• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.3
• /
• pp.300-312
• /
• 2000

The application areas of embedded real-time systems are very wide and so are the requirements for real-time processing and reliability of the systems. To develop embedded real-time systems effectively with its real-time and reliability properties guaranteed, an appropriate real-time model is needed. Recently, the research on real-time object-oriented model is active, which graft the concept of object-orientation on real-time systems modeling and development. In this paper, we propose dRTO (dependable Real-Time Object) model, with 5 primitive classes. These allow designers to effectively model the characteristics of real-time systems, i.e., object-orientation, real-time-ness and dependability. The dRTO model has three main features. First, it is able to model and implement the timing constraints imposed on real-time objects as well as interactions among the objects. Second, hardware and software components (including kernel) of embedded systems can be modeled in one frame. Third, it is able to represent fault detection and recovery mechanisms explicitly.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.311-318
• /
• 2024

Quality control in construction projects necessitates the detection of defects during construction. Currently, this task is performed manually by site supervisors. This manual process is inefficient, labor-intensive, and prone to human error, potentially leading to decreased productivity. To address this issue, research has been conducted to automate defect detection using computer vision-based object detection technologies. However, these studies often suffer from a lack of data for training deep learning models, resulting in inadequate accuracy. This study proposes a method to improve the accuracy of deep learning models through the use of virtual image data. The target building is created as a 3D model and finished with materials similar to actual components. Subsequently, a virtual defect texture is produced by layering three types of images: defect information, area information, and material information images, to fabricate materials with defects. Images are generated by rendering the 3D model and the defect, and annotations are created for segmentation. This approach creates a hybrid dataset by combining virtual data with actual site image data, which is then used to train the deep learning model. This research was conducted on the tile process of finishing construction projects, focusing on cracks and falls as the target defects. The training results of the deep learning model show that the F1-Score increased by 12.08% for falls and cracks when using the hybrid dataset compared to the real image dataset alone, validating the hybrid data approach. This study contributes not only to unmanned and automated smart construction management but also to enhancing safety on construction sites. To establish an integrated smart quality management system, it is necessary to detect various defects simultaneously with high accuracy. Utilizing this method for automatic defect detection in other types of construction can potentially expand the possibilities for implementing an integrated smart quality management system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2013

In this paper, we propose an algorithm to detect scale invariant object from IR image obtained in the sea environment. We create horizontal edge (HL), vertical edge (LH), diagonal edge (HH) of images through 2-D discrete Haar wavelet transform (DHWT) technique after noise reduction using morphology operations. Considering the sea environment, Gaussian blurring to the horizontal and vertical edge images at each level of wavelet is performed and then saliency map is generated by multiplying the blurred horizontal and vertical edges and combining into one image. Then we extract object candidate region by performing a binarization to saliency map. A small area in the object candidate region are removed to produce final result. Experiment results show the feasibility of the proposed algorithm.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.6
• /
• pp.130-141
• /
• 2011

The intelligent excavating system(IES), the development in South Korea of which has been underway since 2006, aims for the full-scale automation of the excavation process that includes a series of tasks such as movement, excavation and loading. The core elements to ensure the quality and safety of the automated excavation equipment include 3D modeling of terrain that surrounds the excavating robot and the technology for detecting objects accurately(i.e., for detecting the location of nearby loading trucks and humans as well as of obstacles positioned on the movement paths). Therefore the purpose of this research is to ensure the quality and safety of automated excavation detecting the objects surrounding the excavating robot via a 3D laser scanning system. In this paper, an algorithm for estimating the location, height, width, and shape of objects in the 3D-realized terrain that surrounds the location of the excavator was proposed. The performance of the algorithm was verified via tests in an actual earthwork field.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.499-508
• /
• 2023

In this paper, we propose a technique to estimate the coordinates of feature points existing on a 2D planar object in the three dimensional space. The proposed method detects multiple 3D features from the image, and excludes those which are not located on the plane. The proposed technique estimates the planar homography between the planar object in the 3D space and the camera image plane, and computes back-projection error of each feature point on the planar object. Then any feature points which have large error is considered as off-plane points and are excluded from the feature estimation phase. The proposed method is archived on the basis of the planar homography without any additional sensors or optimization algorithms. In the expretiments, it was confirmed that the speed of the proposed method is more than 40 frames per second. In addition, compared to the RGB-D camera, there was no significant difference in processing speed, and it was verified that the frame rate was unaffected even in the situation that the number of detected feature points continuously increased.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.10
• /
• pp.116-122
• /
• 2016

This paper proposes a practical object shape reconstruction method using an underwater imaging sonar. In order to reconstruct the object shape, three methods are utilized. Firstly, the vertical field of view of imaging sonar is modified to narrow angle to reduce an uncertainty of estimated 3D position. The wide vertical field of view makes the incorrect estimation result about the 3D position of the underwater object. Secondly, simple noise filtering and range detection methods are designed to extract a distance from the sonar image. Lastly, a low pass filter is adopted to estimate a probability of voxel occupancy. To demonstrate the proposed methods, object shape reconstruction for three sample objects was performed in a basin and results are explained.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.667-670
• /
• 2020

