• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2911-2916
• /
• 2015

The CCTV is limited by weather conditions. To overcome this limitation, we develop a monitoring program that can sense the approach or recede of two or more objects within a surveillance system that uses a continuous-wave (CW) Doppler radar, and we proposed an algorithm to efficiently detect the approach or recede information of the object. The proposed algorithm separates the signal received by the CW Doppler radar into the real and imaginary parts using Fast Fourier Transform (FFT), and sums the amplitudes for each frequency to determine whether the objects are approaching or receding, using their locations. The algorithm is verified by simulations and experiments, which confirms that it successfully detects the approach or recede of two objects.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.209-214
• /
• 2018

The subway, which is an urban railway, is the core of public transportation. Urban railways are always exposed to serious problems such as theft, crime and terrorism, as many passengers use them. Especially, due to the nature of urban railway environment, the scope of surveillance is widely dispersed and the range of surveillance target is rapidly increasing. Therefore, it is difficult to perform comprehensive management by passive surveillance like existing CCTV. In this paper, we propose the implementation, design method and object recognition algorithm for intelligent object recognition system in urban railway. The object recognition system that we propose is to analyze the camera images in the history and to recognize the situations where there are objects in the landing area and the waiting area that are not moving for more than a certain time. The proposed algorithm proved its effectiveness by showing detection rate of 100% for Selected area detection, 82% for detection in neglected object, and 94% for motionless object detection, compared with 84.62% object recognition rate using existing Kalman filter.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.227-228
• /
• 2013

본 논문에서는 연속적으로 입력되는 스테레오 입체 영상으로부터 2차원과 3차원의 특징을 결합하여 군집화함으로써 대상 물체를 보다 강건하게 분할하는 기법을 제안한다. 제안된 방법에서는 촬영된 장면의 좌우 영상으로부터 스테레오 정합 알고리즘을 이용해 영상의 각 화소별로 카메라와 물체 사이의 거리를 나타내는 깊이 특징을 추출한다. 그런 다음, 깊이와 색상 특징을 효과적으로 군집화하여 배경에 해당하는 영역을 제외하고, 전경에 해당하는 대상 물체를 감지한다. 실험에서는 제안된 방법을 여러가지 영상에 적용하여 테스트를 해 보았으며, 제안된 방법이 기존의 2차원 기반의 물체 분리 방법에 비해 보다 강건하게 대상물체를 분할함을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.664-666
• /
• 1999

영상 추적(visual tracking)은 로봇의 시각기반제어, 교통정보시스템, 무인감시시스템 등 다양한 분야에 적용 가능하기 때문에 지정된 혹은 운동이 감지된 물체를 지속적이고 빠르게 추적하는 데 목적을 둔다. 이 때 어려운 문제 중 하나는 시간이 지나면서 위치이동은 물론 회전에 와해 물체의 모양이 변한다는 것이다. 이에 본 논문에서는 물체의 3차원 회전에 대응 가능한 실시간 영상추적 알고리듬을 제안한다. 이 알고리듬은 SSD(sum-of-squared differences)를 기반으로 하되, 물체의 배경이 바뀔 때나 물체가 영상추적 윈도우보다 작은 경우에도 추적이 가능하고 3차원 회전에 대응 가능하다. 이것은 3차원 회전으로 인하여 추적목표를 잃어버리는 것을 막기 위하여 기준 영역이 회전할 때 제안된 성능지수에 따라 영상추적 영역과 기준 영상을 새롭게 설정해줌으로써 구현된다. 제안된 알고리듬은 PC기반 실시간 시각시스템에서 성공적으로 실험되었다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.897-906
• /
• 2017

