scholarly journals Application of Various YOLO Models for Computer Vision-Based Real-Time Pothole Detection

2021 ◽  
Vol 11 (23) ◽  
pp. 11229
Author(s):  
Sung-Sik Park ◽  
Van-Than Tran ◽  
Dong-Eun Lee
Keyword(s):  
Computer Vision ◽  
Real Time ◽  
Road Surface ◽  
Detection Accuracy ◽  
Road Maintenance ◽  
Art Object ◽  
Inspection Process ◽  
Image Set ◽  
Road Surface Monitoring ◽  
Pothole Detection

Pothole repair is one of the paramount tasks in road maintenance. Effective road surface monitoring is an ongoing challenge to the management agency. The current pothole detection, which is conducted image processing with a manual operation, is labour-intensive and time-consuming. Computer vision offers a mean to automate its visual inspection process using digital imaging, hence, identifying potholes from a series of images. The goal of this study is to apply different YOLO models for pothole detection. Three state-of-the-art object detection frameworks (i.e., YOLOv4, YOLOv4-tiny, and YOLOv5s) are experimented to measure their performance involved in real-time responsiveness and detection accuracy using the image set. The image set is identified by running the deep convolutional neural network (CNN) on several deep learning pothole detectors. After collecting a set of 665 images in 720 × 720 pixels resolution that captures various types of potholes on different road surface conditions, the set is divided into training, testing, and validation subsets. A mean average precision at 50% Intersection-over-Union threshold (mAP_0.5) is used to measure the performance of models. The study result shows that the mAP_0.5 of YOLOv4, YOLOv4-tiny, and YOLOv5s are 77.7%, 78.7%, and 74.8%, respectively. It confirms that the YOLOv4-tiny is the best fit model for pothole detection.

scholarly journals Road Surface Monitoring Using Smartphone Sensors: A Review

2021 ◽  
Author(s):  
Shahram Sattar ◽  
Songnian Li ◽  
Michael A. Chapman
Keyword(s):  
Anomaly Detection ◽  
Surface Condition ◽  
Low Frequency ◽  
Road Surface ◽  
Detection Accuracy ◽  
Road Maintenance ◽  
Key Factor ◽  
Smartphone Sensors ◽  
Road Surface Monitoring ◽  
Surface Monitoring

Road surface monitoring is a key factor to providing smooth and safe road infrastructure to road users. The key to road surface condition monitoring is to detect road surface anomalies, such as potholes, cracks, and bumps, which affect driving comfort and on-road safety. Road surface anomaly detection is a widely studied problem. Recently, smartphone-based sensing has become increasingly popular with the increased amount of available embedded smartphone sensors. Using smartphones to detect road surface anomalies could change the way government agencies monitor and plan for road maintenance. However, current smartphone sensors operate at a low frequency, and undersampled sensor signals cause low detection accuracy. In this study, current approaches for using smartphones for road surface anomaly detection are reviewed and compared. In addition, further opportunities for research using smartphones in road surface anomaly detection are highlighted.

scholarly journals AN EFFICIENT METHOD TO AUTOMATE POTHOLE DETECTION IN ROAD SURFACE USING IOT

2021 ◽  
Vol 5 (10) ◽  
Author(s):  
Ajith Kumar B ◽  
Vignesh G ◽  
Anbumani A.
Keyword(s):  
Image Processing ◽  
Digital Image Processing ◽  
Digital Image ◽  
Road Surface ◽  
Detection Accuracy ◽  
Road Maintenance ◽  
Application System ◽  
Image Processing Techniques ◽  
Processing Techniques ◽  
Pothole Detection

With the development of information technology, the digital image processing has the characteristics of strong permeability, large use of action and good comprehensive benefits. A road maintenance pothole detection is one of the important tasks. A road surface modelling or road image analysis is generally come from computer vision approaches. However, these two categories were always used independently. Furthermore, the accuracy of the pothole detection is not satisfactory. These challenges promote the development of a better application to detect potholes, cracks using the digital image processing like segmentation, extraction, recognition, and morphology from the images of road surface by using image processing. We are proposing an application system with efficient digital image processing techniques to improve the accuracy and consistency of obtaining accurate shapes of potholes and topologies, etc. The successful detection accuracy is around 98.7% and the overall pixel-level accuracy is approximately 99.6%. By using the digital image processing techniques, the detected potholes and cracks are updated to the web server by using IOT device.

