A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos

TL;DR

This paper presents a semi-supervised self-training approach using transfer learning and temporal coherence analysis to efficiently develop a deep learning model for multiclass bridge element segmentation from inspection videos, requiring minimal labeled data.

Contribution

It introduces a novel semi-supervised self-training method that incorporates domain expertise and temporal analysis to improve bridge element segmentation with limited labeled data.

Findings

Achieved over 92% F1-score with only 66 labeled images.

Demonstrated efficient model training requiring approximately 3.58 hours of labeling.

Effectively integrated domain knowledge into deep learning for infrastructure inspection.

Abstract

Bridge inspection is an important step in preserving and rehabilitating transportation infrastructure for extending their service lives. The advancement of mobile robotic technology allows the rapid collection of a large amount of inspection video data. However, the data are mainly images of complex scenes, wherein a bridge of various structural elements mix with a cluttered background. Assisting bridge inspectors in extracting structural elements of bridges from the big complex video data, and sorting them out by classes, will prepare inspectors for the element-wise inspection to determine the condition of bridges. This paper is motivated to develop an assistive intelligence model for segmenting multiclass bridge elements from inspection videos captured by an aerial inspection platform. With a small initial training dataset labeled by inspectors, a Mask Region-based Convolutional Neural Network (Mask R-CNN) pre-trained on a large public dataset was transferred to the new task of multiclass bridge element segmentation. Besides, the temporal coherence analysis attempts to recover false negatives and identify the weakness that the neural network can learn to improve. Furthermore, a semi-supervised self-training (S$^3$T) method was developed to engage experienced inspectors in refining the network iteratively. Quantitative and qualitative results from evaluating the developed deep neural network demonstrate that the proposed method can utilize a small amount of time and guidance from experienced inspectors (3.58 hours for labeling 66 images) to build the network of excellent performance (91.8% precision, 93.6% recall, and 92.7% f1-score). Importantly, the paper illustrates an approach to leveraging the domain knowledge and experiences of bridge professionals into computational intelligence models to efficiently adapt the models to varied bridges in the National Bridge Inventory.