• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2005년도 추계학술대회 논문집
• /
• pp.209-212
• /
• 2005

This paper describes detection and tracking of a moving object for unmanned visual surveillance. security systems. Using images obtained from camera it detects and tracks a moving object and displays bounding box enclosing the moving object. The algorithm for detection and tracking is tested using a personal computer, and then implemented on EMPOS II embedded system. Simulation results show that the tracking of a moving object based on embedded system is working well. However it needs to improve image acquisition time for real time implementation to apply security systems.

• ETRI Journal
• /
• 제39권2호
• /
• pp.151-162
• /
• 2017

With the remarkable growth in rich media in recent years, people are increasingly exposed to visual information from the environment. Visual information continues to play a vital role in rich media because people's real interests lie in dynamic information. This paper proposes a novel discrete dynamic swarm optimization (DDSO) algorithm for video object tracking using invariant features. The proposed approach is designed to track objects more robustly than other traditional algorithms in terms of illumination changes, background noise, and occlusions. DDSO is integrated with a matching procedure to eliminate inappropriate feature points geographically. The proposed novel fitness function can aid in excluding the influence of some noisy mismatched feature points. The test results showed that our approach can overcome changes in illumination, background noise, and occlusions more effectively than other traditional methods, including color-tracking and invariant feature-tracking methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.434-436
• /
• 2006

In a visual driver-assistance system, separating moving objects from fixed objects are an important problem to maintain multiple hypothesis for the state. Color and edge-based tracker can often be "distracted" causing them to track the wrong object. Many researchers have dealt with this problem by using multiple features, as it is unlikely that all will be distracted at the same time. In this paper, we improve the accuracy and robustness of real-time tracking by combining a color histogram feature with a brightness of Optical Flow-based feature under a Sequential Monte Carlo framework. And it is also excepted from Tracking as time goes on, reducing density by Adaptive Particles Number in case of the fixed object. This new framework makes two main contributions. The one is about the prediction framework which separating moving objects from fixed objects and the other is about measurement framework to get a information from the visual data under a partial occlusion.

• 제어로봇시스템학회논문지
• /
• 제9권12호
• /
• pp.1033-1041
• /
• 2003

A new visual tracking scheme is proposed for a mobile robot that tracks a moving object in 3D space in real time. Visual tracking is to control a mobile robot to keep a moving target at the center of input image at all time. We made it possible by simplifying the relationship between the 2D image frame captured by a single camera and the 3D workspace frame. To precisely calculate the input vector (orientation and distance) of the mobile robot, the speed vector of the target is determined by eliminating the speed component caused by the camera motion from the speed vector appeared in the input image. The problem of temporary disappearance of the target form the input image is solved by selecting the searching area based on the linear prediction of target motion. The experimental results have shown that the proposed scheme can make a mobile robot successfully follow a moving target in real time.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1524-1529
• /
• 2005

Particle filter is a kind of conditional density propagation model. Its similar characteristics to both selection and mutation operator of evolutionary strategy (ES) due to its Bayesian inference rule structure, shows better performance than any other tracking algorithms. When a new object is entering the region of interest, particle filter sets which have been swarming around the existing objects have to move and track the new one instantaneously. Moreover, there is another problem that it could not track multiple objects well if they were moving away from each other after having been overlapped. To resolve reinitialization problem, we use competitive-AVQ algorithm of neural network. And we regard interfarme difference (IFD) of background images as potential field and give priority to the particles according to this IFD to track multiple objects independently. In this paper, we showed that the possibility of real-time object tracking as intelligent interfaces by simulating the deformable contour particle filters.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.70.1-70
• /
• 2001

Recently, research of visual control is getting more essential in robotic application, and acquiring 3D informations from the 2D images is becoming more important with development of vision system. For this application, we propose the effective way of controlling stereo vision tracking system for target tracking and calculating distance between target and camera. In this paper we address improved controller using dual-loop visual servo which is more effective compared with using single-loop visual servo for stereo vision tracking system. The speed and the accuracy for realizing a real time tracking are important. However, the vision processing speed is too slow to track object in real time by using only vision feedback data. So we use another feedback data from controller parts which offer state feedback ...

