CNN Model & Tuning for Global Road Damage Detection

  title={CNN Model \& Tuning for Global Road Damage Detection},
  author={Rahul Vishwakarma and Ravigopal Vennelakanti},
  journal={2020 IEEE International Conference on Big Data (Big Data)},
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… 

A New Road Damage Detection Baseline with Attention Learning

A novel baseline with attention fusion and normalization is proposed to evaluate and analyze the published dataset, which significantly outperforms most existing methods on the existing RDD2020 dataset and the newly released CNRDD dataset.

Real-Time Deep Learning based Road Deterioration Detection for Smart Cities

This paper utilizes convolutional neural network-based and vision transformer-based object detection models to accurately identify road deteriorations namely, potholes, cracks, and alligators, and presents a new comprehensive and balanced large-scale road condition dataset of 27,298 annotated images, captured by ordinary car cameras.

Automatic Defect Detection of Pavement Diseases

The deep convolution neural network—DASNet is created, which can be used to identify road diseases automatically and is compared to the latest method in order to prove the superiority and effectiveness of this method.

Road damage detection algorithm for improved YOLOv5

The improved YOLOv5 model proposed in this paper can effectively identify pavement cracks and can provide a reference for the automatic detection method of pavement cracks.

Human behavior in image-based Road Health Inspection Systems despite the emerging AutoML

The overall purpose of this case study is to investigate the gap between current AutoML frameworks and practical machine learning development, and confirms the increasing trend of AutoML via an indirect indicator of the numbers of search results in Google trend, IEEE Xplore, and ACM Digital Library during 2012–2021.



Global Road Damage Detection: State-of-the-art Solutions

The top 12 solutions proposed by the Global Road Damage Detection Challenge are summarized, with the best performing model utilizes YOLO-based ensemble learning to yield an F1 score of 0.67 on test1 and 0.66 on test2.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

Feature Pyramid Networks for Object Detection

This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.

CSPNet: A New Backbone that can Enhance Learning Capability of CNN

The proposed CSPNet respects the variability of the gradients by integrating feature maps from the beginning and the end of a network stage, which reduces computations by 20% with equivalent or even superior accuracy on the ImageNet dataset, and significantly outperforms state-of-the-art approaches in terms of AP50 on the MS COCO object detection dataset.

Transfer Learning-based Road Damage Detection for Multiple Countries

An assessment of the usability of the Japanese model for other countries is assessed and a large-scale heterogeneous road damage dataset comprising 26620 images collected from multiple countries using smartphones is proposed.

Aggregated Residual Transformations for Deep Neural Networks

On the ImageNet-1K dataset, it is empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy and is more effective than going deeper or wider when the authors increase the capacity.

SSD: Single Shot MultiBox Detector

The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.

Focal Loss for Dense Object Detection

This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Deep Learning for Generic Object Detection: A Survey

A comprehensive survey of the recent achievements in this field brought about by deep learning techniques, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics.