• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1282-1282
• /
• 2024

Given the widespread use of intelligent surveillance cameras at construction sites, recent studies have introduced vision-based deep learning approaches. These studies have focused on enhancing the performance of vision-based excavator activity recognition to automatically monitor productivity metrics such as activity time and work cycle. However, acquiring a large amount of training data, i.e., videos captured from actual construction sites, is necessary for developing a vision-based excavator activity recognition model. Yet, complexities of dynamic working environments and security concerns at construction sites pose limitations on obtaining such videos from various surveillance camera locations. Consequently, this leads to performance degradation in excavator activity recognition models, reducing the accuracy and efficiency of heavy equipment productivity analysis. To address these limitations, this study aimed to conduct sensitivity analysis of excavator activity recognition performance based on surveillance camera location, utilizing synthetic videos generated from a game-engine-based virtual environment (Unreal Engine). Various scenarios for surveillance camera placement were devised, considering horizontal distance (20m, 30m, and 50m), vertical height (3m, 6m, and 10m), and horizontal angle (0° for front view, 90° for side view, and 180° for backside view). Performance analysis employed a 3D ResNet-18 model with transfer learning, yielding approximately 90.6% accuracy. Main findings revealed that horizontal distance significantly impacted model performance. Overall accuracy decreased with increasing distance (76.8% for 20m, 60.6% for 30m, and 35.3% for 50m). Particularly, videos with a 20m horizontal distance (close distance) exhibited accuracy above 80% in most scenarios. Moreover, accuracy trends in scenarios varied with vertical height and horizontal angle. At 0° (front view), accuracy mostly decreased with increasing height, while accuracy increased at 90° (side view) with increasing height. In addition, limited feature extraction for excavator activity recognition was found at 180° (backside view) due to occlusion of the excavator's bucket and arm. Based on these results, future studies should focus on enhancing the performance of vision-based recognition models by determining optimal surveillance camera locations at construction sites, utilizing deep learning algorithms for video super resolution, and establishing large training datasets using synthetic videos generated from game-engine-based virtual environments.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.9
• /
• pp.841-849
• /
• 2013

Workers engaged in construction works have been exposed to high levels of noise during their work in tunnels. Noise is one of the major health hazards for employees working in construction sites. The aim of this study is to evaluate the noise levels generating from tunneling equipments such as jumbo drills, backhoes, payloaders, shotcrete machines and service cars. Explosion and turbo fan noises were also monitored. A high precision sound level meter was introduced for measuring LAeq, LAFmax, LAFmin and LCpeak noises in 5 tunneling work sites that were located in Seoul, Kyunggi-do and Kangwon-do areas with NATM and shield methods. The highest noise was recorded by explosion(151.9 dB LCpeak) followed by jumbo drills of higher than 110 dB(A) LAeq. Backhoe normally generated 90~110 dB(A) LAeq while breaking work of rock showed additional around 5~15 dB(A). Noise exposure levels for payloader and shotcrete machine scored more than 90 dB(A) which might be a source of noise-induced hearing loss. Additional research in revealing noise levels from construction equipments operating in tunneling works may enhance the protection of workers who exposed to noise primarily at the sites.

• Journal of Korean Society on Water Environment
• /
• v.30 no.5
• /
• pp.532-538
• /
• 2014

A cylinder-shaped filter was developed to manage the runoff from construction sites. Compressed air was used for back-washing and pore sizes of filter were $23{\mu}m$ and $46{\mu}m$. The turbid water was prepared using sediments in construction sites. The grain size analysis showed that grains smaller than $38{\mu}m$ and larger than $335{\mu}m$ in size constituted 34.4 % and 37.6 %, respectively. Removal efficiency of the filter on turbidity, SS, COD, TN and TP showed 25~37%, 20~40%, 50~55%, 23~27% and 14~20%, respectively, whereas their removal efficiecy by using coagulant PAC showed 77~84%, 70~83%, 53~60%, 27~36%, and 59~75%, respectively. The filtration time was determined to be around 10 to 20 minutes. Back-washing for 10 seconds by pressurized air resulted in a satisfactory regeneration efficiency. According to the aforementioned test results, the cylinder-shaped filter is effective in reducing turbidity and would be suitable for practical application in construction sites and farms.

