Towards a Camera-Based Road Damage Assessment and Detection for Autonomous Vehicles: Applying Scaled-YOLO and CVAE-WGAN

Fassmeyer, Pascal; Kortmann, Felix; Drews, Paul; Funk, Burkhardt

doi:10.1109/vtc2021-fall52928.2021.9625213

Cited by 7 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers chose to equip a vehicle platform with a standard camera to acquire pavement images from the vehicle's front view. Single-stage target detection algorithms YOLOv4-Tiny [31], Scaled-YOLOv4 [32], and YOLOv5 [30,33,34] were applied in pavement damage detection using road images captured from the front view of the vehicle, and they all achieved high accuracy. In summary, these studies demonstrated the effectiveness of using vehicle-mounted platforms with cameras to acquire road images and the application of deep learning approaches.…”

Section: Object Detection Neural Networkmentioning

confidence: 99%

“…Some closely related YOLO base damage detection models from images are also listed. Because only F1 scores are given in [32,33], Equation ( 5) is used to describe it as the harmonic mean of the precision and recall. The two metrics contribute equally to the score, ensuring that the F1 metric correctly indicates the reliability of a model.…”

Section: Comparison With State-of-the-artmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Road Pavement Inspection by Integrating Visual Information and IMU

Hsieh,

Jia,

Huang

et al. 2024

Information

View full text Add to dashboard Cite

This study proposes a deep learning method for pavement defect detection, focusing on identifying potholes and cracks. A dataset comprising 10,828 images is collected, with 8662 allocated for training, 1083 for validation, and 1083 for testing. Vehicle attitude data are categorized based on three-axis acceleration and attitude change, with 6656 (64%) for training, 1664 (16%) for validation, and 2080 (20%) for testing. The Nvidia Jetson Nano serves as the vehicle-embedded system, transmitting IMU-acquired vehicle data and GoPro-captured images over a 5G network to the server. The server recognizes two damage categories, low-risk and high-risk, storing results in MongoDB. Severe damage triggers immediate alerts to maintenance personnel, while less severe issues are recorded for scheduled maintenance. The method selects YOLOv7 among various object detection models for pavement defect detection, achieving a mAP of 93.3%, a recall rate of 87.8%, a precision of 93.2%, and a processing speed of 30–40 FPS. Bi-LSTM is then chosen for vehicle vibration data processing, yielding 77% mAP, 94.9% recall rate, and 89.8% precision. Integration of the visual and vibration results, along with vehicle speed and travel distance, results in a final recall rate of 90.2% and precision of 83.7% after field testing.

show abstract

Section: Object Detection Neural Networkmentioning

confidence: 99%

Section: Comparison With State-of-the-artmentioning

confidence: 99%

Deep Learning-Based Road Pavement Inspection by Integrating Visual Information and IMU

Hsieh,

Jia,

Huang

et al. 2024

Information

View full text Add to dashboard Cite

show abstract

“…In terms of pavement disease detection, a YOLOX-based pavement disease detection method was proposed in Reference [ 35 ], which effectively solves the problem of slow identification by traditional methods. To improve the comfort of driverless vehicles, a pavement disease detection system based on the Scaled-YOLOv4 detection framework was proposed in Reference [ 36 ], and the recognition results can be used in the subsequent engineering related to vehicle control. In terms of improving accuracy, a self-supervised learning network based on “SSL YOLOv4” was proposed to solve the problem of manual labeling of data while ensuring the recognition accuracy in Reference [ 37 ].…”

Section: Introductionmentioning

confidence: 99%

Real-Time Target Detection System for Intelligent Vehicles Based on Multi-Source Data Fusion

Zou

Zheng

Wang

2023

Sensors

View full text Add to dashboard Cite

To improve the identification accuracy of target detection for intelligent vehicles, a real-time target detection system based on the multi-source fusion method is proposed. Based on the ROS melodic software development environment and the NVIDIA Xavier hardware development platform, this system integrates sensing devices such as millimeter-wave radar and camera, and it can realize functions such as real-time target detection and tracking. At first, the image data can be processed by the You Only Look Once v5 network, which can increase the speed and accuracy of identification; secondly, the millimeter-wave radar data are processed to provide a more accurate distance and velocity of the targets. Meanwhile, in order to improve the accuracy of the system, the sensor fusion method is used. The radar point cloud is projected onto the image, then through space-time synchronization, region of interest (ROI) identification, and data association, the target-tracking information is presented. At last, field tests of the system are conducted, the results of which indicate that the system has a more accurate recognition effect and scene adaptation ability in complex scenes.

show abstract

Use of Camera and AI for Mapping Monitoring for Architecture

Falcone

Dell’Annunziata

2023

Nexus Netw J

View full text Add to dashboard Cite

show abstract

Towards a Camera-Based Road Damage Assessment and Detection for Autonomous Vehicles: Applying Scaled-YOLO and CVAE-WGAN

Cited by 7 publications

References 20 publications

Deep Learning-Based Road Pavement Inspection by Integrating Visual Information and IMU

Deep Learning-Based Road Pavement Inspection by Integrating Visual Information and IMU

Real-Time Target Detection System for Intelligent Vehicles Based on Multi-Source Data Fusion

Use of Camera and AI for Mapping Monitoring for Architecture

Contact Info

Product

Resources

About