scholarly journals Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7769
Author(s):  
Wansik Choi ◽  
Jun Heo ◽  
Changsun Ahn
Keyword(s):  
Autonomous Vehicles ◽  
Weather Conditions ◽  
Detection Algorithm ◽  
Road Surface ◽  
Detection Methods ◽  
Learning Technology ◽  
Surface Conditions ◽  
The Road ◽  
Detection Algorithms ◽  
Surface Detection

Road surface detection is important for safely driving autonomous vehicles. This is because the knowledge of road surface conditions, in particular, dry, wet, and snowy surfaces, should be considered for driving control of autonomous vehicles. With the rise of deep learning technology, road surface detection methods using deep neural networks (DNN) have been widely used for developing road surface detection algorithms. To apply DNN in road surface detection, the dataset should be large and well-balanced for accurate and robust performance. However, most of the images of road surfaces obtained through usual data collection processes are not well-balanced. Most of the collected surface images tend to be of dry surfaces because road surface conditions are highly correlated with weather conditions. This could be a challenge in developing road surface detection algorithms. This paper proposes a method to balance the imbalanced dataset using CycleGAN to improve the performance of a road surface detection algorithm. CycleGAN was used to artificially generate images of wet and snow-covered roads. The road surface detection algorithm trained using the CycleGAN-augmented dataset had a better IoU than the method using imbalanced basic datasets. This result shows that CycleGAN-generated images can be used as datasets for road surface detection to improve the performance of DNN, and this method can help make the data acquisition process easy.

scholarly journals The road weather model RoadSurf (v6.60b) driven by the regional climate model HCLIM38: evaluation over Finland

2019 ◽  
Vol 12 (8) ◽  
pp. 3481-3501 ◽  
Author(s):  
Erika Toivonen ◽  
Marjo Hippi ◽  
Hannele Korhonen ◽  
Ari Laaksonen ◽  
Markku Kangas ◽  
...  
Keyword(s):  
Regional Climate Model ◽  
Input Data ◽  
Climate Model ◽  
Regional Climate ◽  
Weather Conditions ◽  
Road Surface ◽  
Road Maintenance ◽  
Surface Conditions ◽  
The Road ◽  
Weather Model

Abstract. In this paper, we evaluate the skill of the road weather model RoadSurf to reproduce present-day road weather conditions in Finland. RoadSurf was driven by meteorological input data from cycle 38 of the high-resolution regional climate model (RCM) HARMONIE-Climate (HCLIM38) with ALARO physics (HCLIM38-ALARO) and ERA-Interim forcing in the lateral boundaries. Simulated road surface temperatures and road surface conditions were compared to observations between 2002 and 2014 at 25 road weather stations located in different parts of Finland. The main characteristics of road weather conditions were accurately captured by RoadSurf in the study area. For example, the model simulated road surface temperatures with a mean monthly bias of −0.3 ∘C and mean absolute error of 0.9 ∘C. The RoadSurf's output bias most probably stemmed from the absence of road maintenance operations in the model, such as snow plowing and salting, and the biases in the input meteorological data. The biases in the input data were most evident in northern parts of Finland, where the regional climate model HCLIM38-ALARO overestimated precipitation and had a warm bias in near-surface air temperatures during the winter season. Moreover, the variability in the biases of air temperature was found to explain on average 57 % of the variability in the biases of road surface temperature. On the other hand, the absence of road maintenance operations in the model might have affected RoadSurf's ability to simulate road surface conditions: the model tended to overestimate icy and snowy road surfaces and underestimate the occurrence of water on the road. However, the overall good performance of RoadSurf implies that this approach can be used to study the impacts of climate change on road weather conditions in Finland by forcing RoadSurf with future climate projections from RCMs, such as HCLIM.

scholarly journals CNN-Based Road-Surface Crack Detection Model That Responds to Brightness Changes

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1402
Author(s):  
Taehee Lee ◽  
Yeohwan Yoon ◽  
Chanjun Chun ◽  
Seungki Ryu
Keyword(s):  
Surface Crack ◽  
Autonomous Vehicles ◽  
Crack Detection ◽  
Model Performance ◽  
Semantic Segmentation ◽  
Road Surface ◽  
Image Brightness ◽  
The Road ◽  
Detection Model ◽  
Artificial Intelligence Models

Poor road-surface conditions pose a significant safety risk to vehicle operation, especially in the case of autonomous vehicles. Hence, maintenance of road surfaces will become even more important in the future. With the development of deep learning-based computer image processing technology, artificial intelligence models that evaluate road conditions are being actively researched. However, as the lighting conditions of the road surface vary depending on the weather, the model performance may degrade for an image whose brightness falls outside the range of the learned image, even for the same road. In this study, a semantic segmentation model with an autoencoder structure was developed for detecting road surface along with a CNN-based image preprocessing model. This setup ensures better road-surface crack detection by adjusting the image brightness before it is input into the road-crack detection model. When the preprocessing model was applied, the road-crack segmentation model exhibited consistent performance even under varying brightness values.

