• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.291-297
• /
• 2018

In this paper, we present an automatic image object tracking system for Studio cameras on the stage. For object tracking, we use the OpenCV-based Python program using PC, Raspberry Pi 3 and mobile devices. There are many methods of image object tracking such as mean-shift, CAMshift (Continuously Adaptive Mean shift), background modelling using GMM(Gaussian mixture model), template based detection using SURF(Speeded up robust features), CMT(Consensus-based Matching and Tracking) and TLD methods. CAMshift algorithm is very efficient for real-time tracking because of its fast and robust performance. However, in this paper, we implement an image object tracking system for studio cameras based CMT algorithm. This is an optimal image tracking method because of combination of static and adaptive correspondences. The proposed system can be applied to an effective and robust image tracking system for continuous object tracking on the stage in real time.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.623-632
• /
• 2009

In this paper, we propose a pulmonary nodule registration for the tracking of lung nodules in sequential CT scans. Our method consists of following five steps. First, a translational mismatch is corrected by aligning the center of optimal bounding volumes including each segmented lung. Second, coronal maximum intensity projection(MIP) images including a rib structure which has the highest intensity region in baseline and follow-up CT series are generated. Third, rigid transformations are optimized by normalized average density differences between coronal MIP images. Forth, corresponding nodule candidates are defined by Euclidean distance measure after rigid registration. Finally, template matching is performed between the nodule template in baseline CT image and the search volume in follow-up CT image for the nodule matching. To evaluate the result of our method, we performed the visual inspection, accuracy and processing time. The experimental results show that nodules in serial CT scans can be rapidly and correctly registered by coronal MIP-based rigid registration and local template matching.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1630-1642
• /
• 2010

Recently, there is an increasing need for developing the technique of Hand Gesture Recognition (HGR), for vision based interface. Since hand gesture is defined as consecutive change of hand posture, developing the algorithm of Hand Posture Recognition (HPR) is required. Among the factors that decrease the performance of HPR, we focus on rotation factor. To achieve rotation invariant HPR, we propose a method that uses the property of video that adjacent frames in video have high correlation, considering the environment of HGR. The proposed method introduces template update of object tracking using the above mentioned property, which is different from previous works based on still images. To compare our proposed method with previous methods such as template matching, PCA and LBP, we performed experiments with video that has hand rotation. The accuracy rate of the proposed method is 22.7%, 14.5%, 10.7% and 4.3% higher than ordinary template matching, template matching using KL-Transform, PCA and LBP, respectively.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.12
• /
• pp.1259-1266
• /
• 2014

Road signs provide important safety information about road and traffic conditions to drivers. Road signs include not only common traffic signs but also warning information regarding unexpected obstacles and road constructions. Therefore, accurate detection and identification of road signs is one of the most important research topics related to safe driving. In this paper, we propose a 3-D vision technique to automatically detect and track road signs in a video sequence which is acquired from a stereo vision camera mounted on a vehicle. First, color information is used to initially detect the sign candidates. Second, the SVM (Support Vector Machine) is employed to determine true signs from the candidates. Once a road sign is detected in a video frame, it is continuously tracked from the next frame until it is disappeared. The 2-D position of a detected sign in the next frame is predicted by the 3-D motion of the vehicle. Here, the 3-D vehicle motion is acquired by using the 3-D pose information of the detected sign. Finally, the predicted 2-D position is corrected by template-matching of the scaled template of the detected sign within a window area around the predicted position. Experimental results show that the proposed method can detect and track many types of road signs successfully. Tracking comparisons with two different methods are shown.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.79-79
• /
• 2015

현재 홍수 시 유량조사에 가장 많이 사용하고 있는 부자법은 측정 인력, 측정비용 및 위험성이 높다는 단점이 있다. 또한 교량에서 부자를 투하하고 측면에서 부자의 이동을 추적하기 때문에 평면상의 이동에 대한 정보를 얻기 어렵다는 한계가 있다. 이에 김서준 등(2014)은 PTV 기법을 이용한 부자 추적 알고리즘을 개발하였으나 부자가 회전하거나 물속에 잠기는 부분이 변화하여 수면 위로 확인되는 부자의 길이가 변할 경우 추적이 어렵다는 한계가 있었다. 이를 개선하고자 본 연구에서는 Template Match 알고리즘과 색상 기반 영상 처리 기법을 이용한 목표물 인식 방법인 Camshift 기법을 적용하여 부자를 추적할 수 있는 알고리즘을 개발하였다. Template Match 알고리즘의 경우는 입자가 많을수록 추적을 잘한다는 장점이 있지만 회전 및 변형에 취약하다는 단점이 있고, Camshift 영상 처리 기법의 경우 다수의 추적자가 존재할 경우 추적에 어려움이 있으나 추적자의 회전과 변형을 정확하게 추적할 수 있다는 장점이 있다. 따라서 Template Match 알고리즘을 이용하여 이동 예상영역을 결정하고 Camshift 영상 처리 기법으로 추적을 하게되면 두 방법의 장점을 모두 살릴 수 있다. Camshift 영상 처리 기법을 실제 부자 추적에 적용해 본 결과 부자의 회전 및 변형에도 정확하게 추적할 수 있는 것을 확인하였다. 향후 부자법을 이용한 유량 조사에 본 연구에서 개발한 알고리즘을 적용한다면 현장에서 동영상 촬영만 하면 되기 때문에 측정 인원을 최소화 할 수 있어 매우 경제적이고, 홍수 시 위험성도 감소할 것으로 기대된다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.75-83
• /
• 2008

