• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.11a
• /
• pp.235-236
• /
• 2023

The process of construction site supervision plays a crucial role in ensuring safety and quality assurance in construction projects. However, traditional methods of supervision largely depend on human vision and individual experience, posing limitations in quickly detecting and preventing all defects. In particular, the thorough supervision of expansive sites is time-consuming and makes it challenging to identify all defects. This study proposes a new construction supervision system that utilizes vision processing technology and Artificial Intelligence(AI) to automatically detect and analyze defects as a solution to these issues. The system we developed is provided in the form of an application that operates on portable devices, designed to a lower technical barrier so that even non-experts can easily aid construction site supervision. The developed system swiftly and accurately identifies various potential defects at the construction site. As such, the introduction of this system is expected to significantly enhance the speed and accuracy of the construction supervision process.

• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.403-406
• /
• 2024

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.777-780
• /
• 2003

We have tried to create a vision system like human eye for a long time. We have obtained some distinguished results through many studies. Stereo vision is the most similar to human eye among those. This is the process of recreating 3-D spatial information from a pair of 2-D images. In this paper, we have designed a stereo matching algorithm based on systolic array architecture using edges and pixel data. This is more advanced vision system that improves some problems of previous stereo vision systems. This decreases noise and improves matching rate using edges and pixel data and also improves processing speed using high integration one chip FPGA and compact modules. We can apply this to robot vision and automatic control vehicles and artificial satellites.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2948-2963
• /
• 2015

In the field of computer vision, visual surveillance systems have recently become an important research topic. Growth in this area is being driven by both the increase in the availability of inexpensive computing devices and image sensors as well as the general inefficiency of manual surveillance and monitoring. In particular, the ultimate goal for many visual surveillance systems is to provide automatic activity recognition for events at a given site. A higher level of understanding of these activities requires certain lower-level computer vision tasks to be performed. So in this paper, we propose an intelligent activity recognition model that uses a structure learning method and a classification method. The structure learning method is provided as a K2-learning algorithm that generates Bayesian networks of causal relationships between sensors for a given activity. The statistical characteristics of the sensor values and the topological characteristics of the generated graphs are learned for each activity, and then a neural network is designed to classify the current activity according to the features extracted from the multiple sensor values that have been collected. Finally, the proposed method is implemented and tested by using PETS2013 benchmark data.

• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.233-242
• /
• 2019

Numerous space perception studies have shown that Euclidean 3-D structure cannot be recovered from binocular stereopsis, motion, combination of stereopsis and motion, or even with combined multiple sources of optical information. Humans, however, have no difficulties to perform the task-specific action despite of poor shape perception. We have applied humans skill and capabilities to artificial intelligence and computer vision but those machines are still far behind from humans abilities. Thus, we need to understand how we perceive depth in space and what information we use to perceive 3-D structure accurately to perform. The purpose of this paper was to review space perception literatures to apply humans abilities to artificial intelligence robots more advanced in future.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Aerospace Industry
• /
• s.95
• /
• pp.24-27
• /
• 2007

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.07a
• /
• pp.263-268
• /
• 2000

• The Journal of Korea Robotics Society
• /
• v.6 no.3
• /
• pp.197-209
• /
• 2011

This paper presents a localization system using ceiling images in a large indoor environment. For a system with low cost and complexity, we propose a single camera based system that utilizes ceiling images acquired from a camera installed to point upwards. For reliable operation, we propose a method using hybrid features which include natural landmarks in a natural scene and artificial landmarks observable in an infrared ray domain. Compared with previous works utilizing only infrared based features, our method reduces the required number of artificial features as we exploit both natural and artificial features. In addition, compared with previous works using only natural scene, our method has an advantage in the convergence speed and robustness as an observation of an artificial feature provides a crucial clue for robot pose estimation. In an experiment with challenging situations in a real environment, our method was performed impressively in terms of the robustness and accuracy. To our knowledge, our method is the first ceiling vision based localization method using features from both visible and infrared rays domains. Our system can be easily utilized with a variety of service robot applications in a large indoor environment.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.127-128
• /
• 2023

The construction industry is increasingly adopting vision AI technologies to improve efficiency and safety management. However, the complex and dynamic nature of construction sites can pose challenges to the accuracy of vision AI models trained on datasets that do not consider the background. This study investigates the effect of background on object recognition for vision AI in construction sites by constructing a learning dataset and a test dataset with varying backgrounds. Frame scaffolding was chosen as the object of recognition due to its wide use, potential safety hazards, and difficulty in recognition. The experimental results showed that considering the background during model training significantly improved the accuracy of object recognition.