizing their shape. To test model robustness to varying image quality, we reduced the scan density to half the original resolution through down-sampling range gates. This causes a reduction in skill, yet 92% of wakes are still successfully identified. When grouping scans by meteorological conditions and utilizing the CNN for wake characterization under full and half resolution, wake characteristics are consistent with a priori expectations for wake behavior in different inflow and stability conditions.

show abstract

A Novel Framework Based on Mask R-CNN and Histogram Thresholding for Scalable Segmentation of New and Old Rural Buildings

Cited by 49 publications

References 48 publications

Detecting Buildings and Nonbuildings from Satellite Images Using U-Net

Detecting Buildings and Nonbuildings from Satellite Images Using U-Net

Self-Matching CAM: A Novel Accurate Visual Explanation of CNNs for SAR Image Interpretation

Region-Based Convolutional Neural Network for Wind Turbine Wake Characterization in Complex Terrain

Contact Info

Product

Resources

About