scholarly journals Road Surface Damage Detection Using Fully Convolutional Neural Networks and Semi-Supervised Learning

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5501 ◽  
Author(s):  
Chanjun Chun ◽  
Seung-Ki Ryu
Keyword(s):  
Neural Networks ◽  
Damage Detection ◽  
Supervised Learning ◽  
Convolutional Neural Networks ◽  
Surface Damage ◽  
Road Surface ◽  
Training Dataset ◽  
The Road ◽  
Fully Convolutional Neural Networks ◽  
On The Road

The various defects that occur on asphalt pavement are a direct cause car accidents, and countermeasures are required because they cause significantly dangerous situations. In this paper, we propose fully convolutional neural networks (CNN)-based road surface damage detection with semi-supervised learning. First, the training DB is collected through the camera installed in the vehicle while driving on the road. Moreover, the CNN model is trained in the form of a semantic segmentation using the deep convolutional autoencoder. Here, we augmented the training dataset depending on brightness, and finally generated a total of 40,536 training images. Furthermore, the CNN model is updated by using the pseudo-labeled images from the semi-supervised learning methods for improving the performance of road surface damage detection technique. To demonstrate the effectiveness of the proposed method, 450 evaluation datasets were created to verify the performance of the proposed road surface damage detection, and four experts evaluated each image. As a result, it is confirmed that the proposed method can properly segment the road surface damages.

Multi-Focus Image Fusion Algorithm Based on Supervised Learning for Fully Convolutional Neural Networks

2020 ◽  
Vol 57 (8) ◽  
pp. 081015
Author(s):  
李恒 Li Heng ◽  
张黎明 Zhang Liming ◽  
蒋美容 Jiang Meirong ◽  
李玉龙 Li Yulong
Keyword(s):  
Neural Networks ◽  
Image Fusion ◽  
Supervised Learning ◽  
Convolutional Neural Networks ◽  
Fusion Algorithm ◽  
Fully Convolutional Neural Networks ◽  
Focus Image

scholarly journals The Comparison of Prediction Model of Lowering Rate Road Surface Damage Between RCI and SDI Method in Lumajang Regency

2021 ◽  
Vol 9 (1) ◽  
pp. 19
Author(s):  
Yulianata Halim Afandi ◽  
Dewi Junita Koesoemawati ◽  
Akhmad Hasanuddin
Keyword(s):  
Building Materials ◽  
Good Condition ◽  
Surface Damage ◽  
Road Surface ◽  
Traffic Load ◽  
Survey Method ◽  
The Road ◽  
Mineral Commodity ◽  
Survey Results ◽  
On The Road

Sand mining was a non-metal mineral commodity which had very good quantity and quality for building materials in Lumajang district. It was found in lava routes or large rivers in the Pasirian sub-district at Lumajang district. The location of sand material was in a river that passes through the regency road. This result was in many road damage in the district area. The efforts to overcome the damage that often occurs on roads in Pasirian sub-district included road improvement activities supported by road surface surveys using the RCI method which has been used in reporting basic road conditions. This study aim conducted of comparing the RCI survey method and predicting a decline in the last 3 (three) years to 2021 with the SDI survey method in 2021. The value being compared was in good condition from the overall report. After predicting the reduction in road damage with the regression method from the survey results of road conditions in 2017 - 2020 with the RCI method, the equation Y = -11,807 x 2021 + 23868 has a prediction of a decrease of 6,053%. After carrying out a survey of road conditions used the SDI method in 2021 on district roads in the Pasirian sub-district. There was an 8% decrease in good conditions. On the road in the Pasirian regency area, the decrease in the condition of the road surface was due to one of the factors being the excessive traffic load (over loaded) which causes a steady condition of the sections around the sand mine in the Pasirian sub-district.

scholarly journals Comparison of Semantic Convolution Neural Networks on the Example of Crack Segmentation in Asphalt Images

