A deep learning approach for road damage detection from smartphone images
With recent advances in technology, it is feasible to conveniently monitor urban roads using
various cameras, such as surveillance cameras, in-vehicle cameras, or smartphones, and …
various cameras, such as surveillance cameras, in-vehicle cameras, or smartphones, and …
Yet another deep learning approach for road damage detection using ensemble learning
V Hegde, D Trivedi, A Alfarrarjeh… - … conference on big …, 2020 - ieeexplore.ieee.org
For efficient road maintenance, an automated monitoring system is required to avoid
laboriously and time-consuming manual inspection by road administration crews. One …
laboriously and time-consuming manual inspection by road administration crews. One …
[HTML][HTML] Quantifying land use heterogeneity on drought conditions for mitigation strategies development in the Dongjiang River Basin, China
Spatially-invariant land use and cover changes (LUCC) are not suitable for managing non-
stationary drought conditions. Therefore, developing a spatially varying framework for …
stationary drought conditions. Therefore, developing a spatially varying framework for …
An approach on discretizing time series using recurrent neural network
LEI Kuan-Cheok, XD Zhang - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
In this article we discussed a method to discretize multivariate time series using the recurrent
neural network (RNN). Time series discretization is a technique to convert real-number time …
neural network (RNN). Time series discretization is a technique to convert real-number time …
Recognizing material of a covered object: A case study with graffiti
Recognizing materials using image analysis is a classic problem. However, little research
has been done with the images which have visual impediments such as noise, obstacle, or …
has been done with the images which have visual impediments such as noise, obstacle, or …
Requirement-driven remote sensing metadata planning and online acquisition method for large-scale heterogeneous data
Remote sensing data acquisition is one of the most essential processes in the field of Earth
observation. However, traditional methods to acquire data do not satisfy the requirements of …
observation. However, traditional methods to acquire data do not satisfy the requirements of …
A Synthetic Over-sampling method with Minority and Majority classes for imbalance problems
HA Khorshidi, U Aickelin - arXiv preprint arXiv:2011.04170, 2020 - arxiv.org
Class imbalance is a substantial challenge in classifying many real-world cases. Synthetic
over-sampling methods have been effective to improve the performance of classifiers for …
over-sampling methods have been effective to improve the performance of classifiers for …
TVDP: Translational visual data platform for smart cities
SH Kim, A Alfarrarjeh, G Constantinou… - 2019 IEEE 35th …, 2019 - ieeexplore.ieee.org
This paper proposes a platform, dubbed" Translational Visual Data Platform (TVDP)", to
collect, manage, analyze urban visual data which enables participating community members …
collect, manage, analyze urban visual data which enables participating community members …
A crowd-based image learning framework using edge computing for smart city applications
G Constantinou, GS Ramachandran… - 2019 IEEE Fifth …, 2019 - ieeexplore.ieee.org
Smart city applications covering a wide area such as traffic monitoring and pothole detection
are gradually adopting more image machine learning algorithms utilizing ubiquitous camera …
are gradually adopting more image machine learning algorithms utilizing ubiquitous camera …
A data-centric approach for image scene localization
Due to the ubiquity of GPS-equipped cameras such as smartphones, more photos are
getting automatically tagged with camera locations (referred to as geo-tagged images) so …
getting automatically tagged with camera locations (referred to as geo-tagged images) so …