An automatic assessment of road condition from aerial imagery using modified VGG architecture in faster-RCNN framework

Abstract

To develop a surveillance and detection system for automating the process of road maintenance work which is being carried out by surveying and inspection of roads manually in the current situation. The need of the system lies in the fact that traditional methods are time-consuming, tiresome and require huge workforce. This paper proposes an automation system using Unmanned Aerial Vehicle which monitors and detects the pavement defects like cracks and potholes by processing real-time video footage of Indian highways. The collected data is processed and stored as images in a road defects database which serves as input for the system. The behavior of Region Proposal Network (RPN) is made smooth by varying the number of region proposals utilized in the model. A regularization technique called dropout is used to achieve higher performance in the proposed Faster Region based Convolutional Neural Networks object detection model. The detections are made with 62.3% mean Average Precision @ Intersection over Union (IoU)> = 0.5 for the generation of 300 region proposals which is a good score for object detections. The comparisons between proposed and existing systems shows that the proposed Faster RCNN with modified VGG-16 performs well than the existing variants.

Three-Stage Pavement Crack Localization and Segmentation Algorithm Based on Digital Image Processing and Deep Learning Techniques

“…To further verify the high efficiency of the YOLO-SAMT network architecture proposed in this paper, it is compared with other networks. These networks include the classic single-stage object detection network, the two-stage object detection network, and the advanced networks appearing in the references [ 30 , 31 , 34 , 35 ]. The training data and test data we selected are consistent with the previous section.…”

“…Ju Huyan et al [ 34 ] proposed a new feature fusion network for crack detection in complex backgrounds. In addition, Malini et al [ 35 ] used a series of regularization methods to improve the performance of convolutional neural network models. Cha et al [ 36 ] calculated the defect characteristics of concrete cracks based on machine vision and deep learning network architecture.…”

Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection

“…The single-stage detection algorithm eliminates the region proposal generation steps, so it has certain advantages in speed, but the detection accuracy is relatively low. The other is the two-stage object detection algorithm represented by Region-based Convolutional Neural Network (R-CNN) [3] , the R-CNN method uses the selective search algorithm [4] to generate 1000−2000 region proposals for each image, then extracts features for each region proposal through a convolutional neural network. Then, Support Vector Machine (SVM) classifier or regressor is used for classification or regression.…”

Pavement crack detection based on point cloud data and data fusion

“…Hoang [12] found the crack classification performance of CNN was better than the traditional edge detection algorithms. The newer and more powerful deep learning algorithms are also used for pavement crack segmentation and detection, such as R-CNN (Region-CNN) [22], Fast R-CNN [23], Faster R-CNN [24,25] and Mask R-CNN [26,27]. The YOLO algorithm, the faster and more widely used object detection, is applied to locate cracks in the image which shows a huge potential in pavement inspection [28][29][30].…”