2021 ◽  
pp. 415-423
Author(s):  
Svetlana Mustafina ◽  
Andrey Akimov ◽  
Sofia Mustafina ◽  
Alexandra Plotnikova
Keyword(s):  
Neural Networks ◽  
Comparative Analysis ◽  
Semantic Segmentation ◽  
Surface Damage ◽  
High Accuracy ◽  
Road Surface ◽  
Training Data ◽  
The Road ◽  
Convolutional Networks ◽  
Technical Vision

The article is devoted to a comparative analysis of the effectiveness of convolutional neural networks for semantic segmentation of road surface damage marking. Currently, photo and video surveillance methods are used to control the condition of the road surface. Assessing and analyzing new manual data can take too long. Thus, a completely different procedure is required to inspect and assess the state of controlled objects using technical vision. The authors compared 3 neural networks (Unet, Linknet, PSPNet) used in semantic segmentation using the example of the Crack500 dataset. The proposed architectures have been implemented in the Keras and TensorFlow frameworks. The compared models of neural convolutional networks effectively solve the assigned tasks even with a limited amount of training data. High accuracy is observed. The considered models can be used in various segmentation tasks. The results obtained can be used in the process of modeling, monitoring, and predicting the wear of the road surface.

scholarly journals Road Pothole Detection using Deep Learning Classifiers

2020 ◽  
Vol 8 (6) ◽  
pp. 563-570 ◽  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Data Collection ◽  
Convolutional Neural Networks ◽  
Road Maintenance ◽  
The Road ◽  
Wear And Tear ◽  
On The Road ◽  
Maintenance Process ◽  
Pothole Detection

Pothole is one of the major types of defects frequently found on the road whose assessment is necessary to process. It is one of the important reason of accidents on the road along with the wear and tear of vehicles. Road defects assessment is to be done through defects data collection and processing of this collected data. Currently, using various types of imaging systems data collection is near about becomes automated but an assessment of defects from collected data is still manual. Manual classification and evaluation of potholes are expensive, labour-intensive, time-consuming and thus slows down the overall road maintenance process. This paper describe a method for classification and detection of the potholes on road images using convolutional neural networks which are deep learning algorithms. In the proposed system we used convolutional neural networks based approach with pre-trained models to classify given input images into a pothole and non-pothole categories. The method was implemented in python using OpenCV library under windows and colab environment, trained on 722 and tested on 116 raw images. The results are evaluated and compared for convolutional neural networks and various seven pre-trained models through accuracy, precision and recall metrics. The results show that pre-trained models InseptionResNetV2 and DenseNet201 can detect potholes on road images with reasonably good accuracy of 89.66%.

scholarly journals Interpretation of Swedish Sign Language Using Convolutional Neural Networks and Transfer Learning

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Gustaf Halvardsson ◽  
Johanna Peterson ◽  
César Soto-Valero ◽  
Benoit Baudry
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Web Application ◽  
Training Dataset ◽  
Motion Processing ◽  
Image Perception ◽  
Sign Languages ◽  
High Level

AbstractThe automatic interpretation of sign languages is a challenging task, as it requires the usage of high-level vision and high-level motion processing systems for providing accurate image perception. In this paper, we use Convolutional Neural Networks (CNNs) and transfer learning to make computers able to interpret signs of the Swedish Sign Language (SSL) hand alphabet. Our model consists of the implementation of a pre-trained InceptionV3 network, and the usage of the mini-batch gradient descent optimization algorithm. We rely on transfer learning during the pre-training of the model and its data. The final accuracy of the model, based on 8 study subjects and 9400 images, is 85%. Our results indicate that the usage of CNNs is a promising approach to interpret sign languages, and transfer learning can be used to achieve high testing accuracy despite using a small training dataset. Furthermore, we describe the implementation details of our model to interpret signs as a user-friendly web application.

Sign in / Sign up

Export Citation Format

Share Document