Effective analysis of noise levels due to vehicular traffic in urban area using deep learning with OALO model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

Download Full-text

Building Detection in Earthquake Prone Urban Area with Satellite Imagery Data Using Deep Learning

10.1109/aidas53897.2021.9574257 ◽

2021 ◽

Author(s):

Edy Irwansyah ◽

Alexander A. Santoso. Gunawan ◽

Calvin Surya ◽

Dewa Ayu Defina Audrey Nathania

Keyword(s):

Deep Learning ◽

Urban Area ◽

Satellite Imagery ◽

Building Detection ◽

Imagery Data

Download Full-text

Enhancing GNSS Performance and Detection of Road Crossing in Urban Area Using Deep Learning

2019 IEEE Intelligent Transportation Systems Conference (ITSC) ◽

10.1109/itsc.2019.8917224 ◽

2019 ◽

Author(s):

Sang Jae Cho ◽

Bo Seong Kim ◽

Tae Seon Kim ◽

Seung-Hyun Kong

Keyword(s):

Deep Learning ◽

Urban Area ◽

Road Crossing

Download Full-text

Designing a wireless sensor network for vehicular traffic and CO2 pollution monitoring in an urban area

2017 IEEE 9th Latin-American Conference on Communications (LATINCOM) ◽

10.1109/latincom.2017.8240168 ◽

2017 ◽

Author(s):

Byron A. Bravo Granda ◽

Luis A. Belduma Belduma ◽

Edwin J. Coronel Gonzalez ◽

Angel F. Soto Sarango

Keyword(s):

Wireless Sensor Network ◽

Sensor Network ◽

Urban Area ◽

Pollution Monitoring ◽

Wireless Sensor ◽

Vehicular Traffic

Download Full-text

3 Elaboración del mapa de ruido de las calles de la ciudad de Cuenca, a de partir de características viales y densidad de tráfico.

UNIVERSIDAD VERDAD ◽

10.33324/uv.v1i73.36 ◽

2017 ◽

pp. 39-49

Author(s):

Christian Tacuri Ortega ◽

Felipe Calderón Peralvo ◽

Julia Martínez Gavilanes ◽

Chester Sellers Walden ◽

Omar Delgado Inga

Keyword(s):

Sound Pressure ◽

Vehicular Traffic ◽

Noise Levels ◽

High Noise ◽

The Road ◽

Palabras Clave ◽

Car Park ◽

Progressive Growth ◽

Road Characteristics ◽

The City

Debido al progresivo crecimiento del parque automotor en la ciudad de Cuenca-Ecuador, se evidencian congestiones por la sobresaturación del tráfico en las vías de la ciudad, las cuales colapsan en horas pico, ocasionando, como consecuencia, elevados niveles de ruido. Por esta razón, el presente artículo tiene como objeto modelar el ruido generado por el tráfico vehicular en las principales calles de la ciudad. Para ello se utilizará el modelo de predicción de ruido NMPB-Routes-96 en el software especializado en ruido “Datakustik CadnaA”; para el efecto se ha realizado un levantamiento de los datos requeridos por el software, además de validar, depurar y sistematizar la información de la geodatabase proporcionada por la Dirección Municipal de Tránsito y Transporte (DMT) del GAD municipal de Cuenca, en la cual hay información sobre las características viales y del parque auto motor de la ciudad. Palabras clave: Ruido, mapa, CadnaA, nivel de presión sonora. AbstractDue to the progressive growth of the car park in the city of Cuenca-Ecuador, there is evidence of congestion due to the over-saturation of traffic on the city’s roads, which collapse in peak hours, resulting in high noise levels, resulting in high noise levels. For this reason, this article aims to model the noise generated by vehicular traffic in the main streets of the city, using the noise prediction model NMPB-Routes-96 in the specialized noise software “Datakustik CadnaA”, for this purpose a survey of the data required by the software has been carried out, besides validating, debugging and systematizing of the geodatabase information provided by the Municipal Transit and Transport Department (DMT) of the municipal GAD of Cuenca , in which there is information about the road characteristics and of the automotive park of the city. keywords: Noise, map, CadnaA, sound pressure level.

Download Full-text