• 융합신호처리학회논문지
• /
• 제18권2호
• /
• pp.68-75
• /
• 2017

본 연구에서는 이동 물체의 색상이 배경 내 색상과 동일하거나 유사한 색상이 존재하는 경우 컬러기반에서 효과적으로 이동 물체의 추적 방법을 다루고 있다. 대표적인 컬러 기반 추적방법인 CamShift 알고리즘은 배경 영상에 이동물체의 색상이 존재하는 경우 불안정한 추적을 보여주고 있다. 이러한 단점을 극복하기 위해 본 논문에서는 물체의 Depth 정보를 병합한 CamShift 알고리즘을 제안하고 있다. Depth 정보 영상의 모든 픽셀의 거리정보를 측정하는 Kinect 장치로부터 구할 수 있다. 실험결과 이동물체의 거리정보를 병합시킨 제안된 추적 방법은 기존 CamShift 알고리즘의 불안정한 추적기능을 보완하였고, CamShift 알고리즘만 사용한 경우와 비교해 볼 때 추적성능을 향상시켰다.

• 디지털산업정보학회논문지
• /
• 제9권1호
• /
• pp.141-150
• /
• 2013

This study proposes technology using Active Shape Model to track the object separating it by depth-sensors. Unlike the common visual camera, the depth-sensor is not affected by the intensity of illumination, and therefore a more robust object can be extracted. The proposed algorithm removes the horizontal component from the information of the initial depth map and separates the object using the vertical component. In addition, it is also a more efficient morphology, and labeling to perform image correction and object extraction. By applying Active Shape Model to the information of an extracted object, it can track the object more robustly. Active Shape Model has a robust feature-to-object occlusion phenomenon. In comparison to visual camera-based object tracking algorithms, the proposed technology, using the existing depth of the sensor, is more efficient and robust at object tracking. Experimental results, show that the proposed ASM-based algorithm using depth sensor can robustly track objects in real-time.

• 전기학회논문지
• /
• 제61권4호
• /
• pp.639-642
• /
• 2012

Optical coherence tomography(OCT) can provide real-time and non-invasive subsurface imaging with ultra-high resolution of micrometer scale. However, conventional OCT systems generally have a limited imaging depth range within a depth of only 1-2 mm. To overcome the limitation, we have proposed an active surface tracking algorithm used in common-path Fourier-domain OCT system in order to extend the imaging depth range. The surface tracking algorithm based on the threshold and Savitzky-Golay filter of A-scan data was applied to real-time tracking. The algorithm has controlled a moving stage according to the sample's surface variance in real time. An OCT image obtained by the algorithm clearly show an extended imaging depth range. Consequently, the proposed algorithm demonstrated the potential for improving the conventional OCT systems with limitary depth range.

• 한국멀티미디어학회논문지
• /
• 제19권4호
• /
• pp.774-779
• /
• 2016

The conventional methods using color signal for tracking the movement of the object require a lot of calculation and the performance is not accurate. In this paper, we propose a method to effectively track the moving objects using the depth information from a depth camera. First, it separates the background and the objects based on the depth difference in the depth of the screen. When an object is moved, the depth value of the object becomes blurred because of the phenomenon of Motion Blur. In order to solve the Motion Blur, we observe the changes in the characteristics of the object (the area of the object, the border length, the roundness, the actual size) by its velocity. The proposed algorithm was implemented in the simulation that was applied directly to the tracking of a golf ball. We can see that the estimated value of the proposed method is accurate enough to be very close to the actual measurement.

• 디지털산업정보학회논문지
• /
• 제4권2호
• /
• pp.15-19
• /
• 2008

In this paper, we propose a new algorithm of image depth detection using motion estimation and object tracking. In industry, robots are used for automobile, conveyer system, etc. But, these have much necessary time. Thus, in this paper, we develop the efficient method of image depth detection based on motion estimation and object tracking.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1121-1141
• /
• 2020

We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark.

• 한국기계가공학회지
• /
• 제20권4호
• /
• pp.66-72
• /
• 2021

Since the behavior of an autonomous underwater vehicle (AUV) is influenced by disturbances and moments that are not accurately known, the depth control law of AUVs must have the ability to track the input signal and to reject disturbances simultaneously. Here, we proposed robust tracking control for controlling the depth of an AUV. An augmented closed-loop system is represented by an error dynamic equation, and we can easily show the asymptotic stability of the overall system by using a Lyapunov function. The robust tracking controller is consisted of the internal model of the command signal and a state feedback controller, and it has the ability to track the input signal and reject disturbances. The closed-loop control system is robust to parameter uncertainties. Simulation results showed the control performance of the robust tracking controller to be better than that of a P + PD controller.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.131-139
• /
• 2016

Recognition of human motions has become a main area of computer vision due to its potential human-computer interface (HCI) and surveillance. Among those existing recognition techniques for human motions, head detection and tracking is basis for all human motion recognitions. Various approaches have been tried to detect and trace the position of human head in two-dimensional (2D) images precisely. However, it is still a challenging problem because the human appearance is too changeable by pose, and images are affected by illumination change. To enhance the performance of head detection and tracking, the real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor are recently used. In this paper, we propose an effective feature extraction method, called adaptive local binary pattern (ALBP), for depth image based applications. Contrasting to well-known conventional local binary pattern (LBP), the proposed ALBP cannot only extract shape information without texture in depth images, but also is invariant distance change in range images. We apply the proposed ALBP for head detection and tracking in depth images to show its effectiveness and its usefulness.

• 한국멀티미디어학회논문지
• /
• 제15권8호
• /
• pp.963-976
• /
• 2012

'제스처'는 음성을 제외한 가장 직관적인 인간의 의사표현 수단이다. 그에 따라 제스처를 이용하여 컴퓨터를 제어하는 방법에 대한 많은 연구가 진행되고 있다. 이러한 연구에서 사용자를 검출하고 추적하는 방법은 매우 중요한 과정 중의 하나이다. 기존의 2차원 객체 검출 및 추출 방법은 조명이나 주변 환경의 변화에 민감하고, 2차원과 3차원 정보의 혼합사용 방법은 연산량이 많다는 단점이 있다. 또한 3차원 정보를 이용한 기존 방법들은 유사한 깊이의 객체 분할이 불가능하다. 따라서 본 논문에서는 깊이 정보의 누적 값인 Depth Projection Map (DPM)과 움직임 정보를 이용하여 객체를 검출하고 추적하는 방법을 제안한다. 실험 결과 제안 방법은 조명이나 환경변화에 강인하고, 연산속도가 빠르며, 유사한 깊이의 물체도 잘 검출하고 추적할 수 있음을 확인하였다.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.707-720
• /
• 2014

This paper proposes a face tracking scheme that is a combination of a face detection algorithm and a face tracking algorithm. The proposed face detection algorithm basically uses the Adaboost algorithm, but the amount of search area is dramatically reduced, by using skin color and motion information in the depth map. Also, we propose a face tracking algorithm that uses a template matching method with depth information only. It also includes an early termination scheme, by a spiral search for template matching, which reduces the operation time with small loss in accuracy. It also incorporates an additional simple refinement process to make the loss in accuracy smaller. When the face tracking scheme fails to track the face, it automatically goes back to the face detection scheme, to find a new face to track. The two schemes are experimented with some home-made test sequences, and some in public. The experimental results are compared to show that they outperform the existing methods in accuracy and speed. Also we show some trade-offs between the tracking accuracy and the execution time for broader application.