scholarly journals Road Hazard Assessment Using Pothole and Traffic Data in South Korea

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Choong Heon Yang ◽  
Jin Guk Kim ◽  
Sung Pil Shin
Keyword(s):  
Hazard Assessment ◽  
Traffic Safety ◽  
Hazard Index ◽  
Surface Damage ◽  
Road Surface ◽  
Risk Level ◽  
Traffic Data ◽  
Surface Conditions ◽  
The Road ◽  
Damage Data

Road surface conditions have a direct effect on the quality of driving, which in turn affects overall traffic flow. Many studies have been conducted to accurately identify road surface conditions using diverse technologies. However, these previously proposed methods may still be insufficient to estimate actual risks along the roads because the exact road risk levels cannot be determined from only road surface damage data. The actual risk level of the road must be derived by considering both the road surface damage data as well as other factors such as speed. In this study, the road hazard index is proposed using smartphone-obtained pothole and traffic data to represent the level of risk due to road surface conditions. The relevant algorithm and its operating system are developed to produce the estimated index values that are classified into four levels of road risk. This road hazard index can assist road agencies in establishing road maintenance plans and budgets and will allow drivers to minimize the risk of accidents by adjusting their driving speeds in advance of dangerous road conditions. To demonstrate the proposed risk hazard assessment methodology, road hazards were assessed along specific test road sections based on observed pothole and historical travel speed data. It was found that the proposed methodology provides a rational method for improving traffic safety.

scholarly journals Road Surface Condition Forecasting in France

2009 ◽  
Vol 48 (12) ◽  
pp. 2513-2527 ◽  
Author(s):  
L. Bouilloud ◽  
E. Martin ◽  
F. Habets ◽  
A. Boone ◽  
P. Le Moigne ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Initial Conditions ◽  
Meteorological Data ◽  
Surface Condition ◽  
Road Surface ◽  
Snow Layer ◽  
Surface Conditions ◽  
The Road ◽  
Road Surface Temperature ◽  
On The Road

Abstract A numerical model designed to simulate the evolution of a snow layer on a road surface was forced by meteorological forecasts so as to assess its potential for use within an operational suite for road management in winter. The suite is intended for use throughout France, even in areas where no observations of surface conditions are available. It relies on short-term meteorological forecasts and long-term simulations of surface conditions using spatialized meteorological data to provide the initial conditions. The prediction of road surface conditions (road surface temperature and presence of snow on the road) was tested at an experimental site using data from a comprehensive experimental field campaign. The results were satisfactory, with detection of the majority of snow and negative road surface temperature events. The model was then extended to all of France with an 8-km grid resolution, using forcing data from a real-time meteorological analysis system. Many events with snow on the roads were simulated for the 2004/05 winter. Results for road surface temperature were checked against road station data from several highways, and results for the presence of snow on the road were checked against measurements from the Météo-France weather station network.

scholarly journals Real-Time Vehicle Detection Algorithm Based on Vision and Lidar Point Cloud Fusion

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Hai Wang ◽  
Xinyu Lou ◽  
Yingfeng Cai ◽  
Yicheng Li ◽  
Long Chen
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Point Cloud ◽  
Vehicle Detection ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Depth Information ◽  
Detection Accuracy ◽  
Classification Rate

Vehicle detection is one of the most important environment perception tasks for autonomous vehicles. The traditional vision-based vehicle detection methods are not accurate enough especially for small and occluded targets, while the light detection and ranging- (lidar-) based methods are good in detecting obstacles but they are time-consuming and have a low classification rate for different target types. Focusing on these shortcomings to make the full use of the advantages of the depth information of lidar and the obstacle classification ability of vision, this work proposes a real-time vehicle detection algorithm which fuses vision and lidar point cloud information. Firstly, the obstacles are detected by the grid projection method using the lidar point cloud information. Then, the obstacles are mapped to the image to get several separated regions of interest (ROIs). After that, the ROIs are expanded based on the dynamic threshold and merged to generate the final ROI. Finally, a deep learning method named You Only Look Once (YOLO) is applied on the ROI to detect vehicles. The experimental results on the KITTI dataset demonstrate that the proposed algorithm has high detection accuracy and good real-time performance. Compared with the detection method based only on the YOLO deep learning, the mean average precision (mAP) is increased by 17%.

