• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권4호
• /
• pp.1066-1079
• /
• 2023

Multi-target tracking based on the detector is a very hot and important research topic in target tracking. It mainly includes two closely related processes, namely target detection and target tracking. Where target detection is responsible for detecting the exact position of the target, while target tracking monitors the temporal and spatial changes of the target. With the improvement of the detector, the tracking performance has reached a new level. The problem that always exists in the research of target tracking is the problem that occurs again after the target is occluded during tracking. Based on this question, this paper proposes a DeepSORT model based on SIFT features to improve ship tracking. Unlike previous feature extraction networks, SIFT algorithm does not require the characteristics of pre-training learning objectives and can be used in ship tracking quickly. At the same time, we improve and test the matching method of our model to find a balance between tracking accuracy and tracking speed. Experiments show that the model can get more ideal results.

• 한국멀티미디어학회논문지
• /
• 제15권3호
• /
• pp.336-344
• /
• 2012

객체 인식(recognition)과 추적(tracking)은 컴퓨터 비전의 중요 분야로써 작게는 동작 인식으로부터 크게는 우주 항공까지 그 활용 가능성이 무궁무진하다. 객체 인식의 정확도를 향상시키는 방법 중 하나는 회전, 스케일 그리고 가려짐에 강건한 컬러를 이용하는 것이다. 컬러를 이용함으로써 더 많은 특징점들을 추출하기 위한 계산 비용을 감소시킬 수 있다. 또한, 빠른 객체 인식을 위해 알고리즘의 정확도를 낮추는 것보다 객체의 위치를 예측하고 좀 더 작은 영역에서 인식을 수행하는 것이 더욱 효과적이다. 본 논문은, 인식 정확도를 향상시키기 위해 대표적인 객체 인식 알고리즘인 SURF와 컬러모델을 적용한 기술자(descriptor)를 사용하고, 움직임 예측 알고리즘인 Kalman filter를 결합하여 빠른 객체 추적 방법을 제안한다. 그 결과, 제안하는 방법은 다른 컬러를 갖는 같은 패턴의 객체들을 구분하고, 객체의 향후 움직임을 미리 예측한 관심영역(ROI)에서 인식을 수행함으로써 빠른 추적 결과를 보였다.

• 전기학회논문지
• /
• 제60권8호
• /
• pp.1529-1536
• /
• 2011

Recently, worldwide government policy is pursuing saving energy and preservation. add to this, the solar cells are getting the spotlight nonpolluting energy source, using a variety of products for solar cell. in this paper, we'll make solar tracking system for suitable of dynamic boat. we knew that general boats are using fixed solar cell, it's first time to use tracking system of solar cells for boats so it is hard to application. To solve this problem in this paper we use to a magnetic compass and GPS for suitable solar tracking system of dynamic movement and to analyze fixed and tracking solar system. frist. solar tracking device is designed two-axis control system. one-axis control system is taken a magnetic compass for making efficiency defence solar tracking sensor, two-axis control system apply GPS latitude and longitude data for SPA(Solar position algorithm) so we know the azimuth and altitude. it analyze data value of accuracy comparison from result. so the proposed algorithm confirm to have validity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1287-1300
• /
• 2018

Target-tracking algorithm based on ad hoc camera sensor networks (ACSNs) utilizes the distributed observation capability of nodes to achieve accurate target tracking. A compressed sensing-based multiple-target tracking algorithm (CSMTTA) for ACSNs is proposed in this work based on the study of camera node observation projection model and compressed sensing model. The proposed algorithm includes reconfiguration of observed signals and evaluation of target locations. It reconfigures observed signals by solving the convex optimization of L1-norm least and forecasts node group to evaluate a target location by the motion features of the target. Simulation results show that CSMTTA can recover the subtracted observation information accurately under the condition of sparse sampling to a high target-tracking accuracy and accomplish the distributed tracking task of multiple mobile targets.

• 한국정밀공학회지
• /
• 제15권6호
• /
• pp.175-182
• /
• 1998

An advanced visual tracking and stable grasping algorithm for a moving object is proposed. The stable grasping points for a moving 2D polygonal object are obtained through the visual tracking system with the Kalman filter and image prediction technique. The accuracy and efficiency are improved more than any other prediction algorithms for the tracking of an object. In the processing of a visual tracking. the shape predictors construct the parameterized family and grasp planner find the grasping points of unknown object through the geometric properties of the parameterized family. This algorithm conducts a process of ‘stable grasping and real time tracking’.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권6호
• /
• pp.407-412
• /
• 2015

In model-based tracking, an accurate 3D model of a target object or scene is mostly assumed to be known or given in advance, but the accuracy of the model should be guaranteed for accurate pose estimation. In many application domains, on the other hand, end users are not highly distracted by tracking errors from certain levels of modeling errors. In this paper, we examine perceptual tracking errors, which are predominantly caused by modeling errors, on subjective evaluation and compare them to computational tracking errors. We also discuss the tolerance of modeling errors by analyzing their permissible ranges.

• 제어로봇시스템학회논문지
• /
• 제4권3호
• /
• pp.349-359
• /
• 1998

A robot control scheme for specific application a line-tracking system is newly presented. To improve the performance of line-tracking, robot arm dynamics and torque constraints are incorporated into the control scheme. The tracking problem for the workpiece on a variable-speed conveyor is formulated as an optimal tracking problem with specific criteria. Dividing the conveyor speed into the nominal term and the perturbed term, a two-stage control strategy is employed to cope with the nonlinearity and uncertainty of the robot-conveyor system. Simulation results are given to verify good tracking performance with fast cycle time and high accuracy in a robotic workcell.

• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.344-358
• /
• 2019

Surveillance cameras have installed in many places because security and safety is becoming important in modern society. Through surveillance cameras installed, we can deal with troubles and prevent accidents. However, watching surveillance videos and judging the accidental situations is very labor-intensive. So now, the need for research to analyze surveillance videos is growing. This study proposes an algorithm to track multiple persons using SURF and background subtraction. While the SURF algorithm, as a person-tracking algorithm, is robust to scaling, rotating and different viewpoints, SURF makes tracking errors with sudden changes in videos. To resolve such tracking errors, we combined SURF with a background subtraction algorithm and showed that the proposed approach increased the tracking accuracy. In addition, the background subtraction algorithm can detect persons in videos, and SURF can initialize tracking targets with these detected persons, and thus the proposed algorithm can automatically detect the enter/exit of persons.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.153-156
• /
• 1996

A new filtering algorithm for radar tracking is developed based on the fact that correct evaluation of the measurement error covariance can be made possible by doing it with respect to the Cartesian state vector. The new filter may be viewed as a modification of the extended Kalman filter where the variance of the range measurement errors is evaluated in an adaptive manner. The structure of the proposed filter allows sequential measurement processing scheme to be incorporated into the scheme, and this makes the resulting algorithm favorable in both estimation accuracy and computational efficiency.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.73-77
• /
• 2002

The requirements for higher productivity call for high speed of the machine tool axes. Iron core type linear DC motor is growly accepted far a viable candidate of the high speed machine tool feed unit. LDM, however, has inherent disturbance force components: cogging and force ripple. These disturbance force directly affects tracking accuracy of the carrage and must be eliminated or reduced. Reducing motor ripple, this paper adapted the feed forward compensation method and neural network control. Experiments carried 7ut on the linear motor test setup show that this control methods is usable in order to reduce the motor ripple.