We propose a welfare interface using multiple fecial features tracking, which can efficiently implement various mouse operations. The proposed system consist of five modules: face detection, eye detection, mouth detection, facial feature tracking, and mouse control. The facial region is first obtained using skin-color model and connected-component analysis(CCs). Thereafter the eye regions are localized using neutral network(NN)-based texture classifier that discriminates the facial region into eye class and non-eye class, and then mouth region is localized using edge detector. Once eye and mouth regions are localized they are continuously and correctly tracking by mean-shift algorithm and template matching, respectively. Based on the tracking results, mouse operations such as movement or click are implemented. To assess the validity of the proposed system, it was applied to the interface system for web browser and was tested on a group of 25 users. The results show that our system have the accuracy of 99% and process more than 21 frame/sec on PC for the $320{\times}240$ size input image, as such it can supply a user-friendly and convenient access to a computer in real-time operation.

• Annual Conference of KIPS
• /
• 2000.10a
• /
• pp.247-250
• /
• 2000

본 논문에서는 다양한 배경을 가지는 연속적인 얼굴 영상에서 실시간으로 눈의 위치를 자동적으로 추출하는 방법에 대하여 제시한다. 얼굴 요소 중에서 눈은 얼굴 인식 분야에 있어서 중요한 특징을 나타내는 주 요소로써 주로 히스토그램 분석과 색상 정보를 이용하여 눈 영역의 윤곽을 추출하는 방법이 제기되고 있다. 본 논문에서는 명암의 변화에도 비교적 적응력이 강한 이진화 기법을 사용하여 원영상을 이진화하고, 가변 템플릿(Deformable Template)방법을 사용하여 후보 영역을 추출한다. 이러한 후보영역들은 ART2 신경회로망을 이용하여 병합되며, 병합된 후보 영역들은 얼굴 요소의 기하학적 사전지식을 기반으로 검증되어, 시간에 따라 모양변화가 급변하는 눈 영역에 대한 실시간 추출을 가능하게 한다. 이상의 연구 결과는 교통사고 방지를 위한 눈의 졸림감지 등의 응용 시스템에 이용될 수 있다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.45-56
• /
• 2015

In this paper we propose a very rapid moving object tracking method for an object-based auto focus on a smart phone camera. By considering the limit of non-learning approach on low-performance platforms, we use a sliding-window detection technique based on histogram features. By adapting the integral histogram, we solve the problem of the time-consuming histogram computation on each sub-window. For more speed up, we propose a local candidate search, and an adaptive scaling template method. In addition, we propose to apply a stabilization term in the matching function for a stable detection location. In experiments on our dataset, we demonstrated that we achieved a very rapid tracking performance demonstrating over 100 frames per second on a PC environment.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.810-815
• /
• 2018

The kernelized correlation filter algorithm yielded meaningful results in accuracy for object tracking. However, because of the use of a fixed size template, we could not cope with the scale change of the tracking object. In this paper, we propose a method to track objects by finding the best scale for each frame using correlation filtering response values in multi-scale using nearest neighbor interpolation and Gaussian normalization. The scale values of the next frame are updated using the optimal scale value of the previous frame and the optimal scale value of the next frame is found again. For the accuracy comparison, the validity of the proposed method is verified by using the VOT2014 data used in the existing kernelized correlation filter algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1182-1187
• /
• 2004

Robust, real-time, fully automatic tracking of facial features is required for many computer vision and graphics applications. In this paper, we describe a fully automatic system that tracks eyes and eyebrows in real time. The pupils are tracked using the red eye effect by an infrared sensitive camera equipped with infrared LEDs. Templates are used to parameterize the facial features. For each new frame, the pupil coordinates are used to extract cropped images of eyes and eyebrows. The template parameters are recovered by PCA analysis on these extracted images using a PCA basis, which was constructed during the training phase with some example images. The system runs at 30 fps and requires no manual initialization or calibration. The system is shown to work well on sequences with considerable head motions and occlusions.