• 한국멀티미디어학회논문지
• /
• 제20권6호
• /
• pp.893-910
• /
• 2017

In this paper, we propose a simple online multiple object (human) tracking method, LKDeep (Lucas-Kanade feature and Detection based Simple Online Multiple Object Tracker), which can run in fast online enough on CPU core only with acceptable tracking performance for embedded surveillance purpose. The proposed LKDeep is a pragmatic hybrid approach which tracks multiple objects (humans) mainly based on LK features but is compensated by detection on periodic times or on necessity times. Compared to other state-of-the-art multiple object tracking methods based on 'Tracking-By-Detection (TBD)' approach, the proposed LKDeep is faster since it does not have to detect object on every frame and it utilizes simple association rule, but it shows a good object tracking performance. Through experiments in comparison with other multiple object tracking (MOT) methods using the public DPM detector among online state-of-the-art MOT methods reported in MOT challenge [1], it is shown that the proposed simple online MOT method, LKDeep runs faster but with good tracking performance for surveillance purpose. It is further observed through single object tracking (SOT) visual tracker benchmark experiment [2] that LKDeep with an optimized deep learning detector can run in online fast with comparable tracking performance to other state-of-the-art SOT methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.597-600
• /
• 1999

In this paper, we propose a fast object-tracking algorithm in a moving picture. The proposed object-tracking algorithm is based on a projection scheme. More specifically, to alleviate the computational complexities of the previous motion estimation methods, we propose to use the projected row and column 1-D image data to extract the motion information. Experimental results show that the proposed method can detect the motion of an object fairly well with reduced computational time.

• Journal of information and communication convergence engineering
• /
• 제5권1호
• /
• pp.12-16
• /
• 2007

In this paper, a new method is proposed for tracking the direction-of-arrival (DOA) of the wideband moving source incident on uniform linear array sensors. DOA is estimated by focusing transformation matrices. To update focusing matrices along with new data snap shots, we use the FAST (Fast Approximate Subspace Tracking) method. Present focusing matrices are constructed by previous signal and its orthogonal basis vectors as well as present signal and its orthogonal basis vectors, which are the left and right singular vectors of the inner product of two approximated matrices. Simulation results are shown to illustrate the performance of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.135-135
• /
• 2001

In recent years there have been increasing interests in real-time object tracking with image information. Since image information is affected by illumination, this paper presents the real-time object tracking method based on neural networks that have robust characteristics under various illuminations. This paper proposes three steps to track the object and the fast tracking method. In the first step the object color is extracted using neural networks. In the second step we detect the object feature information based on invariant moment. Finally the object is tracked through a shape recognition using neural networks. To achieve the fast tracking performance, we have a global search for entire image and then have tracking the object through local search when the object is recognized.

• 대한원격탐사학회지
• /
• 제37권1호
• /
• pp.1-11
• /
• 2021

This study measures the change of ice flow velocity of David Glacier, one of the fast-moving glaciers in East Antarctica that drains through Drygalski Ice Tongue. In order to effectively observe the rapid flow velocity, we applied the offset tracking technique to Sentinel-1A SAR images obtained from 2016 to 2020 with 36-day temporal baseline. The resulting velocity maps were averaged and the two relatively fast points (A1 and A2) were selected for further time-series analysis. The flow velocity increased during the Antarctic summer (around December to March) over the four years' observation period probably due to the ice surface melting and reduced friction on the ice bottom. Bedmap2 showed that the fast flow velocities at A1 and A2 are associated with a sharp decrease in the ice surface and bottom elevation so that ice volumetric cross-section narrows down and the crevasses are being created on the ice surface. The local maxima in standard deviation of ice velocity, S1 and S2, showed random temporal fluctuation due to the rotational ice swirls causing error in offset tracking method. It is suggested that more robust offset tracking method is necessary to incorporate rotational motion.

• 전기학회논문지
• /
• 제60권7호
• /
• pp.1331-1338
• /
• 2011

This paper proposes a method for frequency control of islanded microgrid with battery energy storage system. For frequency control of islanded microgrid, battery energy storage system uses a phase locked loop algorithm with positive sequence components for a fast frequency estimation. Microgrid is a power system with small inertia because it has small capacity generators and inverter systems for renewable energy. So, Islanded microgrid's frequency varies fast and large as small generation and load changes. To reduce frequency variation of islanded microgrid, it needs a device with fast frequency response. For fast frequency response, a fast frequency tracking is important. To show the validation of proposed fast frequency tracking algorithm, battery energy storage system with proposed algorithm is tested in microgrid pilot plant.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.191-196
• /
• 2003

This paper presents a method to design an adaptive controller for the kinematic model of a two-wheeled welding mobile robot (WMR) with unknown parameters. We propose a nonlinear controller based on the Lyapunov function to enhance the tracking properties of the WMR. The WMR can track any smooth curved welding path at a constant velocity of the welding point. The system has three degrees of freedom including two wheels and one torch slider. Torch slider motion is used for fast tracking. To design the tracking performance, the errors from WMR to steel wall is defined, and the controller is designed to drive the errors to zero as fast as possible. The effectiveness of the proposed controller is shown through simulation results.

• Journal of Electrical Engineering and information Science
• /
• 제3권2호
• /
• pp.230-238
• /
• 1998

When size and shape of moving object have been changed, a correlator often accumulates walk-off error. A success of correlation-based tracking largely depends on choosing suitable window size and position and thus transferring the proper reference image to the next frame. For this, we propose the Adaptive Window Algorithm with Four-Direction Sizing Factors (AWA-FSF) for fast adjusting a reference region to enhance reliability of correlation-based image tracking in complex cluttered environments. Since the AWA-FSF is capable of adjusting a reference image size more rapidly and properly, we can minimize the influence of complex background and clutter. In addition, we can finely tune the center point of the reference image repeatedly after main tracking process. Thus we have increased stability and reliability of correlation-based image tracking. We tested performance of the AWA-FSF using 45 real image sequences made of over 3400 images and had the satisfied results for most of them.

• 한국컴퓨터정보학회논문지
• /
• 제22권7호
• /
• pp.47-54
• /
• 2017

Recently, correlation filter based trackers have shown excellent tracking performance and computational efficiency. In order to enhance tracking performance in the correlation filter based tracker, search area which is image patch for finding target must include target. In this paper, two methods to discriminatively represent target in the search area are proposed. Firstly, search area location is estimated using pyramidal Lucas-Kanade algorithm. By estimating search area location before filtering, fast motion target can be included in the search area. Secondly, we investigate multi-channel Local Edge Pattern(LEP) which is insensitive to illumination and noise variation. Qualitative and quantitative experiments are performed with eight dataset, which includes ground truth. In comparison with method without search area estimation, our approach retain tracking for the fast motion target. Additionally, the proposed multi-channel LEP improves discriminative performance compare to existing features.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2358-2361
• /
• 2001

In recent years there have been increasing interests in real-time object tracking with image information. Since image information is affected by illumination, this paper presents the real-time object tracking method based on neural networks which have robust characteristics under various illuminations. This paper proposes three steps to track the object and the fast tracking method. In the first step the object color is extracted using neural networks. In the second step we detect the object feature information based on invariant moment. Finally the object is tracked through a shape recognition using neural networks. To achieve the fast tracking performance, this paper first has a global search of entire image and tracks the object through local search when the object is recognized.