scholarly journals ROAD SURFACE DETECTION FROM MOBILE LIDAR DATA

2018 ◽  
Vol IV-5 ◽  
pp. 95-101 ◽  
Author(s):  
M. Yadav ◽  
B. Lohani ◽  
A. K. Singh
Keyword(s):  
Point Cloud ◽  
Three Dimensional ◽  
Test Site ◽  
Road Surface ◽  
Lidar Data ◽  
Rural Roads ◽  
The Road ◽  
Surface Detection ◽  
Rural Road ◽  
Data Points

<p><strong>Abstract.</strong> The accurate three-dimensional road surface information is highly useful for health assessment and maintenance of roads. It is basic information for further analysis in several applications including road surface settlement, pavement condition assessment and slope collapse. Mobile LiDAR system (MLS) is frequently used now a days to collect detail road surface and its surrounding information in terms three-dimensional (3D) point cloud. Extraction of road surface from volumetric point cloud data is still in infancy stage because of heavy data processing requirement and the complexity in the road environment. The extraction of roads especially rural road, where road-curb is not present is very tedious job especially in Indian roadway settings. Only a few studies are available, and none for Indian roads, in the literature for rural road detection. The limitations of existing studies are in terms of their lower accuracy, very slow speed of data processing and detection of other objects having similar characteristics as the road surface. A fast and accurate method is proposed for LiDAR data points of road surface detection, keeping in mind the essence of road surface extraction especially for Indian rural roads. The Mobile LiDAR data in <i>XYZI</i> format is used as input in the proposed method. First square gridding is performed and ground points are roughly extracted. Then planar surface detection using mathematical framework of principal component analysis (PCA) is performed and further road surface points are detected using similarity in intensity and height difference of road surface pointe in their neighbourhood.</p><p>A case study was performed on the MLS data points captured along wide-street (two-lane road without curb) of 156<span class="thinspace"></span>m length along rural roadway site in the outskirt of Bengaluru city (South-West of India). The proposed algorithm was implemented on the MLS data of test site and its performance was evaluated it terms of recall, precision and overall accuracy that were 95.27%, 98.85% and 94.23%, respectively. The algorithm was found computationally time efficient. A 7.6 million MLS data points of size 27.1<span class="thinspace"></span>MB from test site were processed in 24 minutes using the available computational resources. The proposed method is found to work even for worst case scenarios, i.e., complex road environments and rural roads, where road boundary is not clear and generally merged with road-side features.</p>

scholarly journals Detection of Coordinate Based Accident-Prone Areas on Road Surface using Machine Learning Methods

2020 ◽  
Vol 12 (3) ◽  
pp. 19-25
Author(s):  
Anitha Kumari Dara ◽  
Dr. A. Govardhan
Keyword(s):  
Spatial Data ◽  
Surface Defects ◽  
Road Accident ◽  
Road Surface ◽  
The Other ◽  
Work Outcomes ◽  
Traffic Density ◽  
Surface Conditions ◽  
The Road ◽  
On The Road

The growth in the road networks in India and other developing countries have influenced the growth in transport industry and other industries, which depends on the road network for operations. The industries such as postal services or mover services have influenced the similar growths in these industries as well. However, the dependency of these industries is high on the road surface conditions and any deviation on the road surface conditions can also influence the performance of the services provided by the mentioned services. Nonetheless, the conditions of the road surface are one of the prime factors for road safety and number of evidences are found, which are discussed in subsequent sections of this work, that the bad road surface conditions are increasing the road accidents. Several parallel research attempts are deployed in order to find out, the regions where the road surface conditions are not proper, and the traffic density is higher. Nevertheless, outcomes of these parallel works are highly criticised due to the lack of accuracy in detection of the road surface defects, detection of accurate location of the defects and detection of the traffic density data from various sources. Thus, this work proposes a novel framework for detection of the road defect and further mapping to the spatial data coordinates resulting into the detection of the accident-prone zones or accident affinities of the roads. This work deploys a self-adjusting parametric coefficient-based regression model for detection of the risk factors of the road defects and in the other hand, extracts the traffic density of the road regions and further maps the accident affinities. This work outcomes into 97.69% accurate detection of the road accident affinity and demonstrates less complexity compared with the other parallel research outcomes

scholarly journals Image target detection algorithm compression and pruning based on neural network

2021 ◽  
Vol 18 (2) ◽  
pp. 499-516
Author(s):  
Yan Sun ◽  
Zheping Yan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Target Detection ◽  
Network Model ◽  
Detection Algorithm ◽  
Image Feature ◽  
Propagation Mode ◽  
Learning Technology ◽  
Image Detection ◽  
Detection Algorithms

