• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.64-72
• /
• 2007

In this paper we proposed a combined active contour model and motion estimation-based object tracking technique. After assigning the initial contour, we find the object's boundary and update the initial contour by using object's motion information. In the following frames, similar snake algorithm is repeated to make continuously estimated object's region. The snake algerian plays a role in separating the object from background, while motion estimation provides object's moving direction and displacement. The proposed algorithm provides equivalently stable, robust, tracking performance with significantly reduced amount of computation, compared with the existing shape model-based algorithms.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.192-199
• /
• 2020

Recently, the utilization of the object tracking algorithm based on the deep learning model is increasing. A system for tracking multiple objects in an image is typically composed of a chain form of an object detection algorithm and an object tracking algorithm. However, chain-type systems composed of several modules require a high performance computing environment and have limitations in their application to actual applications. In this paper, we propose a method that enables real-time operation in low-performance computing environment by adjusting the computational process of object detection module in the object detection-tracking chain type system.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.386-393
• /
• 2012

In this paper, we propose an efficient multi-object recognition and tracking scheme based on interest points of objects and their feature descriptors. To do that, we first define a set of object types of interest and collect their sample images. For sample images, we detect interest points and construct their feature descriptors using SURF. Next, we perform a statistical analysis of the local features to select representative points among them. Intuitively, the representative points of an object are the interest points that best characterize the object. in addition, we make the movement vectors of the interest points based on matching between their SURF descriptors and track the object using these vectors. Since our scheme treats all the objects independently, it can recognize and track multiple objects simultaneously. Through the experiments, we show that our proposed scheme can achieve reasonable performance.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2017.11a
• /
• pp.327-328
• /
• 2017

본 논문에서는 사회재난 안전사고 중 수상 안전사고를 예방 및 사고 발생시 즉각 대응을 위한 센서 융복합 상황인지 기술을 개발하였다. 실제 현장에서의 위험상황을 전문가 컨설팅을 통하여 정의하였으며 이를 영상 분석을 이용한 객체의 검출 및 객체의 추적을 통한 위험상황 검출을 개발하였다. 기존 패턴인식 기술에 비하여 우수한 성능을 보이는 인공지능 기반 딥러닝 기술을 적용하였으며 딥러닝 기술을 적용하기 위하여는 많은 수의 데이터베이스 확보가 필수적이고 이를 위하여 기존 데이터베이스의 확보 및 현장에서의 실제 데이터베이스 구축을 위한 작업을 통하여 충분한 데이터베이스를 확보하였다. 객체 검출은 최적의 속도를 확보하기 위하여 SSD 구조를 이용하였으며 객체 추적을 위해서는 Re-identification 기법을 적용하여 Tied convolution 구조를 이용하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.1
• /
• pp.32-41
• /
• 2008

The moving object tracking in vision based observation using video uses difference method between GMM(Gaussian Mixture Model) based background and present image. In the case of racking object using binary image made by threshold, the object is merged not by object information but by Cast-Shadow. This paper proposed the method that eliminates Cast-Shadow using backpropagation Neural Network. The neural network is trained by abstracting feature value form training image of object range in 10-movies and Cast-Shadow range. The method eliminating Cast-Shadow is based on the method distinguishing shadow from binary image, its Performance is better(16.2%, 38.2%, 28.1%, 22.3%, 44.4%) than existing Cast-Shadow elimination algorithm(SNP, SP, DNM1, DNM2, CNCC).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.4C
• /
• pp.401-410
• /
• 2007

In this paper, we propose water quality monitoring system using vision camera and multiple objects tracking method. The proposed system analyzes object individually using vision camera unlike monitoring system using sensor method. The system using vision camera consists of individual object segmentation part and objects tracking part based on interrelation between successive frames. For real-time processing, we make background image using non-parametric estimation and extract objects using background image. If we use non-parametric estimation, objects extraction method can reduce large amount of computation complexity, as well as extract objects more effectively. Multiple objects tracking method predicts next motion using moving direction, velocity and acceleration of individual object then carries out tracking based on the predicted motion. And we apply exception handling algorithms to improve tracking performance. From experiment results under various conditions, it shows that the proposed system can be available for real-time water quality monitoring system since it has very short processing time and correct multiple objects tracking.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.455-458
• /
• 2002

분기를 가지는 대상객체에 대한 가상 네비게이션 시 네비게이션 경로를 지정하기 위하여 일반적으로 반복적인 형태학적 연산(Iterative Morphological Operation)중 세선화(thining)연산을 기반으로 한 골격화(skeletonization)기법들이 널리 사용되었다. 이러한 방법은 반복적인 세선화 연산 수행과정을 거쳐야하므로 수행효율성이 떨어지고, 잡음에 의하여 잘못된 경로를 생성하기 쉽다. 본 연구에서 수행효율성을 개선하고, 잡음에 안정적으로 네비게이션 경로를 추적하기 위하여 영역 중심점 선형 보간 기법을 기반으로 한 네비게이션 경로추적 기법을 제안한다. 본 제안 기법에서는 2 차원 영상 분할 후, 분할 영상에 대한 영역의 수와 영역 중심점을 기반으로 분기위치를 추적하고, 분기영역에서의 영역 중심점 선명 보간을 통하여 자연스러운 네비게이션 경로를 생성한다.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.5
• /
• pp.397-408
• /
• 2021

The construction industry has the highest occupational accidents/injuries and has experienced the most fatalities among entire industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. A long-time monitoring surveillance system causes high physical fatigue and has limitations in grasping all accidents in real-time. Therefore, this study aims to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple object tracking with instance segmentation. To evaluate the system's performance, we utilized the Microsoft common objects in context and the multiple object tracking challenge metrics. These results prove that it is optimal for efficiently automating monitoring surveillance system task at construction sites.

• Journal of Satellite, Information and Communications
• /
• v.7 no.1
• /
• pp.134-138
• /
• 2012

In this paper, we implement the real-time status monitoring system to surveil the object in the automation manufacturing facilities and we propose the CCTV video tracking system using the video tracking filter to improve efficiency. To surveil the object in automation manufacturing facilities, we implement monitoring SW on the based of the video tracking filter instead of the general method for the video monitoring so the reliable monitoring based on the PC is possible efficiently. In addition, accessibility and convenience for administrator are improved as the real-time status confirmation function. Also, we conform the performance improvement effect through the performance analysis of the proposed monitoring system using the video tracking filter.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.448-450
• /
• 2012

본 논문에서는 Kinect 방식의 RGB-D 영상센서를 사용하여, 깊이(Depth) 영상으로부터 3차원 객체의 기하정보를 표현하는 표면 정규 벡터(Surface Normal Vector)를 추출하고, 그 결과를 영상화하는 방법을 제안하며, 제안된 방법으로 생성된 영상으로부터 깊이 영상의 특징점 및 특징 기술자를 추출하여 3차원 객체 인식 성능을 향상시키는 방법을 제안한다. 또한 생성된 RGB-D 특징 기술자들을 객체 단위로 구분 가능한 코드북(CodeBook) 학습을 통한 인식방법을 제안하여 객체의 인식 성능을 높이는 방법을 제안한다. 제안하는 RGB-D 기반의 특징 추출 및 학습 방법은 텍스쳐 유무, 카메라 회전 및 이동 변화 등의 환경변화에 강건함을 실험적으로 증명하였으며, 이 방법은 Kinect 방식의 RGB-D 영상을 사용하는 3차원 객체/공간 인식 및 추적, 혹은 이를 응용하는 증강현실 시스템에 적용하여 사용될 수 있다.