• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.1
• /
• pp.64-75
• /
• 2003

Medical image segmentation is the process by which an original image is partitioned into some homogeneous regions like bones, soft tissues, etc. This study demonstrates an automatic medical image segmentation technique based on independent component analysis. Independent component analysis is a generalization of principal component analysis which encodes the higher-order dependencies in the input in addition to the correlations. It extracts statistically independent components from input data. Use of automatic medical image segmentation technique using independent component analysis under the assumption that medical image consists of some statistically independent parts leads to a method that allows for more accurate segmentation of bones from CT data. The result of automatic segmentation using independent component analysis with square test data was evaluated using probability of error(PE) and ultimate measurement accuracy(UMA) value. It was also compared to a general segmentation method using threshold based on sensitivity(True Positive Rate), specificity(False Positive Rate) and mislabelling rate. The evaluation result was done statistical Paired-t test. Most of the results show that the automatic segmentation using independent component analysis has better result than general segmentation using threshold.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.39-48
• /
• 2005

This paper proposes novel texture segmentation method using Bayesian estimation method and neural networks. We use multi-scale wavelet coefficients and the context information of neighboring wavelets coefficients as the input of networks. The output of neural networks is modeled as a posterior probability. The context information is obtained by HMT(Hidden Markov Tree) model. This proposed segmentation method shows better performance than ML(Maximum Likelihood) segmentation using HMT model. And post-processed texture segmentation results as using multi-scale Bayesian image segmentation technique called HMTseg in each segmentation by HMT and the proposed method also show that the proposed method is superior to the method using HMT.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.4
• /
• pp.1426-1436
• /
• 2014

In this article, we present a new grey scale image segmentation method based on Fuzzy logic and bitplane techniques which combines the bits of different bitplanes of a pixel inorder to increase the segmentation quality and to get a more reliable and accurate segmentation result. The proposed segmentation approach is conceptually different and explores a new strategy. Infact, our technique consists in combining many realizations of the image together inorder to increase the information quality and to get an optimal segmented image. For segmentation, we proceed in two steps. In the first step, we begin by identifying the bitplanes that represent the lungs clearly. For this purpose, the intensity value of a pixel is separated into bitplanes. In the second step, segmentation values are assigned for each bitplane based on membership table. The segmented values of foreground are combined and the segmentation values of background are combined. The algorithm is demonstrated through the medical computed tomography (CT) images. The segmentation accuracy of the proposed method is compared with two existing techniques. Satisfactory segmentation results have been obtained showing the effectiveness and superiority of the proposed method.

• Computers and Concrete
• /
• v.21 no.6
• /
• pp.727-739
• /
• 2018

Crack is the most common typical feature of concrete deterioration, so routine monitoring and health assessment become essential for identifying failures and to set up an appropriate rehabilitation strategy in order to extend the service life of concrete structures. At present, image segmentation algorithms have been applied to crack analysis based on inspection images of concrete structures. The results of crack segmentation offering crack information, including length, width, and area is helpful to assist inspectors in surface inspection of concrete structures. This study proposed an algorithm of image segmentation enhancement, named morphological segmentation based on edge detection-II (MSED-II), to concrete crack segmentation. Several concrete pavement and building surfaces were imaged as the study materials. In addition, morphological operations followed by cross-curvature evaluation (CCE), an image segmentation technique of linear patterns, were also tested to evaluate their performance in concrete crack segmentation. The result indicates that MSED-II compared to CCE can lead to better quality of concrete crack segmentation. The least area, length, and width measurement errors of the concrete cracks are 5.68%, 0.23%, and 0.00%, respectively, that proves MSED-II effective for automatic measurement of concrete cracks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.2
• /
• pp.81-87
• /
• 2013

Motion segmentation is a fundamental technique for analysing image sequences of real scenes. A process of identifying moving objects from data is a typical task in many computer vision applications. In this paper, we propose motion segmentation that generally consists from background subtraction and foreground pixel segmentation. The Approximated Median Filter (AMF) was chosen to perform background modeling. Motion segmentation in this paper covers RGB video data.

• Proceedings of the KIEE Conference
• /
• 1987.11a
• /
• pp.338-340
• /
• 1987

The speech recognition system usually consists of two modules, segmentation module and identification module. So, the performance of the system heavily depends on the segmentation accuracy and the segmentation unit. This paper is concerned with the agreeable features for segmentation in syllables. Total energy and two band width energy. (LE:4000-5000Hz and HE:900-3100Hz) are suitable cues for segmentation. And we testify it through the experiment using connected digit.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.1
• /
• pp.61-67
• /
• 2014

Motion segmentation is a fundamental technique for analysing image sequences of real scenes. A process of identifying moving objects from data is a typical task in many computer vision applications. In this paper, we propose motion segmentation that generally consists from background subtraction and foreground pixel segmentation. The Approximated Median Filter(AMF) was chosen to perform background modeling. Motion segmentation in this paper covers RGB video data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.37-39
• /
• 2021

본 논문에서는 간단한 아두이노 모듈을 이용하여 MATLAB에서 실행되는 semantic segmentation을 조작해보았다. 기존에는 단순히 센서를 통해 감지하거나, 입력을 받아 출력하는 등의 수동적으로 아두이노 모듈을 활용하였다. 하지만 직접 아두이노와 semantic segmentation을 연결하여 semantic segmentation 결과를 조작하여, 아두이노를 인공지능과 결합하여 능동적으로 사용할 수 있게 하였다.