최근에는 증강현실, 로봇공학 등의 분야에서 객체의 위치 검출 이외에도, 객체의 자세에 대한 추정이 요구되고 있다. 객체의 자세 정보가 포함된 데이터셋은 위치 정보만 포함된 데이터셋에 비하여 상대적으로 매우 적기 때문에 인공 신경망 구조를 활용하기 어려운 측면이 있으나, 최근에 들어서는 기계학습 기반의 자세 추정 알고리즘들이 여럿 등장하고 있다. 본 논문에서는 이 가운데 Dense 6d Pose Object detector (DPOD) [11]의 구조를 기반으로 하여 가구의 조립 설명서에 그려진 가구 부품들의 자세를 추정하고자 한다. DPOD [11]는 입력으로 RGB 영상을 받으며, 해당 영상에서 자세를 추정하고자 하는 객체의 영역에 해당하는 픽셀들을 추정하고, 객체의 영역에 해당되는 각 픽셀에서 해당 객체의 3D 모델의 UV map 값을 추정한다. 이렇게 픽셀 개수만큼의 2D - 3D 대응이 생성된 이후에는, RANSAC과 PnP 알고리즘을 통해 RGB 영상에서의 객체와 객체의 3D 모델 간의 변환 관계 행렬이 구해지게 된다. 본 논문에서는 사전에 정해진 24개의 자세 후보들을 기반으로 가구 부품의 3D 모델을 2D에 투영한 RGB 영상들로 인공 신경망을 학습하였으며, 평가 시에는 실제 조립 설명서에서의 가구 부품의 자세를 추정하였다. 실험 결과 IKEA의 Stefan 의자 조립 설명서에 대하여 100%의 ADD score를 얻었으며, 추정 자세가 자세 후보군 중 정답 자세에 가장 근접한 경우를 정답으로 평가했을 때 100%의 정답률을 얻었다. 제안하는 신경망을 사용하였을 때, 가구 조립 설명서에서 가구 부품의 위치를 찾는 객체 검출기(object detection network)와, 각 개체의 종류를 구분하는 객체 리트리벌 네트워크(retrieval network)를 함께 사용하여 최종적으로 가구 부품의 자세를 추정할 수 있다.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.10 no.4
• /
• pp.78-84
• /
• 1996

In this study, 3-D object recognition and restoration independent of the object translation for automotive kind recognition in parking administration system using an ultrasonic sensor array, neural networks and invariant moments are presented. Using invariant moment vectors of the acquired data 16$\times$8 pixels, 3-D objects could be classified by SCL (Simple Competitive Learning) neural networks. Modified SCL neural networks using the 16$\times$8 low resolution image was used for object restoration of 32$\times$32 high resolution image. Invariant moment vectors kept constant independent of the object translation. The recognition rates for the training and the testing data were 98[%] and 95[%], respectively. The experimental results have shown that ultrasonic sensor array with the neural networks could be applied for the detection of the automobiles and classification of the automotive kind.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.59-66
• /
• 2021

Humans mainly recognize surrounding objects using visual and auditory information among the five senses (sight, hearing, smell, touch, taste). Major research related to the latest object recognition mainly focuses on analysis using image sensor information. In this paper, after emitting various chirp audio signals into the observation space, collecting echoes through a 2-channel receiving sensor, converting them into spectral images, an object recognition experiment in 3D space was conducted using an image learning algorithm based on deep learning. Through this experiment, the experiment was conducted in a situation where there is noise and echo generated in a general indoor environment, not in the ideal condition of an anechoic room, and the object recognition through echo was able to estimate the position of the object with 83% accuracy. In addition, it was possible to obtain visual information through sound through learning of 3D sound by mapping the inference result to the observation space and the 3D sound spatial signal and outputting it as sound. This means that the use of various echo information along with image information is required for object recognition research, and it is thought that this technology can be used for augmented reality through 3D sound.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.326-331
• /
• 2019

In the real world, there are both dynamic objects and static objects, but an autonomous vehicle or mobile robot cannot distinguish between them, even though a human can distinguish them easily. It is important to distinguish static objects from dynamic objects clearly to perform autonomous driving successfully and stably for an autonomous vehicle or mobile robot. To do this, various sensor systems can be used, like cameras and LiDAR. Stereo camera images are used often for autonomous driving. The stereo camera images can be used in object recognition areas like object segmentation, classification, and tracking, as well as navigation areas like 3D world reconstruction. This study suggests a method to distinguish static/dynamic objects using stereo vision for an online autonomous vehicle and mobile robot. The method was applied to a 3D world map reconstructed from stereo vision for navigation and had 99.81% accuracy.