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

Abstract

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.

Enhanced pothole detection system using YOLOX algorithm

“…The mAP@0.50 values of YOLOv5s, YOLOv4tiny, YOLOv4 used in Table 2 were from the results of Park et al [36]. In the same table, the mAP@0.50 value for the YOLOv3 model was reported by Lin et al [33].…”

“…The researchers also improved their pothole detection mechanism by using the YOLOv4 algorithm for various object detection applications. Various pothole detection mechanisms using YOLOv4 [32,35,36] have been proposed. Authors Sung-sick et al [36] used different modules from YOLOv4 and YOLOv5s for pothole detecting applications.…”

“…Various pothole detection mechanisms using YOLOv4 [32,35,36] have been proposed. Authors Sung-sick et al [36] used different modules from YOLOv4 and YOLOv5s for pothole detecting applications. The research concluded that YOLOv4-tiny has higher precision compared to YOLOv5.…”

“…It has been said to be a significant improvement over both the YOLO v3 and v4 in terms of both speed and precision. Several research projects were conducted on YOLOv5 [36,38] to test the precision and accuracy of the algorithm. Ahmed [38] proposed to find a best method to detect potholes by evaluating and comparing different parameters of different image recognition algorithms like YOLOv5, YOLOR [39] and Faster R-CNN with five different backbone structures.…”

Detección de baches y su severidad usando el Video VBOX Lite y teléfonos inteligentes

“…Es así que, en la actualidad, existen tres enfoques principales para su detección: basados en vibración, basados en reconstrucción en 3D y métodos basados en visión (Arjapure & Kalbande, 2020). Dentro de estos enfoques se han empleado varias técnicas: inteligencia artificial (Tithi et al, 2021;Yebes et al, 2021) y su subcampo aprendizaje de máquinas (Egaji et al, 2021;Kandoi et al, 2021;Shah et al, 2021;Yik et al, 2021), redes neuronales (Kempaiah et al, 2022;Rahman et al, 2022) tales como convolucional (Agrawal et al, 2021;Fan, Wang, et al, 2021;Kharel & Ahmed, 2022; S. S. Park et al, 2021;Patra et al, 2021;Pratama et al, 2021;Rahman et al, 2022), aprendizaje profundo (Bhavya et al, 2021;Kempaiah et al, 2022;Li & Liu, 2021;Shah et al, 2021) y visión por computadora (Camilleri & Gatt, 2020;Fan, Wang, et al, 2021;Kharel & Ahmed, 2022;Riedl et al, 2020), utilizando principalmente el procesamiento de imágenes computarizadas (Muhammad Hanif et al, 2020;Tithi et al, 2021;Wang, 2021). También se han utilizado videos (Javed et al, 2021;Tithi et al, 2021), imágenes térmicas (S. Gupta et al, 2020), o imágenes aéreas (Han et al, 2020), imágenes de UAV (Becker1 et al, 2019), tecnología láser (Li & Liu, 2021;Ravi et al, 2020;Srivastava et al, 2020), tecnología LiDAR (J. S.…”