• 한국컴퓨터정보학회논문지
• /
• 제29권2호
• /
• pp.79-86
• /
• 2024

본 논문에서는 단일 영역 정보만을 활용하는 기존의 방법론을 개선하기 위해, 물체의 맥락영역에 대한 정보를 함께 물체 추적에 활용하는 새로운 기법을 제시한다. 기존의 방법론들은 모든 후보 영역들을 독립적으로 처리하는 구조로, 비슷한 외양의 영역들이 등장하는 경우 이를 성공적으로 구분하지 못하는 문제점을 보여주었다. 이는 주어진 장면 내에 등장하는 모든 후보 물체 영역들에 대한 맥락 정보를 고려하지 못하여 생기는 문제이다. 제안하는 방법론에서는 비슷한 외양의 영역들 간의 특징점 정보 교환을 보조하고 이들 간의 구별성을 높이는 것을 목표로 하였다. 이를 구현하기 위해 MLP-믹서 (MLP-Mixer) 모델을 활용하여 맥락영역 간의 정보 교환을 모델링하는 모듈을 제시하였다. 이를 통해 구현된 특징점 채널별, 영역간의 상호작용 연산은 영역의 개별 특징점 표현에 대해 장면 맥락 정보가 내장될 수 있도록 보조한다. 제안한 방법론의 성능을 평가하기 위해 대규모 물체 추적 데이터셋인 LaSOT을 사용하였고, 성능 평가 결과 제안한 알고리즘은 AUC 지표 기준 0.560의 높은 성능과 함께 65fps의 실시간 속도로 동작함을 확인하였다.

• 한국정보전자통신기술학회논문지
• /
• 제2권1호
• /
• pp.23-28
• /
• 2009

히스토그램에 의한 객체 유형 인식 방법은 최근 들어 많은 연구가 이루어지고 있다. 그러나 대부분의 히스토그램 기반의 객체 추적이 칼라 모델을 사용하여 견실성을 개선하였지만 아직 충분히 견실하다고 할 수 없다. 이러한 단점을 보안하기 위하여 본 논문에서는 연속적인 프레임에서 히스토그램을 이용하여 객체를 표현하고 추적하는 방법을 제시하고자 한다. 자동차를 대상으로 실험한 결과 80m 거리 이내에서 신뢰성 있는 방법임을 확인하였다.

• 한국통신학회논문지
• /
• 제34권3C호
• /
• pp.274-278
• /
• 2009

히스토그램에 의한 객체 유형 인식 방법은 최근 들어 많은 연구가 이루어지고 있다. 그러나 대부분의 히스토그램 기반의 객체 추적이 칼라 모델을 사용하여 견실성을 개선하였지만 아직 충분히 견실하다고 할 수 없다. 이러한 단점을 보안하기 위하여 본 논문에서는 연속적인 프레임에서 히스토그램을 이용하여 객체를 표현하고 추적하는 방법을 제시하고자 한다. 자동차를 대상으로 실험한 결과 80m 거리 이내에서 신뢰성 있는 방법임을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.167-177
• /
• 2019

Even though so much progresses have been achieved in Multiple Object Tracking (MOT), most of reported MOT methods are not still satisfactory for commercial embedded products like Pan-Tilt-Zoom (PTZ) camera. In this paper, we propose a real-time multiple pedestrians tracking method for embedded environments. First, we design a new light weight convolutional neural network(CNN)-based pedestrian detector, which is constructed to detect even small size pedestrians, as well. For further saving of processing time, the designed detector is applied for every other frame, and Kalman filter is employed to predict pedestrians' positions in frames where the designed CNN-based detector is not applied. The pose orientation information is incorporated to enhance object association for tracking pedestrians without further computational cost. Through experiments on Nvidia's embedded computing board, Jetson TX2, it is verified that the designed pedestrian detector detects even small size pedestrians fast and well, compared to many state-of-the-art detectors, and that the proposed tracking method can track pedestrians in real-time and show accuracy performance comparably to performances of many state-of-the-art tracking methods, which do not target for operation in embedded systems.