# Hierarchical Convolutional Neural Network with Feature Preservation and Autotuned Thresholding for Crack Detection

arXiv: https://arxiv.org/abs/2104.10511 · HTML: https://mlsanity.com/paper/2104.10511/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Salient Object Detection: A Benchmark](https://mlsanity.com/paper/1501.02741/) (2015)
- [Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection](https://mlsanity.com/paper/1901.06340/) (2019)
- [Mean Absolute Percentage Error for regression models](https://mlsanity.com/paper/1605.02541/) (2016)
- [Towards Bayesian Deep Learning: A Framework and Some Existing Methods](https://mlsanity.com/paper/1608.06884/) (2016)
- [Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding](https://mlsanity.com/paper/1904.08582/) (2019)
- [Semantic Segmentation from Limited Training Data](https://mlsanity.com/paper/1709.07665/) (2017)
- [System Architecture for Real-time Surface Inspection Using Multiple UAVs](https://mlsanity.com/paper/1907.03305/) (2019)
- [Crack Detection Using Enhanced Hierarchical Convolutional Neural Networks](https://mlsanity.com/paper/1912.12139/) (2019)
- [Reconfigurable Multi-UAV Formation Using Angle-Encoded PSO](https://mlsanity.com/paper/1909.03352/) (2019)

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

- [Classification of EEG Motor Imagery Using Deep Learning for Brain-Computer Interface Systems](https://mlsanity.com/paper/2206.07655/) (2022)
- [When Simpler Wins: Facebooks Prophet vs LSTM for Air Pollution Forecasting in Data-Constrained Northern Nigeria](https://mlsanity.com/paper/2508.16244/) (2025)

## Abstract (arXiv)

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure (AFbeta) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of AFbeta while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.