• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• Journal of Advanced Navigation Technology
• /
• v.21 no.3
• /
• pp.251-257
• /
• 2017

Recently, hybrid positioning system combining GPS, vision sensor, and inertial sensor has drawn many attentions to estimate accurate vehicle positions. Since accurate multi-sensor fusion requires efficient time synchronization, this paper proposes an efficient method to obtain time synchronized measurements of vision sensor, inertial sensor, and OBD device based on GPS time information. In the proposed method, the time and position information is obtained by the GPS receiver, the attitude information is obtained by the inertial sensor, and the speed information is obtained by the OBD device. The obtained time, position, speed, and attitude information is converted to the color information. The color information is inserted to several corner pixels of the corresponding image frame. An experiment was performed with real measurements to evaluate the feasibility of the proposed method.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.4 no.2
• /
• pp.38-45
• /
• 1995

The diagnosis and monitoring system of abnormal cutting condition is necessary to realize precision machining proces and factory automation, which are final goal of metal cutting in order to develop this system, theimage processing technique has been investigated in machining process. In theis paper, the measurement system of tool wear using computer vision is designed to detect the wear pattern by non-contact and direct method and get the realiable wear information about cutting tool. We measured the area of the side and front part of the diamond core dril which is used in 40kHz ultrasonic vibration machine.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.88-93
• /
• 1993

This paper introduces an ARV(Autonomous Road Vehicle) system which can run on orads without help of a driver by detecting road boundaries through computer vision. This vehicle can also detect obstacles in front through sonar sensors and infrared sensors. This system largely consists of a handle steering module and a braking module. From road boundaries, the steering module determines handle turn angle. The braking module stops or decelerates to avoid collision depending on the relative speeds and distance to the obstacles detected by different sensors. This ARV system has been implemented in a small jeep and can run 30-40 km/h city traffic. In this paper, we illustrate the structure of the ARV systems and its operation principle.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.700-704
• /
• 1989

A robotic system with a 3-dimensional profile measuring sensor is developed in order to measure the complicated shape of the target body. Due to this 3-dimensional profile measuring sensor, a computer is able to adjust the posture of the robot hand so that complicated global profile of the target body can be recognized after several measurements from the variant directions. In order to enable fast data processing, a digital signal processor and a look-up table is introduced.

• Journal of information and communication convergence engineering
• /
• v.12 no.4
• /
• pp.263-270
• /
• 2014

Corner detection and feature extraction are essential aspects of computer vision problems such as object recognition and tracking. Feature detectors such as Scale Invariant Feature Transform (SIFT) yields high quality features but computationally intensive for use in real-time applications. The Features from Accelerated Segment Test (FAST) detector provides faster feature computation by extracting only corner information in recognising an object. In this paper we have analyzed the efficient object detection algorithms with respect to efficiency, quality and robustness by comparing characteristics of image detectors for corner detector and feature extractors. The simulated result shows that compared to conventional SIFT algorithm, the object recognition system based on the FAST corner detector yields increased speed and low performance degradation. The average time to find keypoints in SIFT method is about 0.116 seconds for extracting 2169 keypoints. Similarly the average time to find corner points was 0.651 seconds for detecting 1714 keypoints in FAST methods at threshold 30. Thus the FAST method detects corner points faster with better quality images for object recognition.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.347-348
• /
• 2024

본 논문에서는 철도 구성요소 모니터링을 위한 효율적인 객체 분할 기법으로 사전학습된 SegFormer 모델의 적용을 제안하고, 객체 분할을 위해 보편적으로 사용되는 U-Net 모델과의 성능 비교 분석을 진행하였다. 철도의 주요 구성요소인 선로, 침목, 고정 장치, 배경을 분할할 수 있도록 라벨링된 데이터셋을 학습에 사용하였다. SegFormer 모델이 대조군인 U-Net보다 성능이 Jaccard Score 기준 5.29% 향상됨에 따라 Vision Transformer 기반의 모델이 기존 CNN 기반 모델의 이미지의 전역적인 문맥을 파악하기 상대적으로 어렵다는 한계를 극복하고, 철도 구성요소 객체 분할에 더욱 효율적인 모델임을 확인한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4115-4120
• /
• 2010

In manual inspection of Lead Screw of computers many workers are needed to inspect samples, and its main disadvantage is that such types of inspection system not only gives low production, but also gives low perfection. Besides, in manual inspection system, the inspection cost of samples is higher than that of the automatic inspection system. Therefore, in this study to compensate these shortcomings, an automatic inspection system is developed. For the inspection of the surfaces and different dimensional parameters of computer Lead screw, a $360^{\circ}$ rotating machine vision system is developed. From the detailed analysis of the inspection results using the present developed inspection system, it is observed that the developed Lead Screw automatic inspection system is superior to those of manually inspection system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.3
• /
• pp.270-274
• /
• 2002

This paper presents a teleoperation system that combines computer network and an autonomous mobile robot. We control remotely an autonomous mobile robot with vision over the Internet to guide it under unknown environments in the real time. The main feature of this system is that local operators need a web browser and a computer connected to the communication network and so they can command the robot in a remote location through the home page. The hardware architecture of this system consists of an autonomous mobile robot, workstation, and local computers. The software architecture of this system includes the client part for the user interface and robot control as well as the server part for communication between users and robot. The server and client systems are developed using Java language which is suitable to internet application and supports multi-platform. Furthermore. this system offers an image compression method using JPEG concept which reduces large time delay that occurs in network during image transmission.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1858-1861
• /
• 2005

Automatic nut sorting machine used to calculate the size of inserted nut and detect the black spot defection is introduced in this paper. Because most of farm products are imported from the underdeveloped countries, domestic farm products have no place to be sold in market. To overcome this critical situation, lowering the productivity cost is strongly demanded to compete with foreign corps. Imaged processed nut sorting algorithm is developed to the automatic nut sorting machine to remove the sorting time which takes lots of man power. This system is composed of mainly two parts, mechanical parts and vision system. The purpose of mechanical part is supplying the nuts automatically to make computer system capture the images of objects. Simplified mechanical system was assembled followed by 3D simulation by Pro/E design for the adaptive cost effects. Several image processing algorithms are designed to detect the spot defects and calculate the size of nuts. Test algorithm shows good results to the designed automatic nut sorting system.