# Learning-Based Defect Recognitions for Autonomous UAV Inspections

arXiv: https://arxiv.org/abs/2302.06093 · HTML: https://mlsanity.com/paper/2302.06093/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 7 of 7)

- [FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling](https://mlsanity.com/paper/2012.09439/) (2020)
- [Legacy Photo Editing with Learned Noise Prior](https://mlsanity.com/paper/2011.11309/) (2020)
- [An Integrated LiDAR-SLAM System for Complex Environment with Noisy Point Clouds](https://mlsanity.com/paper/2212.05705/) (2022)
- [Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation](https://mlsanity.com/paper/2211.15066/) (2022)
- [A Light-Weight LiDAR-Inertial SLAM System with Loop Closing](https://mlsanity.com/paper/2212.05743/) (2022)
- [An Enhanced LiDAR-Inertial SLAM System for Robotics Localization and Mapping](https://mlsanity.com/paper/2212.14209/) (2022)
- [A LiDAR-Inertial-Visual SLAM System with Loop Detection](https://mlsanity.com/paper/2301.05604/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors](https://mlsanity.com/paper/2312.01262/) (2023)
- [A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing](https://mlsanity.com/paper/2312.02208/) (2023)

## Abstract (arXiv)

Automatic crack detection and segmentation play a significant role in the whole system of unmanned aerial vehicle inspections. In this paper, we have implemented a deep learning framework for crack detection based on classical network architectures including Alexnet, VGG, and Resnet. Moreover, inspired by the feature pyramid network architecture, a hierarchical convolutional neural network (CNN) deep learning framework which is efficient in crack segmentation is also proposed, and its performance of it is compared with other state-of-the-art network architecture. We have summarized the existing crack detection and segmentation datasets and established the largest existing benchmark dataset on the internet for crack detection and segmentation, which is open-sourced for the research community. Our feature pyramid crack segmentation network is tested on the benchmark dataset and gives satisfactory segmentation results. A framework for automatic unmanned aerial vehicle inspections is also proposed and will be established for the crack inspection tasks of various concrete structures. All our self-established datasets and codes are open-sourced at: https://github.com/KangchengLiu/Crack-Detection-and-Segmentation-Dataset-for-UAV-Inspection