The population of Yangon has increased more than two times in the last 40 years and will reach 9.... more The population of Yangon has increased more than two times in the last 40 years and will reach 9.5 million by 2035. Owing to changes in car import policies, the number of cars in Yangon has increased from 3.6 million to 6.3 million in 5 years. This causes severe traffic congestion, resulting in social, economic, and environmental impacts. Rail transportation is one solution to this problem, but regular maintenance of railway tracks is necessary. In this study, onboard sensor measurement and satellite image analysis are used to monitor rail track conditions for the early detection of damage. The accelerometer in a smartphone is placed against the car body to measure the vertical and lateral acceleration. The smartphone vibrates as the cabin vibrates when the train passes irregular rail track sections. Phased-array-type L-band synthetic aperture radar images are analyzed using the interferometric technique to detect rail track irregularities. Thus, the rail track conditions can be est...
UAV photography system is implementation of efficient data acquisition techniques, high resolutio... more UAV photography system is implementation of efficient data acquisition techniques, high resolution texture, low cost and using in commercial application. In research paper, we got several images from UAV (unmanned aerial vehicle) and produced image mosaic. Firstly, this paper proposes image mosaic method based of SIFT (scale invariance feature transform) feature to detect key points, scaling, rotation and matching between two images in the image mosaic. RANSAC (random sample consensus) method is used to find homography, transformation and adjust colour for rgb or grey scale for grey image with SIFT (scale invariance feature transform) matching location and then produced mosaic image from combination of SIFT (scale invariance feature transform) and RANSAC (random sample consensus). The results from experiment based on four pairs of images with 70% overlapped captures by using the camera of UAV show that our method has many feature points and matching points for image mosaic. In this ...
International Journal of Scientific & Technology Research, 2015
GPS is playing in very important role in our modern mobile societies. Software approach is very f... more GPS is playing in very important role in our modern mobile societies. Software approach is very flexible rather than the traditional hardware receivers. The soft-GPS receiver includes two portions: hardware and software. In hardware portion, an antenna, filter, down-converter from RF (Radio Frequency) to IF (Intermediate Frequency), and an ADC (Analog to Digital Converter) are included. In software portion, signal processing such as acquisition, tracking and navigation that runs on general purpose processor is included. The GPS signal is taken from N-FUELS (Full Educational Library of Signals for Navigation) signal simulator. The heart of soft-GPS receiver is the synchronization processes such as acquisition and tracking. In tracking, there are two main loops for code and carrier tracking. The objective of this paper is to analyse and find the optimum discriminator function for the code tracking loop in soft-GPS receivers. The delay lock loop (DLL) is a well-known technique to track...
In this paper, building footprints in Yangon city are automatically extracted only from high reso... more In this paper, building footprints in Yangon city are automatically extracted only from high resolution optical satellite image by using deep learning algorithm. Automatic extraction of building footprints only from optical satellite images is a very challenging task because of spatial and spectral complexities of urban objects, especially trees, buildings occluded by trees, shadow and water bodies. Moreover, very high spatial resolution of satellite image is necessary for building level extraction. In this work, pix2pix is used for automatic building footprint extraction in Yangon City. Pix2pix is based on conditional generative adversarial network which is an unsupervised deep learning algorithm that only needs fewer labelled samples. First, four different models of pix2pix are designed and trained based on different number of epochs, and different types and number of training images. Second, the trained pix2pix models are tested on the images of the study area. After that, the ou...
The population of Yangon has increased more than two times in the last 40 years and will reach 9.... more The population of Yangon has increased more than two times in the last 40 years and will reach 9.5 million by 2035. Owing to changes in car import policies, the number of cars in Yangon has increased from 3.6 million to 6.3 million in 5 years. This causes severe traffic congestion, resulting in social, economic, and environmental impacts. Rail transportation is one solution to this problem, but regular maintenance of railway tracks is necessary. In this study, onboard sensor measurement and satellite image analysis are used to monitor rail track conditions for the early detection of damage. The accelerometer in a smartphone is placed against the car body to measure the vertical and lateral acceleration. The smartphone vibrates as the cabin vibrates when the train passes irregular rail track sections. Phased-array-type L-band synthetic aperture radar images are analyzed using the interferometric technique to detect rail track irregularities. Thus, the rail track conditions can be est...
UAV photography system is implementation of efficient data acquisition techniques, high resolutio... more UAV photography system is implementation of efficient data acquisition techniques, high resolution texture, low cost and using in commercial application. In research paper, we got several images from UAV (unmanned aerial vehicle) and produced image mosaic. Firstly, this paper proposes image mosaic method based of SIFT (scale invariance feature transform) feature to detect key points, scaling, rotation and matching between two images in the image mosaic. RANSAC (random sample consensus) method is used to find homography, transformation and adjust colour for rgb or grey scale for grey image with SIFT (scale invariance feature transform) matching location and then produced mosaic image from combination of SIFT (scale invariance feature transform) and RANSAC (random sample consensus). The results from experiment based on four pairs of images with 70% overlapped captures by using the camera of UAV show that our method has many feature points and matching points for image mosaic. In this ...
International Journal of Scientific & Technology Research, 2015
GPS is playing in very important role in our modern mobile societies. Software approach is very f... more GPS is playing in very important role in our modern mobile societies. Software approach is very flexible rather than the traditional hardware receivers. The soft-GPS receiver includes two portions: hardware and software. In hardware portion, an antenna, filter, down-converter from RF (Radio Frequency) to IF (Intermediate Frequency), and an ADC (Analog to Digital Converter) are included. In software portion, signal processing such as acquisition, tracking and navigation that runs on general purpose processor is included. The GPS signal is taken from N-FUELS (Full Educational Library of Signals for Navigation) signal simulator. The heart of soft-GPS receiver is the synchronization processes such as acquisition and tracking. In tracking, there are two main loops for code and carrier tracking. The objective of this paper is to analyse and find the optimum discriminator function for the code tracking loop in soft-GPS receivers. The delay lock loop (DLL) is a well-known technique to track...
In this paper, building footprints in Yangon city are automatically extracted only from high reso... more In this paper, building footprints in Yangon city are automatically extracted only from high resolution optical satellite image by using deep learning algorithm. Automatic extraction of building footprints only from optical satellite images is a very challenging task because of spatial and spectral complexities of urban objects, especially trees, buildings occluded by trees, shadow and water bodies. Moreover, very high spatial resolution of satellite image is necessary for building level extraction. In this work, pix2pix is used for automatic building footprint extraction in Yangon City. Pix2pix is based on conditional generative adversarial network which is an unsupervised deep learning algorithm that only needs fewer labelled samples. First, four different models of pix2pix are designed and trained based on different number of epochs, and different types and number of training images. Second, the trained pix2pix models are tested on the images of the study area. After that, the ou...
Uploads
Papers by Sao Hone Pha