• Journal of the Korea Institute of Building Construction
• /
• v.21 no.5
• /
• pp.397-408
• /
• 2021

The construction industry has the highest occupational accidents/injuries and has experienced the most fatalities among entire industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. A long-time monitoring surveillance system causes high physical fatigue and has limitations in grasping all accidents in real-time. Therefore, this study aims to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple object tracking with instance segmentation. To evaluate the system's performance, we utilized the Microsoft common objects in context and the multiple object tracking challenge metrics. These results prove that it is optimal for efficiently automating monitoring surveillance system task at construction sites.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.29-34
• /
• 2022

We propose a novel network architecture and build dataset for recognizing clickable objects on mobile device screens. The data was collected based on clickable objects on the mobile device screen that have numerous resolution, and a total of 24,937 annotation data were subdivided into seven categories: text, edit text, image, button, region, status bar, and navigation bar. We use the Deconvolution Single Shot Detector as a baseline, the backbone network with Squeeze-and-Excitation blocks, the Single Shot Detector layer structure to derive inference results and the Feature pyramid networks structure. Also we efficiently extract features by changing the input resolution of the existing 1:1 ratio of the network to a 1:2 ratio similar to the mobile device screen. As a result of experimenting with the dataset we have built, the mean average precision was improved by up to 101% compared to baseline.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.1-19
• /
• 2019

Artificial intelligence (AI) is one of the main driving forces leading the Fourth Industrial Revolution. The technologies associated with AI have already shown superior abilities that are equal to or better than people in many fields including image and speech recognition. Particularly, many efforts have been actively given to identify the current technology trends and analyze development directions of it, because AI technologies can be utilized in a wide range of fields including medical, financial, manufacturing, service, and education fields. Major platforms that can develop complex AI algorithms for learning, reasoning, and recognition have been open to the public as open source projects. As a result, technologies and services that utilize them have increased rapidly. It has been confirmed as one of the major reasons for the fast development of AI technologies. Additionally, the spread of the technology is greatly in debt to open source software, developed by major global companies, supporting natural language recognition, speech recognition, and image recognition. Therefore, this study aimed to identify the practical trend of AI technology development by analyzing OSS projects associated with AI, which have been developed by the online collaboration of many parties. This study searched and collected a list of major projects related to AI, which were generated from 2000 to July 2018 on Github. This study confirmed the development trends of major technologies in detail by applying text mining technique targeting topic information, which indicates the characteristics of the collected projects and technical fields. The results of the analysis showed that the number of software development projects by year was less than 100 projects per year until 2013. However, it increased to 229 projects in 2014 and 597 projects in 2015. Particularly, the number of open source projects related to AI increased rapidly in 2016 (2,559 OSS projects). It was confirmed that the number of projects initiated in 2017 was 14,213, which is almost four-folds of the number of total projects generated from 2009 to 2016 (3,555 projects). The number of projects initiated from Jan to Jul 2018 was 8,737. The development trend of AI-related technologies was evaluated by dividing the study period into three phases. The appearance frequency of topics indicate the technology trends of AI-related OSS projects. The results showed that the natural language processing technology has continued to be at the top in all years. It implied that OSS had been developed continuously. Until 2015, Python, C ++, and Java, programming languages, were listed as the top ten frequently appeared topics. However, after 2016, programming languages other than Python disappeared from the top ten topics. Instead of them, platforms supporting the development of AI algorithms, such as TensorFlow and Keras, are showing high appearance frequency. Additionally, reinforcement learning algorithms and convolutional neural networks, which have been used in various fields, were frequently appeared topics. The results of topic network analysis showed that the most important topics of degree centrality were similar to those of appearance frequency. The main difference was that visualization and medical imaging topics were found at the top of the list, although they were not in the top of the list from 2009 to 2012. The results indicated that OSS was developed in the medical field in order to utilize the AI technology. Moreover, although the computer vision was in the top 10 of the appearance frequency list from 2013 to 2015, they were not in the top 10 of the degree centrality. The topics at the top of the degree centrality list were similar to those at the top of the appearance frequency list. It was found that the ranks of the composite neural network and reinforcement learning were changed slightly. The trend of technology development was examined using the appearance frequency of topics and degree centrality. The results showed that machine learning revealed the highest frequency and the highest degree centrality in all years. Moreover, it is noteworthy that, although the deep learning topic showed a low frequency and a low degree centrality between 2009 and 2012, their ranks abruptly increased between 2013 and 2015. It was confirmed that in recent years both technologies had high appearance frequency and degree centrality. TensorFlow first appeared during the phase of 2013-2015, and the appearance frequency and degree centrality of it soared between 2016 and 2018 to be at the top of the lists after deep learning, python. Computer vision and reinforcement learning did not show an abrupt increase or decrease, and they had relatively low appearance frequency and degree centrality compared with the above-mentioned topics. Based on these analysis results, it is possible to identify the fields in which AI technologies are actively developed. The results of this study can be used as a baseline dataset for more empirical analysis on future technology trends that can be converged.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.363-373
• /
• 2020

