• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1722-1728
• /
• 2011

The security issue in urban transit system has been widely considered as the common matters after the fire accident at Daegu subway station. The safe urban transit system is highly demanded because of the vast number of daily passengers, and it is one of the most challenging projects. We introduced a test model for integrated security system for urban transit system and built it at a subway station to demonstrate its performance. This system consists of cameras, sensor network and central monitoring software. We described the smart camera functionality in more detail. The proposed smart camera includes the moving objects recognition module, video analytics, video encoder and server module that transmits video and audio information.

• Journal of Information Technology Services
• /
• v.8 no.2
• /
• pp.147-156
• /
• 2009

As the result of the rapid development of IT technology, an on-line diagnostic system using the field bus communication network coupled with a smart sensor module will be widely used at the nuclear power plant in the near future. The smart sensor system is very useful for the prompt understanding of abnormal state of the key equipments installed in the nuclear power plant. In this paper, it is assumed that a smart sensor system based on the fieldbus communication network for the surveillance and diagnostics of safety-critical equipments will be installed in the harsh-environment of the nuclear power plant. It means that the key components of fieldbus communication system including microprocessor, FPGA, and ASIC devices, are to be installed in the RPV (reactor pressure vessel) and the RCS (reactor coolant system) area, which is the area of a high dose-rate gamma irradiation fields. Gamma radiation constraints for the DBA (design basis accident) qualification of the RTD sensor installed in the harsh environment of nuclear power plant, are typically on the order of 4 kGy/h. In order to use a field bus communication network as an ad-hoc diagnostics sensor network in the vicinity of the RCS pump area of the nuclear power plant, the robust survivability of IT-based micro-electronic components in such intense gamma-radiation fields therefore should be verified. An intelligent CCD camera system, which are composed of advanced micro-electronics devices based on IT technology, have been gamma irradiated at the dose rate of about 4.2kGy/h during an hour UP to a total dose of 4kGy. The degradation performance of the gamma irradiated CCD camera system is explained.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.259-262
• /
• 1997

This paper presents a visual servoing of RV-M2 robot manipulators to track and grasp moving object, using pruned dynamic recurrent neural networks(DRNN). The object is stationary in the robot work space and the robot is tracking and grasping the object by using CCD camera mounted on the end-effector. In order to optimize the structure of DRNN, we decide the node whether delete or add, by mutation probability, first in case of delete node, the node which have minimum sum of input weight is actually deleted, and then in case of add node, the weight is connected according to the number of case which added node can reach the other nodes. Using evolutionary programming(EP) that search the struture and weight of the DRNN, and evolution strategies(ES) which train the weight of neuron, we pruned the net structure of DRNN. We applied the DRNN to the Visual Servoing of a robot manipulators to control position and orientation of end-effector, and the validity and effectiveness of the pro osed control scheme will be verified by computer simulations.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.560-567
• /
• 1998

This paper concerned about a imputed color printed material image in camera to decrease noise and distortion by processing median filtering with input image to identical condition. Also this paper proposed the way of compares a normal printed material with an abnormal printed material color tone with trained a learning of the error back-propagation to block classification by extracting five place from identical block(3${\times}$3) of color printed material R, G, B value. As a representative algorithm of multi-layer perceptron the error Back-propagation technique used to solve complex problems. However, the Error Back-propagation is algorithm which basically used a gradient descent method which can be converged to local minimum and the Back Propagation train include problems, and that may converge in a local minimum rather than get a global minimum. The network structure appropriate for a given problem. In this paper, a good result is obtained by improve initial condition and adjust th number of hidden layer to solve the problem of real time process, learning and train.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.189-196
• /
• 2024

Frequent false positives alarm from the Intelligent Selective Control System have raised significant concerns. These persistent issues have led to declines in operational efficiency and market credibility among agents. Developing a new model or replacing the existing one to mitigate false positives alarm entails substantial opportunity costs; hence, improving the quality of the training dataset is pragmatic. However, smaller organizations face challenges with inadequate capabilities in dataset collection and refinement. This paper proposes an automatic human pose data collection system centered around a human pose estimation model, utilizing camera-based sensor fusion techniques and edge devices. The system facilitates the direct collection and real-time processing of field data at the network periphery, distributing the computational load that typically centralizes. Additionally, by directly labeling field data, it aids in constructing new training datasets.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.1
• /
• pp.39-45
• /
• 2019

We propose an active color model based method for tracking motions of multiple human using a networked multiple-camera system in IoT space as a human-robot coexistent system. An IoT space is a space where many intelligent devices, such as computers and sensors(color CCD cameras for example), are distributed. Human beings can be a part of IoT space as well. One of the main goals of IoT space is to assist humans and to do different services for them. In order to be capable of doing that, IoT space must be able to do different human related tasks. One of them is to identify and track multiple objects seamlessly. In the environment where many camera modules are distributed on network, it is important to identify object in order to track it, because different cameras may be needed as object moves throughout the space and IoT space should determine the appropriate one. This paper describes appearance based unknown object tracking with the distributed vision system in IoT space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• The Journal of the Korea Contents Association
• /
• v.15 no.2
• /
• pp.11-20
• /
• 2015

In this paper, we develop an intelligent mobile surveillance system based on binary CDMA for the unmanned automatic tracking and surveillance. That is, we implement a intelligent surveillance system using the binary CDMA wireless communication technology which is applied the merit of CDMA and TDMA on it complexly. This system is able to monitor the site of the accident on network in real time and process the various situations by implementing the security surveillance system. This system pursues an object by the 360-degree using camera, expands image using a PTZ(Pan/Tilt/Zoom) camera zooming function, identifies the mobile objects image within a screen and transfers the identified image to the remote site. Finally, we show the efficiency of the implemented system through the simulation of the controlled situations, such as tracking coverage on objects, object expansion, object detection number, monitoring the remote transferred image, number of frame per second by the image output signal etc..

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2016

Nowadays, there are many research for recognizing face of people using the machine vision. the machine vision is classification and analysis technology using machine that has sight such as human eyes. In this paper, we propose algorithm for classifying human face using this machine vision system. This algorithm consist of Convolutional Neural Network and cascade face detector. And using this algorithm, we classified the face of subjects. For training the face classification algorithm, 2,000, 3,000, and 4,000 images of each subject are used. Training iteration of Convolutional Neural Network had 10 and 20. Then we classified the images. In this paper, about 6,000 images was classified for effectiveness. And we implement the system that can classify the face of subjects in realtime using USB camera.

• Journal of Engineering Education Research
• /
• v.23 no.2
• /
• pp.24-30
• /
• 2020

This paper proposes the approaches to the evaluation of learning using concepts of artificial intelligence. Among various techniques, deep learning algorithm is employed to achieve quantitative results of evaluation. In particular, this paper focuses on the process-based evaluation instead of the result-based one using face expression. The expression is simply acquired by digital camera that records face expression when students solve sample test problems. Face expressions are trained using convolutional neural network (CNN) model followed by classification of expression data into three categories, i.e., easy, neutral, difficult. To substantiate the proposed approach, the simulation results show promising results, and this work is expected to open opportunities for intelligent evaluation system in the future.