-
Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN
This paper summarizes the design, experiments and results of our solutio...
read it
-
Global Road Damage Detection: State-of-the-art Solutions
This paper summarizes the Global Road Damage Detection Challenge (GRDDC)...
read it
-
Road Damage Detection and Classification with Detectron2 and Faster R-CNN
The road is vital for many aspects of life, and road maintenance is cruc...
read it
-
Deep Learning Frameworks for Pavement Distress Classification: A Comparative Analysis
Automatic detection and classification of pavement distresses is critica...
read it
-
Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone
Research on damage detection of road surfaces using image processing tec...
read it
-
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Neural networks have enabled state-of-the-art approaches to achieve incr...
read it
-
An Efficient and Scalable Deep Learning Approach for Road Damage Detection
Pavement condition evaluation is essential to time the preventative or r...
read it
CNN Model Tuning for Global Road Damage Detection
This paper provides a report on our solution including model selection, tuning strategy and results obtained for Global Road Damage Detection Challenge. This Big Data Cup Challenge was held as a part of IEEE International Conference on Big Data 2020. We assess single and multi-stage network architectures for object detection and provide a benchmark using popular state-of-the-art open-source PyTorch frameworks like Detectron2 and Yolov5. Data preparation for provided Road Damage training dataset, captured using smartphone camera from Czech, India and Japan is discussed. We studied the effect of training on a per country basis with respect to a single generalizable model. We briefly describe the tuning strategy for the experiments conducted on two-stage Faster R-CNN with Deep Residual Network (Resnet) and Feature Pyramid Network (FPN) backbone. Additionally, we compare this to a one-stage Yolov5 model with Cross Stage Partial Network (CSPNet) backbone. We show a mean F1 score of 0.542 on Test2 and 0.536 on Test1 datasets using a multi-stage Faster R-CNN model, with Resnet-50 and Resnet-101 backbones respectively. This shows the generalizability of the Resnet-50 model when compared to its more complex counterparts. Experiments were conducted using Google Colab having K80 and a Linux PC with 1080Ti, NVIDIA consumer grade GPU. A PyTorch based Detectron2 code to preprocess, train, test and submit the Avg F1 score to is made available at https://github.com/vishwakarmarhl/rdd2020
READ FULL TEXT
Comments
There are no comments yet.