• Journal of Drive and Control
• /
• v.17 no.3
• /
• pp.1-8
• /
• 2020

Recently, a special purpose machine with two manipulators and quadruped crawler system has been developed for rapid life-saving and initial restoration work at disaster sites. This special purpose machine provides the driver with various environmental recognition functions for accurate and rapid task determination. In particular, the human detection technology assists the driver in poor working conditions such as low-light, dust, water vapor, fog, rain, etc. to prevent secondary human accidents when moving and working. In this study, a human detection module is developed to be mounted on a special purpose machine. A thermal sensor and CCD camera were used to detect victims and nearby workers in response to the difficult environmental conditions present at disaster sites. The performance of various AI-based life detection algorithm were verified and then applied to the task of detecting various objects with different postures and exposure conditions. In addition, image visibility improvement technology was applied to further improve the accuracy of human detection.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.411-418
• /
• 2002

In domestic road construction sites, the compaction control based on strength are widely performed through the direct method with high accuracy, such as Plate Loading Test or Field CBR test. It is impossible to manage all construction sites using the direct method because the direct method requires heavy reaction loads and long measurement time. Therefore, it is necessary to apply the indirect method that could control the relative density of construction sites on the whole. Indirect methods, such as Cone Penetration Test and Fall Cone Test, require extra time for data analyzing and fixed area for test device. In this paper, the field applicability of Soil Impact Hammer (SIH) was investigated comparing with the results of field measurement tests and laboratory compaction tests. SIH developed by Japan Construction Administration and Asanuma Ltd., is a kind of indirect methods for compaction checking. According to the results of SIH performed in domestic road construction site, the subgrade reaction modulus obtained from SIH are similar to that from Plate loading tests in the range of 10 to 40. In comparison with laboratory compaction test, similar compaction line are shown in the dry side of optimum moisture contents.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.211-218
• /
• 2021

Construction sites have various risk factors. There are various approaches to reduce safety accidents, but they have limitations to some extent. By utilizing the wireless communication technology of IT and the rapidly developing image processing technology, it will be possible to reduce accidents at the construction site if risk factors are identified and actively responded to. Therefore, in this study, a system that can detect risk factors of construction sites in advance is constructed, and a system is proposed to discover and respond to risk factors of construction sites using OpenCV for the purpose of real-time computer vision.

• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.433-446
• /
• 2022

Despite efforts to reduce unexpected accidents at confined construction sites, choking accidents continue to occur. Because of the poorly ventilated atmosphere, particularly in long, confined underground spaces, workers are subject to dangerous working conditions despite the use of artificial ventilation. Moreover, the traditional monitoring methods of using portable gas detectors place safety inspectors in direct contact with hazardous conditions. In this study, a long-range (LoRa)-based wireless safety monitoring system that features the network organization, fault-tolerant, power management, and a graphical user interface (GUI) was developed for underground construction sites. The LoRa wireless data communication system was adopted to detect hazardous gases and oxygen deficiency within a confined underground space with adjustable communication range and low power consumption. Fault tolerance based on the mapping information of the entire wireless sensor network was particularly implemented to ensure the reliable operation of the monitoring system. Moreover, a sleep mode was implemented for the efficient power management. The GUI was also developed to control the entire safety-monitoring system and to manage the measured data. The developed safety-monitoring system was validated in an indoor testing and at two full-scale water pipeline construction sites.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.05a
• /
• pp.335-340
• /
• 2004

To analyze risk factors of temporary power installations, the investigation was carried out for power receiving system and pack and panel boards at construction sites. The subject was variable such as an airport, an apartment, a municipal playground. There are many risk factors caused by inadequate working environments and the deterioration of temporary power installations using equipment with minimum safety devices at construction sites. There, it is intended to present problems and preventive measures against electrical shock accidents, through analyzing risk factors of real field condition and investigating temporary power installations all over the country.

• Journal of the Korean Institute of Rural Architecture
• /
• v.7 no.3
• /
• pp.76-83
• /
• 2005

According to the results of analyzing the formation enterprise of beautiful public latrines, which Chungcheongnamdo is promoting, the conclusions of this study are as follows. The design for construction form should be suitable well for the surrounding environment according to the installation place of public latrines. Construction scales and sanitary appliances should be decided according to the location, use personnel, use frequency, and user type of latrines. It is not desirable to decide working expenses on the basis of pyeong irrespective of construction scale. In the purchase of building sites, because the building sites owned by the nation or the public bodies are difficult to apply the related laws, it is difficult to construct public latrines as eternal facilities. Because the building sites owned by individuals are very expensive, the execution of enterprises is difficult. Therefore, it is necessary to simplify the administrative procedures and increase the working expenses.

• Journal of the Korean Society of Safety
• /
• v.22 no.4
• /
• pp.51-56
• /
• 2007

In order to present basic data for the balancing improvement of safety management level in domestic construction companies the improvement index and characteristic of safety management level are offered by comparing the year 2006's safety level with the year 2001's one. The companies under concern are classified into 51 large scale companies and 61 middle and small scale ones. The safety management level of both head office and construction sites is improved for all companies without regard to the scale. Specially, the improvement index of middle and small scale companies shows the higher rate than large ones and head office higher than construction sites.