• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.251-252
• /
• 2023

As technology improves with the 4th industrial revolution, smart construction is becoming a key part of safety management in the architecture and civil engineering. By using object detection technology with CCTV data, construction sites can be managed efficiently. In this study, super resolution technology based on deep learning is proposed to improve the accuracy of object detection in construction sites. As the resolution of a train set data and test set data get higher, the accuracy of object detection model gets better. Therefore, according to the scale of construction sites, different object detection models can be considered.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.893-903
• /
• 2022

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.587-598
• /
• 2022

To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique pre-classifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.989-1006
• /
• 2020

Building change monitoring based on building detection is one of the most important fields in terms of monitoring artificial structures using high-resolution multi-temporal images such as CAS500-1 and 2, which are scheduled to be launched. However, not only the various shapes and sizes of buildings located on the surface of the Earth, but also the shadows or trees around them make it difficult to detect the buildings accurately. Also, a large number of misdetection are caused by relief displacement according to the azimuth and elevation angles of the platform. In this study, object-based building detection was performed using the azimuth angle of the Sun and the corresponding main direction of shadows to improve the results of building change detection. After that, the platform's azimuth and elevation angles were used to detect changed buildings. The object-based segmentation was performed on a high-resolution imagery, and then shadow objects were classified through the shadow intensity, and feature information such as rectangular fit, Gray-Level Co-occurrence Matrix (GLCM) homogeneity and area of each object were calculated for building candidate detection. Then, the final buildings were detected using the direction and distance relationship between the center of building candidate object and its shadow according to the azimuth angle of the Sun. A total of three methods were proposed for the building change detection between building objects detected in each image: simple overlay between objects, comparison of the object sizes according to the elevation angle of the platform, and consideration of direction between objects according to the azimuth angle of the platform. In this study, residential area was selected as study area using high-resolution imagery acquired from KOMPSAT-3 and Unmanned Aerial Vehicle (UAV). Experimental results have shown that F1-scores of building detection results detected using feature information were 0.488 and 0.696 respectively in KOMPSAT-3 image and UAV image, whereas F1-scores of building detection results considering shadows were 0.876 and 0.867, respectively, indicating that the accuracy of building detection method considering shadows is higher. Also among the three proposed building change detection methods, the F1-score of the consideration of direction between objects according to the azimuth angles was the highest at 0.891.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.136-144
• /
• 2022

Construction sites are characterized by dangerous situations and environments that cause fatal accidents. Potential risk detection needs to be improved by continuously monitoring site conditions. However, the current labor-intensive inspection practice has many limitations in monitoring dangerous conditions at construction sites. Computer vision technology that can quickly analyze and collect site conditions from images has been in the spotlight as a solution. Nonetheless, inspection results obtained via computer vision are still stored and managed in centralized systems vulnerable to tampering with information by the central node. Blockchain has been used as a reliable and efficient decentralized information management system. Despite its potential, only limited research has been conducted integrating computer vision and blockchain. Therefore, to solve the current safety management problems, the authors propose a framework for construction site inspection that integrates object detection and blockchain network, enabling efficient and reliable remote inspection. Object detection is applied to enable the automatic analysis of site safety conditions. As a result, the workload of safety managers can be reduced with inspection results stored and distributed reliably through the blockchain network. In addition, errors or forgery in the inspection process can be automatically prevented and verified through a smart contract. As site safety conditions are reliably shared with project participants, project participants can remotely inspect site conditions and make safety-related decisions in trust.

• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.2
• /
• pp.74-78
• /
• 2018

Recently, due to decrease hardware prices and the development of technology, analog signage has been changing to digital signage for providing content such as advertisements, videos. Furthermore, in order to provide advertisements and contents to users more effectively, technical researches are being conducted in various industries. In addition, including digital signage that uses displays, it can be seen that it provides advertisements and contents using diverse devices such as LED signage, smart pads, and smart phones. However, most digital signage is installed in one place to provide contents and provides interactivity through simple events such as manual content provision or touch. So, in this paper, we suggest a new object detection algorithm based on an adjacent frames based image correction algorithm for interactive building signage.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.6
• /
• pp.1161-1175
• /
• 2018

An unexpected event could be easily followed by a large secondary accident due to the limitation in sight of drivers in road tunnels. Therefore, a series of automated incident detection systems have been under operation, which, however, appear in very low detection rates due to very low image qualities on CCTVs in tunnels. In order to overcome that limit, deep learning based tunnel incident detection system was developed, which already showed high detection rates in November of 2017. However, since the object detection process could deal with only still images, moving direction and speed of moving vehicles could not be identified. Furthermore it was hard to detect stopping and reverse the status of moving vehicles. Therefore, apart from the object detection, an object tracking method has been introduced and combined with the detection algorithm to track the moving vehicles. Also, stopping-reverse discrimination algorithm was proposed, thereby implementing into the combined incident detection processes. Each performance on detection of stopping, reverse driving and fire incident state were evaluated with showing 100% detection rate. But the detection for 'person' object appears relatively low success rate to 78.5%. Nevertheless, it is believed that the enlarged richness of image big-data could dramatically enhance the detection capacity of the automatic incident detection system.

• Journal of the Korea Institute of Building Construction
• /
• v.8 no.4
• /
• pp.71-77
• /
• 2008

Earthwork is very equipment-intensive task and researches related to automated excavation have been conducted. There is an issue to secure the safety for an automated excavating system. Therefore, this paper focuses on how to improve safety for semi- or fully-automated backhoe excavation. The primary objective of this research is to develop the core technology for automated object detection in excavation work. In order to satisfy the research objective, a diverse sensing technologies are investigated and analysed in terms of functions, durability, and reliability. The authors developed detecting algorithm for the objects using laser sensor and verified its performance by several tests. The results of this study would be the basis for developing the automated object detection system.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.923-926
• /
• 2003

In this paper we propose a scheme to generate DTM and detect buildings on DSM generated from LIDAR data. Two stages are performed. The first stage is to perform object segmentation by using two morphology operations namely, flattening and H-Dome transformation. After filtering out the object points above the ground, we used the non-object points to generate DTM. The second stage is to detect buildings from the objects by analyzing differential slopes. The test data is in raster form with 1m spacing around Hsin-Chu Scientific Area in Taiwan. The mean error is -0.16m and the RMSE is 0.45m for DTM generation. The successful rate for building detection is 87.7%.