scholarly journals Road Surface Monitoring Using Smartphone Sensors: A Review

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3845 ◽  
Author(s):  
Shahram Sattar ◽  
Songnian Li ◽  
Michael Chapman
Keyword(s):  
Anomaly Detection ◽  
Surface Condition ◽  
Low Frequency ◽  
Road Surface ◽  
Detection Accuracy ◽  
Road Maintenance ◽  
Key Factor ◽  
Smartphone Sensors ◽  
Road Surface Monitoring ◽  
Surface Monitoring

Road surface monitoring is a key factor to providing smooth and safe road infrastructure to road users. The key to road surface condition monitoring is to detect road surface anomalies, such as potholes, cracks, and bumps, which affect driving comfort and on-road safety. Road surface anomaly detection is a widely studied problem. Recently, smartphone-based sensing has become increasingly popular with the increased amount of available embedded smartphone sensors. Using smartphones to detect road surface anomalies could change the way government agencies monitor and plan for road maintenance. However, current smartphone sensors operate at a low frequency, and undersampled sensor signals cause low detection accuracy. In this study, current approaches for using smartphones for road surface anomaly detection are reviewed and compared. In addition, further opportunities for research using smartphones in road surface anomaly detection are highlighted.

scholarly journals Road Surface Monitoring Using Smartphone Sensors: A Review

2021 ◽  
Author(s):  
Shahram Sattar ◽  
Songnian Li ◽  
Michael A. Chapman
Keyword(s):  
Anomaly Detection ◽  
Surface Condition ◽  
Low Frequency ◽  
Road Surface ◽  
Detection Accuracy ◽  
Road Maintenance ◽  
Key Factor ◽  
Smartphone Sensors ◽  
Road Surface Monitoring ◽  
Surface Monitoring

Road surface monitoring is a key factor to providing smooth and safe road infrastructure to road users. The key to road surface condition monitoring is to detect road surface anomalies, such as potholes, cracks, and bumps, which affect driving comfort and on-road safety. Road surface anomaly detection is a widely studied problem. Recently, smartphone-based sensing has become increasingly popular with the increased amount of available embedded smartphone sensors. Using smartphones to detect road surface anomalies could change the way government agencies monitor and plan for road maintenance. However, current smartphone sensors operate at a low frequency, and undersampled sensor signals cause low detection accuracy. In this study, current approaches for using smartphones for road surface anomaly detection are reviewed and compared. In addition, further opportunities for research using smartphones in road surface anomaly detection are highlighted.

scholarly journals A Crowdsourcing Technique For Road Surface Monitoring Using Smarthphone Sensors

2021 ◽  
Author(s):  
Shahram Sattar
Keyword(s):  
Information System ◽  
Surface Condition ◽  
Road Surface ◽  
Detection Accuracy ◽  
Active Monitoring ◽  
The Road ◽  
Detection Approach ◽  
Smartphone Sensors ◽  
Road Surface Monitoring ◽  
Surface Monitoring

Road surface monitoring is a key factor in providing safe road infrastructure for road users. As a result, road surface condition monitoring aims to detect road surface anomalies such potholes, cracks and bumps, which affect driving comfort and on-road safety. Road surface anomaly detection is a widely studied problem. Recently, smartphone-based sensing has become popular with the increased amount of available embedded smartphone sensors. Using smartphones to detect road surface anomalies could change the way government agencies monitor and plan for road rehabilitation and maintenance. Several studies have been developed to utilize smartphone sensors (e.g., Global Positioning system (GPS) and accelerometers) mounted on a moving vehicle to collect and process the data to monitor and tag roadway surface defects. Geotagged images or videos from the roadways have also been used to detect the road surface anomalies. However, existing studies are limited to identifying roadway anomalies mainly from a single source or lack the utility of combined and integrated multi-sensors in terms of accuracy and functionality. Therefore, low-cost, more efficient pavement evaluation technologies and a centralized information system are necessary to provide the most up-to-date information about the road status due to the dynamic changes on the road surface This information will assist transportation authorities to monitor and enhance the road surface condition. In this research, a probabilistic-based crowdsourcing technique is developed to detect road surface anomalies from smartphone sensors such as linear accelerometers, gyroscopes and GPS to integrate multiple detections accurately. All case studies from the proposed detection approach showed an approximate 80% detection accuracy (from a single survey) which supports the inclusiveness of the detection approach. In addition, the results of the proposed probabilistic-based integration approach indicated that the detection accuracy can be further improved by 5 to 20% with multiple detections conducted by the same vehicle along the same road segments. Finally, the development of the web-based Geographic Information System (GIS) platform would facilitate the real-time and active monitoring of road surface anomalies and offer further improvement of road surface quality control in large cities like Toronto.