The main purpose of target detection is to identify and locate targets from still images or video sequences. It is one of the key tasks in the field of computer vision. With the continuous breakthrough of deep machine learning technology, especially the convolutional neural network model shows strong Ability to extract image feature in the field of digital image processing. Although the model research of target detection based on convolutional neural network is developing rapidly, but there are still some problems in practical applications. For example, a large number of parameters requires high storage and computational costs in detected model. Therefore, this paper optimizes and compresses some algorithms by using early image detection algorithms and image detection algorithms based on convolutional neural networks. After training and learning, there will appear forward propagation mode in the application of CNN network model, providing the model for image feature extraction, integration processing and feature mapping. The use of back propagation makes the CNN network model have the ability to optimize learning and compressed algorithm. Then research discuss the Faster-RCNN algorithm and the YOLO algorithm. Aiming at the problem of the candidate frame is not significant which extracted in the Faster- RCNN algorithm, a target detection model based on the Significant area recommendation network is proposed. The weight of the feature map is calculated by the model, which enhances the saliency of the feature and reduces the background interference. Experiments show that the image detection algorithm based on compressed neural network image has certain feasibility.

scholarly journals Investigation of the wear of asphalt concrete pavement taking into account the influence of temperature, moisture of the pavement and the presence of an aggressive environment

2021 ◽  
Vol 2 (92) ◽  
pp. 68
Author(s):  
Andrii Siedov ◽  
Olena Fomenko
Keyword(s):  
Asphalt Concrete ◽  
High Speed ◽  
Climatic Factors ◽  
Load Capacity ◽  
Weather Conditions ◽  
Road Surface ◽  
Winter Period ◽  
Influence Of Temperature ◽  
The Road ◽  
Industrial Enterprises

Abstract. The emergence of a large number of modern high-speed cars with improved dynamic characteristics and an increase in the share of cars, especially large load capacity, have significantly accelerated the destruction of asphalt roads. Plastic deformations, tracks and cracks are more and more often observed on asphalt concrete pavements of roads, their wear is accelerated. As a result, the transport and operational condition of roads deteriorates, the speed of traffic decreases, the cost of road transport increases, and increasing costs are required for road repairs. Thus, the conditions of traction of the wheels of the car with the road surface are influenced by the service life of the coating, traffic intensity, the amount of harmful emissions of industrial enterprises and climatic factors. At the same time uneven change of conditions of coupling in cross and longitudinal profiles of the highway comes to light. Analyzing the natural and climatic factors, we can establish that different weather conditions have different effects on the condition of the road surface. In summer, the condition of the surface is dry and clean, so the driving conditions are safe. Taking into account all the factors that lead to the destruction of the coating with the formation of residual deformations and irreversible changes, requires the study of wear of the coating surface. he wear of the coating largely depends on the friction force in the area of contact of the tire with the surface of the coating, the type of tires and the pressure in the tires. But the random nature of changes in the intensity and composition of traffic, seasons, temperature, humidity, rainfall affects the amount of wear over a period of operation of the road surface. The presence of water or solutions in the pores of the coating leads to the separation of mineral particles from the layer under the action of impact force from the wheels of vehicles. It is experimentally established that the wear of asphalt concrete in the dry and wet state increases with increasing temperature. One of the main types of damage to road surfaces is their premature wear under the influence of vehicle wheels, in combination with changing weather conditions. Analyzing the natural and climatic factors, we can establish that different weather conditions have different effects on the condition of the road surface. The article considers the influence of temperature, humidity and the presence of solutions of chloride anti-icing materials on the process of abrasion of asphalt pavement in the autumn-winter period. Occurrence of big differences of temperature and humidity accelerates processes of aging of materials from which layers are made, influencing their durability and wear resistance.

scholarly journals An Automatic Detection by Classification of Cracked Pixels or Noncracked Pixels in Road Surface

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Khaddouj Taifi ◽  
Naima Taifi ◽  
Es-said Azougaghe ◽  
Said Safi
Keyword(s):  
Wavelet Transforms ◽  
Crack Detection ◽  
Automatic Detection ◽  
Detection Algorithm ◽  
Essential Elements ◽  
Road Surface ◽  
Discrete Wavelet ◽  
Second Phase ◽  
The Road

Automatic detection and monitoring of the condition of cracks in the road surface are essential elements to ensure road safety and quality of service. A crack detection method based on wavelet transforms (2D-DWT) and Jerman enhancement filter is used. This paper presents different contributions corresponding to the three phases of the proposed system. The first phase presents the contrast enhancement technique to improve the quality of roads surface image. The second phase proposes an effective detection algorithm using discrete wavelet (2D-DWT) with “db8” and two-level sub-band decomposition. Finally, in the third phase, the Jerman enhancement filter is usually used with different parameters of the control response uniformity “ τ ” to enhance for cracks detection. The experimental results in this article provide very powerful results and the comparisons with five existing methods show the effectiveness of the proposed technique to validate the recognition of surface cracks.

Sign in / Sign up

Export Citation Format

Share Document