Detection and localization of potholes in thermal images using deep neural networks

Abstract

A pothole is a depression caused on roads due to seepage of water into soil structure or weight of continuously moving traffic. This not only damages the suspension of the vehicles but is also a prime reason for road accidents worldwide. This necessitates the need to develop an efficient automatic pothole detection system which can assist concerned authorities for timely repair and maintenance of the roads. This paper proposes a novel approach of bounding box based pothole localization from thermal images using deep neural networks. The modified ResNet34-single shot multibox detector gives an average precision of 74.53% whereas modified ResNet50-RetinaNet model provides 91.15% precision. The results obtained by the proposed modified ResNet50-RetinaNet model are the state-of-the-art results for localization of potholes using thermal images. In real-world scenarios such a system can assist relevant authorities to judge the severity of road damage and take appropriate effective measures accordingly.

Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms

“…Researchers in this field have mainly incorporated different image classification networks into the SSD for road pothole detection. For example, Inception-v2 [85] and MobileNet [82] were used as the backbone networks in [86], while ResNet-34 [78] and RetinaNet [87] were used as the backbone networks in [88].…”

“…and ResNet-101 as the backbone networks, separately) and one SSD (with MobileNet-v2 as the backbone network) are trained to detect road potholes. Faster R-CNN (with ResNet-101 as the backbone network) achieves the best performance.Gupta et al[88] (2020)Thermal image SSD Two SSDs (with ResNet-34 and ResNet-50 as the backbone networks, separately) are trained to detect potholes in thermal road images. The latter significantly outperforms the former.Javed et al[95] …”

Novel deep learning model for vehicle and pothole detection

“…The model uses this inception module to develop the GoogLeNet neural network architecture. There are nine such inception modules in the GoogLeNet neural network architecture [22], [23]. Also, it introduces the inception v2 architecture to improve computational speed, as shown in Figure 3.…”

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

“…Uno de estos deterioros son los baches que se producen en pavimento flexible, los cuales pueden afectar el confort en la conducción, seguridad vial y las condiciones del vehículo (Fan, Ozgunalp et al, 2021). Una de las tareas más críticas en las redes viales es el monitorear la carretera para detectar este tipo de anomalías (S. Gupta et al, 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. Park et al, 2019;Ravi et al, 2020), análisis de agrupamiento (Fan, Ozgunalp,...…”