Detection of Roads in Satellite Images Using Deep Learning Technique

Kanakaraddi, Suvarna G.; Chikaraddi, Ashok K.; Pooja, B. L.; Preeti, T.

doi:10.1007/978-981-15-8354-4_44

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recently emerging deep learning has demonstrated great potential in feature extraction based on end-to-end architecture, and the performance of deep learning has far exceeded traditional machine learning in many applications. In fact, deep learning has penetrated into various aspects of remote sensing applications such as road recognition [9], building recognition [10], crop yield estimation [11], and pest and disease identification [12]. Multiple advanced semantic segmentation models such as U-Net [13], FCN [14], SEGNet [15], PSPNet [16], and Deeplabs [17,18] have been proposed for the recognition of specific targets from remote sensing images In the semantic segmentation models described above, a convolutional neural network composed of multiple convolutional layers and pooling layers is used to learn the underlying and high-level features of the target objects and identify different types of features from remote sensing images, and these semantic segmentation models have exhibited desirable performance in many remote sensing image analysis tasks.…”

Section: Introductionmentioning

confidence: 99%

Construction of Improved Semantic Segmentation Model and Application to Extraction of Anthropogenically Disturbed Parcels With Soil Erosion From Remote Sensing Images

Li³

et al. 2023

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

View full text Add to dashboard Cite

With the rapid socioeconomic development in China, the increasing soil erosion caused by anthropogenic production and construction activities is taking place, which is characterized by short duration, high frequency, and great damage to its surrounding environment. Therefore, the regulation and control of soil erosion of anthropogenically disturbed parcels is an urgent task. This study proposes an improved model that combines the boundary constraint and jagged hybrid dilated convolution channel shuffling module (BCJHDC) and the polarized self-attention (PSA) module for extracting anthropogenically disturbed parcels with soil erosion (ADPSE) from high-resolution remote sensing images in Hubei Province. Firstly, the PSA module is added to the encoder to better extract the feature information of the target object. Secondly, BCJHDC module is used to extract multi-scale semantic information from images and improve the boundary segmentation quality. Precision, recall, intersection over union (IOU), and F1 score are calculated to evaluate the model accuracy. The results indicate that our improved model performs well on the human-perturbed parcel extraction task with an F1 of 87.92% and an IOU of 78.44%. Ablation experiments and application experiments suggest the validity the applicability, and the portability of our proposed improved model, respectively. Compared with the other 7 advanced semantic segmentation models, our improved model has significant advantages. Overall, this study provides valuable reference for policy formulation of water and soil conservation.

show abstract

Section: Introductionmentioning

confidence: 99%

Construction of Improved Semantic Segmentation Model and Application to Extraction of Anthropogenically Disturbed Parcels With Soil Erosion From Remote Sensing Images

Li³

et al. 2023

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

View full text Add to dashboard Cite

show abstract

“…One solution for this is through the use of deep learning techniques that make it possible to detect entities in satellite images with several layers in neural networks to carry out the analysis of points of interest in a versatile way. [1], [2], [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Satellite Images Using Deep Learning Techniques and Remotely Piloted Aircraft for a Detailed Description of Tertiary Roads

Moreno-Vergara,

Sarmiento-Iscala,

Casares-Pavia

et al. 2021

Rev. Fac. Ing.

View full text Add to dashboard Cite

This document presents the results of a proof of concept for describing with more detail the social and complementary infrastructure around the tertiary roads of the Taminango region in the department of Nariño, Colombia. A dataset with samples of free satellite images from Google Maps and OpenStreetMaps was obtained. Then, a supervised deep learning algorithm with FCN (Fully Convolutional Network) topology is applied for the points of interest labeling process and the identification of the state of the roads using Keras and TensorFlow. Subsequently, a system consisting of a desktop application and a mobile application that integrates the functionalities of the trained algorithm through an intuitive interface and simple logic that stimulates interaction with the consultant is proposed. The desktop application includes a GUI designed in Python for tagging points of interest. The mobile application was developed with Flutter and comprises a database with documentation of the routes and road network in the region. It includes an augmented reality system in Vuforia Engine and Unity with virtual content developed in Blender and SolidWorks; A 3D model of the map of the region has been recreated for easier interaction and visualization of the points of interest and the status of the studied roads. In addition, complementary information was collected through remotely piloted aircraft for data acquisition in environments difficult to access, and through the community participation for the description and identification of areas not visible on official maps or statistics. This study addresses a method for the classification and identification of state of tertiary road network of the studied region, as well as labeling points of interest for the efficient management of resources for the development of new infrastructure there.

show abstract

Mapping wheel-ruts from timber harvesting operations using deep learning techniques in drone imagery

Bhatnagar

Puliti

Talbot

et al. 2022

Forestry: An International Journal of Forest Research

View full text Add to dashboard Cite

Wheel ruts, i.e. soil deformations caused by harvesting machines, are considered a negative environmental impact of forest operations and should be avoided or ameliorated. However, the mapping of wheel ruts that would be required to monitor harvesting operations and to plan amelioration measures is a tedious and time-consuming task. Here, we examined whether a combination of drone imagery and algorithms from the field of artificial intelligence can automate the mapping of wheel ruts. We used a deep-learning image-segmentation method (ResNet50 + UNet architecture) that was trained on drone imagery acquired shortly after harvests in Norway, where more than 160 km of wheel ruts were manually digitized. The cross-validation of the model based on 20 harvested sites resulted in F1 scores of 0.69–0.84 with an average of 0.77, and in total, 79 per cent of wheel ruts were correctly detected. The highest accuracy was obtained for severe wheel ruts (average user’s accuracy (UA) = 76 per cent), and the lowest accuracy was obtained for light wheel ruts (average UA = 67 per cent). Considering the nowadays ubiquitous availability of drones, the approach presented in our study has the potential to greatly increase the ability to effectively map and monitor the environmental impact of final felling operations with respect to wheel ruts. The automated mapping of wheel ruts may serve as an important input to soil impact analyses and thereby support measures to restore soil damages.

show abstract

Detection of Roads in Satellite Images Using Deep Learning Technique

Cited by 3 publications

References 11 publications

Construction of Improved Semantic Segmentation Model and Application to Extraction of Anthropogenically Disturbed Parcels With Soil Erosion From Remote Sensing Images

Construction of Improved Semantic Segmentation Model and Application to Extraction of Anthropogenically Disturbed Parcels With Soil Erosion From Remote Sensing Images

Analysis of Satellite Images Using Deep Learning Techniques and Remotely Piloted Aircraft for a Detailed Description of Tertiary Roads

Mapping wheel-ruts from timber harvesting operations using deep learning techniques in drone imagery

Contact Info

Product

Resources

About