scholarly journals Real-Time Small Drones Detection Based on Pruned YOLOv4

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3374
Author(s):  
Hansen Liu ◽  
Kuangang Fan ◽  
Qinghua Ouyang ◽  
Na Li
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Processing Speed ◽  
State Of The Art ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Small Object ◽  
Art Object ◽  
Real Time Detection ◽  
Small Object Detection

To address the threat of drones intruding into high-security areas, the real-time detection of drones is urgently required to protect these areas. There are two main difficulties in real-time detection of drones. One of them is that the drones move quickly, which leads to requiring faster detectors. Another problem is that small drones are difficult to detect. In this paper, firstly, we achieve high detection accuracy by evaluating three state-of-the-art object detection methods: RetinaNet, FCOS, YOLOv3 and YOLOv4. Then, to address the first problem, we prune the convolutional channel and shortcut layer of YOLOv4 to develop thinner and shallower models. Furthermore, to improve the accuracy of small drone detection, we implement a special augmentation for small object detection by copying and pasting small drones. Experimental results verify that compared to YOLOv4, our pruned-YOLOv4 model, with 0.8 channel prune rate and 24 layers prune, achieves 90.5% mAP and its processing speed is increased by 60.4%. Additionally, after small object augmentation, the precision and recall of the pruned-YOLOv4 almost increases by 22.8% and 12.7%, respectively. Experiment results verify that our pruned-YOLOv4 is an effective and accurate approach for drone detection.

scholarly journals Smart Pothole Detection Using Deep Learning Based on Dilated Convolution

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8406
Author(s):  
Khaled R. Ahmed
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Computational Cost ◽  
Detection Accuracy ◽  
Setup Cost ◽  
Detection Algorithms ◽  
Dilated Convolution ◽  
Wide Range ◽  
Adequate Accuracy ◽  
Pothole Detection

Roads make a huge contribution to the economy and act as a platform for transportation. Potholes in roads are one of the major concerns in transportation infrastructure. A lot of research has proposed using computer vision techniques to automate pothole detection that include a wide range of image processing and object detection algorithms. There is a need to automate the pothole detection process with adequate accuracy and speed and implement the process easily and with low setup cost. In this paper, we have developed efficient deep learning convolution neural networks (CNNs) to detect potholes in real-time with adequate accuracy. To reduce the computational cost and improve the training results, this paper proposes a modified VGG16 (MVGG16) network by removing some convolution layers and using different dilation rates. Moreover, this paper uses the MVGG16 as a backbone network for the Faster R-CNN. In addition, this work compares the performance of YOLOv5 (Large (Yl), Medium (Ym), and Small (Ys)) models with ResNet101 backbone and Faster R-CNN with ResNet50(FPN), VGG16, MobileNetV2, InceptionV3, and MVGG16 backbones. The experimental results show that the Ys model is more applicable for real-time pothole detection because of its speed. In addition, using the MVGG16 network as the backbone of the Faster R-CNN provides better mean precision and shorter inference time than using VGG16, InceptionV3, or MobilNetV2 backbones. The proposed MVGG16 succeeds in balancing the pothole detection accuracy and speed.

Detecting Potholes in Asphalt Pavement under Small-sample Conditions Based on Improved Faster Region-based Convolution Neural Networks

2021 ◽  
Author(s):  
Lili Pei ◽  
Li Shi ◽  
Zhaoyun Sun ◽  
Wei Li ◽  
Yao Gao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Asphalt Pavement ◽  
Small Sample ◽  
Small Samples ◽  
Detection Accuracy ◽  
Fusion Model ◽  
Convolution Neural Networks ◽  
Image Set ◽  
Pothole Detection ◽  
Different Sources

Pavement potholes have low detection accuracy under the condition of small samples. To address this issue, we propose a method for efficient and accurate pothole detection under small-sample conditions, based on improved Faster R-CNN (Region-based Convolution Neural Networks). First, images consisting of different pothole shapes and sizes are acquired from different sources and then, augmented and denoised to obtain the image set. Second, two representative target detection models, Faster R-CNN and YOLOv3, are tested. The detection results indicate that Faster R-CNN achieves better detection performance. Furthermore, to overcome inconsistencies (missed detections and inaccurate position estimations), the feature extraction layers of VGG16, ZFNet, and ResNet50 networks are used in combination with Faster R-CNN. The results show that the VGG16+Faster R-CNN fusion model yields superior accuracy. Finally, the detection accuracy improved to 0.8997 after adjusting the size of the candidate frame, which also enabled the successful detection of previously missed targets.

Sign in / Sign up

Export Citation Format

Share Document