Projection Mapping, also known as Spatial Augmented Reality(SAR) has attracted much attention recently and used for many division, which can augment physical objects with projected various virtual replications. However, conventional approaches towards projection mapping have faced some limitations. Target objects' geometric transformation property does not considered, and movements of flexible objects-like paper are hard to handle, such as folding and bending as natural interaction. Also, precise registration and tracking has been a cumbersome process in the past. While there have been many researches on Projection Mapping on static objects, dynamic projection mapping that can keep tracking of a moving flexible target and aligning the projection at interactive level is still a challenge. Therefore, this paper propose a new method using Unity3D and ARToolkit for high-speed robust tracking and dynamic projection mapping onto non-rigid deforming objects rapidly and interactively. The method consists of four stages, forming cubic bezier surface, process of rendering transformation values, multiple marker recognition and tracking, and webcam real time-lapse imaging. Users can fold, curve, bend and twist to make interaction. This method can achieve three high-quality results. First, the system can detect the strong deformation of objects. Second, it reduces the occlusion error which reduces the misalignment between the target object and the projected video. Lastly, the accuracy and the robustness of this method can make result values to be projected exactly onto the target object in real-time with high-speed and precise transformation tracking.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.97-107
• /
• 2017

In the field of automatic door, the infrared rays and microwave sensor are much used as the important components in charge of the motor's operation control of open and close through the incoming signal of object recognition. In case of existing system that the sensor of the infrared rays and microwave are applied to the automatic door, there are many malfunctions by the infrared rays and visible rays of the sun. Because the automatic doors are usually installed outside of building in state of exposure. The environmental change by temperature difference occurs the noise of object recognition detection signal. With this problem, the hardware fault that the detection sensor is unable to follow the object moving rapidly within detection area makes the sensing blind spot. This fault should be improved as soon as possible. Because It influences safety of passengers who use the automatic doors. This paper conducted an experiment to improve the detection area by installing extra ultrasonic sensor besides existing detection sensor. So, this paper realize the computing circuit and detection algorithm which can correctly and rapidly process the access route of objects moving fast and the location area of fixed obstacles by applying detection and advantages of ultrasonic signal to the automatic doors. With this, It is proved that the automatic door applying ultrasonic sensor is improved detection area of blind spot sensing through field test and improvement plan is proposed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.901-904
• /
• 2012

In this paper, we proposed the context-aware system which can estimate the information on the objects and transmit video information by utilizing multi-sensors. The proposed system is to reduce the excessive video information from a system capturing videos outdoor. This system uses the human-detect sensor attached on the multi-sensor board and four ultrasonic sensor to measure the object's size and movement speed, to recognize the human body's information, and finally to send videos. In order to assess the performance of the context-aware system based on the multi sensor, a comparison has been made between video system and human-detect sensor. As a result, The body human-detect sensor had more reliable images and transmitted information more effectively than when the images were sent by server without sensors attached.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2022

Although 2D Object detection has been largely improved in the past years with the advance of deep learning methods and the use of large labeled image datasets, 3D object detection from 2D imagery is a challenging problem in a variety of applications such as robotics, due to the lack of data and diversity of appearances and shapes of objects within a category. Google has just announced the launch of Objectron that has a novel data pipeline using mobile augmented reality session data. However, it also is corresponding to 2D-driven 3D object detection technique. This study explores more mature 2D object detection method, and applies its 2D projection to Objectron 3D lifting system. Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a stochastic representation of object regions using Gaussian distributions. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a stochastic Intersection-over-Union. Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in available datasets. Thus, less accuracy problem that is one of several limitations of Objectron can be relaxed.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.168-173
• /
• 2018

To overcome the problems of the existing black box which is exposed to the risk of blind spots in the imaging of a fixed front and rear views of an object, this paper suggests a new intelligent black box that can detect and shoot side views of an object. This paper proposes an algorithm of the intelligent black box with a rotating function in order to compensate for the side blind spot of the vehicle. This intelligent black box with rotating screen adopts the infrared distance sensor to sense an object which approaches to the vehicle and rotates automatically towards the object.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.364-368
• /
• 2018

In this paper, we use Faster R-CNN that is one of object detection algorithm and OpenCV that purposes computer vision, to implement the system that can detect danger when a vehicle attempts to change lanes into its own lane in videos of highway, national road, general road and etc. Also, the performance of implemented system is evaluated to prove that the performance is not bad.