During last decades numerous studies generating orthoimage have been carried out. Traditional methods require exterior orientation parameters of aerial images and precise 3D object modeling data and DTM (Digital Terrain Model) to detect and recover occlusion areas. Furthermore, it is challenging task to automate the complicated process. In this paper, we proposed a new concept of true orthoimage generation using DL (Deep Learning). DL is rapidly used in wide range of fields. In particular, GAN (Generative Adversarial Network) is one of the DL models for various tasks in imaging processing and computer vision. The generator tries to produce results similar to the real images, while discriminator judges fake and real images until the results are satisfied. Such mutually adversarial mechanism improves quality of the results. Experiments were performed using GAN-based Pix2Pix model by utilizing IR (Infrared) orthoimages, intensity from LiDAR data provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) through the ISPRS (International Society for Photogrammetry and Remote Sensing). Two approaches were implemented: (1) One-step training with intensity data and high resolution orthoimages, (2) Recursive training with intensity data and color-coded low resolution intensity images for progressive enhancement of the results. Two methods provided similar quality based on FID (Fréchet Inception Distance) measures. However, if quality of the input data is close to the target image, better results could be obtained by increasing epoch. This paper is an early experimental study for feasibility of DL-based true orthoimage generation and further improvement would be necessary.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.31-38
• /
• 2017

In this paper, we propose a system which estimates Manhattan coordinate systems for urban scene images using a convolutional neural network (CNN). Estimating the Manhattan coordinate system from an image under the Manhattan world assumption is the basis for solving computer graphics and vision problems such as image adjustment and 3D scene reconstruction. We construct a CNN that estimates Manhattan coordinate systems based on GoogLeNet [1]. To train the CNN, we collect about 155,000 images under the Manhattan world assumption by using the Google Street View APIs and calculate Manhattan coordinate systems using existing calibration methods to generate dataset. In contrast to PoseNet [2] that trains per-scene CNNs, our method learns from images under the Manhattan world assumption and thus estimates Manhattan coordinate systems for new images that have not been learned. Experimental results show that our method estimates Manhattan coordinate systems with the median error of $3.157^{\circ}$ for the Google Street View images of non-trained scenes, as test set. In addition, compared to an existing calibration method [3], the proposed method shows lower intermediate errors for the test set.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.621-628
• /
• 2021

This paper proposes a method to calibrate a thermal camera with three different perspectives. In particular, the intrinsic parameters of the camera and re-projection errors were provided to quantify the accuracy of the calibration result. Three lenses of the camera capture the same image, but they are not overlapped, and the image resolution is worse than the one captured by the RGB camera. In computer vision, camera calibration is one of the most important and fundamental tasks to calculate the distance between camera (s) and a target object or the three-dimensional (3D) coordinates of a point in a 3D object. Once calibration is complete, the intrinsic and the extrinsic parameters of the camera(s) are provided. The intrinsic parameters are composed of the focal length, skewness factor, and principal points, and the extrinsic parameters are composed of the relative rotation and translation of the camera(s). This study estimated the intrinsic parameters of thermal cameras that have three lenses of different perspectives. In particular, image enhancement based on a deep learning algorithm was carried out to improve the quality of the calibration results. Experimental results are provided to substantiate the proposed method.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.308-317
• /
• 2022

Researches are underway to efficiently reduce the size of video data transmitted and stored in the image analysis process using deep learning-based machine vision technology. MPEG (Moving Picture Expert Group) has newly established a standardization project called VCM (Video Coding for Machine) and is conducting research on video encoding for machines rather than video encoding for humans. We are researching a multitask that performs various tasks with one image input. The proposed pipeline does not perform all object detection of each task that should precede object detection, but precedes it only once and uses the result as an input for each task. In this paper, we propose a pipeline for efficient multitasking and perform comparative experiments on compression efficiency, execution time, and result accuracy of the input image to check the efficiency. As a result of the experiment, the capacity of the input image decreased by more than 97.5%, while the accuracy of the result decreased slightly, confirming the possibility of efficient multitasking.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.57-74
• /
• 2022

Recently, artificial intelligence parking control systems have increased the recognition rate of vehicle license plates using deep learning, but there is a problem that they cannot determine vehicles with fake license plates. Despite these security problems, several institutions have been using the existing system so far. For example, in an experiment using a counterfeit license plate, there are cases of successful entry into major government agencies. This paper proposes an improved system over the existing artificial intelligence parking control system to prevent vehicles with such fake license plates from entering. The proposed method is to use the degree of matching of the front feature points of the vehicle as a passing criterion using the ORB algorithm that extracts information on feature points characterized by an image, just as the existing system uses the matching of vehicle license plates as a passing criterion. In addition, a procedure for checking whether a vehicle exists inside was included in the proposed system to prevent the entry of the same type of vehicle with a fake license plate. As a result of the experiment, it showed the improved performance in identifying vehicles with fake license plates compared to the existing system. These results confirmed that the methods proposed in this paper could be applied to the existing parking control system while taking the flow of the original artificial intelligence parking control system to prevent vehicles with fake license plates from entering.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.