Semi‐supervised learning based on convolutional neural network and uncertainty filter for façade defects classification

Guo, Jingjing; Wang, Qian; Li, Yiting

doi:10.1111/mice.12632

Cited by 70 publications

(42 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of novelty detection, novel neural network architectures, such as CNN and RNN, were practised in the literature. For instance, CNNs were operated on both 1D signals (F. Wang et al., 2021), and 2D images (Guo et al., 2021; N. Wang et al., 2020). 2D CNN can also receive sensors’ data in the format of a 2D grid (Sajedi & Liang, 2020, 2021), preserving the spatial distribution of sensors.…”

Section: Methodsmentioning

confidence: 99%

Toward a general unsupervised novelty detection framework in structural health monitoring

Soleimani‐Babakamali

Sepasdar

Nasrollahzadeh

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

This study proposes an unsupervised, online structural health monitoring framework robust to the sensor configuration, that is, the number and placement of sensors. The proposed methodology leverages generative adversarial networks (GANs). The GAN's discriminator network is the novelty detector, while its generator provides additional data to tune the detection threshold. GAN models are trained with the fast Fourier transform of structural accelerations as input, avoiding the need for any structure-specific feature extraction. Dense, convolutional (convolutional neural network), and long short-term memory (LSTM) units are evaluated as discriminators under different GAN training loss patterns, that is, the differences between discriminator and generator training losses. Resultsshow that the LSTM-based discriminators and the suggested threshold tuning technique to be robust even in loss patterns with overfitted discriminators, a probable outcome of limited training sets. The framework is evaluated on two benchmark datasets. With only 100 s of training data, it achieved 95% novelty detection accuracy, distinguishing between different damage classes and identifying their resurgence under varying sensor configurations. Finally, the majorityvote-ensemble of discriminator-generator pairs at different training epochs is introduced to reduce false alarms, improve novelty detection accuracy and stability.

show abstract

Section: Methodsmentioning

confidence: 99%

Toward a general unsupervised novelty detection framework in structural health monitoring

Soleimani‐Babakamali

Sepasdar

Nasrollahzadeh

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…In the last few years, deep learning‐based methods, especially convolutional neural networks (CNNs), have emerged for object detection (Arabi et al, 2020; Reyes & Ventura, 2019; Vera‐Olmos et al, 2019) and other engineering fields (Benito‐Picazo et al, 2020; García‐González et al, 2020; Guo et al, 2021; Lara‐Benıtez et al, 2020; Mishra et al, 2020; Shen et al, 2019; T. Yang et al, 2019), so these methods have motivated object detection on construction sites. Currently, more pedestrian datasets such as the WIDER pedestrian challenge dataset (Loy et al, 2018) and better models for pedestrian detection (Bochkovskiy et al, 2020; Cai & Vasconcelos, 2019) are emerging.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep learning‐based object identification with instance segmentation and pseudo‐LiDAR point cloud for work zone safety

Shen

Yan

Xiong

2021

Computer aided Civil Eng

View full text Add to dashboard Cite

Automated object identification in three‐dimensional (3D) space is crucial for work zone safety, such as compliance with construction rules and preventing workplace injuries and deaths. However, it is greatly challenged by some factors like high‐quality detection, high‐quality instance segmentation, few engineering object datasets with masks, and accurate 3D object understanding due to scale variations and limited cues in the 3D world. Traditional hand‐crafted methods suffer from these challenges. Our key insight is to use 2D object detection, instance segmentation and camera vision to compute pseudo‐light detection and ranging (LiDAR) point cloud for 3D object identification. On the one hand, an enhanced feature pyramid network is proposed to extract more fine‐grained object features, and an improved cascade mask R‐CNN is applied to detect bounding boxes and masks for all 2D objects efficiently. Moreover, the AIM dataset for heavy equipment detection is augmented, and a new object class with the bounding box and mask is added. On the other hand, pseudo‐LiDAR point clouds of objects based on bounding boxes and masks are recovered from a monocular image by deep learning, automatic camera parameter estimation, vision‐based method, and space filter. Extensive experiments and analyses show that the new methodology can identify 3D objects and automatically analyze work zone safety. The proposed object detection model has achieved state‐of‐the‐art results on the AIM dataset and 97.2% in mean average precision for the augmented dataset. The collision detection model using pseudo‐LiDAR point cloud has obtained 95.99% in accuracy. The new model will serve as a baseline to support 3D object identification research for other 3D tasks.

show abstract

“…Deng et al [ 16 ] also opt for a minimal training data approach and employ an atrous spatial pyramid pooling module and include a weight balanced intersection over union (IoU) loss function to mediate the class-imbalance in the training data. A promising work with the same goal is from Guo et al [ 17 ], who describe a semi-supervised method to classify defects on facades. They incorporate an uncertainty filter to select reliable unlabeled data to improve the network’s prediction from limited data.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning on Construction Sites: A Case Study of Sparse Data Learning Techniques for Rebar Segmentation

Cuypers

Bassier

Vergauwen

2021

Sensors

View full text Add to dashboard Cite

With recent advancements in deep learning models for image interpretation, it has finally become possible to automate construction site monitoring processes that rely on remote sensing. However, the major drawback of these models is their dependency on large datasets of training images labeled at pixel level, which have to be produced manually by skilled personnel. To alleviate the need for training data, this study evaluates weakly- and semi-supervised semantic segmentation models for construction site imagery to efficiently automate monitoring tasks. As a case study, we compare fully-, weakly- and semi-supervised methods for the detection of rebar covers, which are useful for quality control. In the experiments, recent models, i.e. IRNet, DeepLabv3+ and the cross-consistency training model, are compared for their ability to segment rebar covers from construction site imagery with minimal manual input. The results show that weakly- and semi-supervised models can indeed approach the performance of fully-supervised models, with the majority of the target objects being properly found. Through this study, construction site stakeholders are provided with detailed information on how tp leverage deep learning for efficient construction site monitoring and weigh preprocessing, training and testing efforts against each other in order to decide between fully-, weakly- and semi-supervised training.

show abstract

Semi‐supervised learning based on convolutional neural network and uncertainty filter for façade defects classification

Cited by 70 publications

References 45 publications

Toward a general unsupervised novelty detection framework in structural health monitoring

Toward a general unsupervised novelty detection framework in structural health monitoring

Deep learning‐based object identification with instance segmentation and pseudo‐LiDAR point cloud for work zone safety

Deep Learning on Construction Sites: A Case Study of Sparse Data Learning Techniques for Rebar Segmentation

Contact Info

Product

Resources

About