• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• 한국전자통신학회논문지
• /
• 제18권6호
• /
• pp.1109-1116
• /
• 2023

객체 추적은 영상의 첫 번째 프레임에서 annotation으로 제공되는 좌표 정보를 활용하여 비디오 시퀀스의 목표 추적에 활용된다. 본 논문에서는 객체 추적 정확도 향상을 위해 심층 특징과 영역 추론 모듈을 결합한 추적 알고리즘을 제안한다. 충분한 객체 정보를 획득하기 위해 Convolution Neural Network를 Siamese Network 구조로 네트워크를 설계하였다. 객체의 영역 추론을 위해 지역 제안 네트워크와 중첩 신뢰도 모듈을 적용하여 추적에 활용하였다. 제안한 추적 알고리즘은 Object Tracking Benchmark 데이터셋을 사용하여 성능검증을 수행하였고, Success 지표에서 69.1%, Precision 지표에서 89.3%를 달성하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권4호
• /
• pp.344-365
• /
• 2009

The performance of a tracking system is greatly increased if multiple types of sensors are combined to achieve the objective of the tracking instead of relying on single type of sensor. To conduct the multi-modal tracking, we have previously developed a multi-modal sensor-based tracking model where acoustic sensors mainly track the objects and visual sensors compensate the tracking errors [1]. In this paper, we find a network synchronization problem appearing in the developed tracking system. The problem is caused by the different location and traffic characteristics of multi-modal sensors and non-synchronized arrival of the captured sensor data at a processing server. To effectively deliver the sensor data, we propose a time-based packet aggregation algorithm where the acoustic sensor data are aggregated based on the sampling time and sent to the server. The delivered acoustic sensor data is then compensated by visual images to correct the tracking errors and such a compensation process improves the tracking accuracy in ideal case. However, in real situations, the tracking improvement from visual compensation can be severely degraded due to the aforementioned network synchronization problem, the impact of which is analyzed by simulations in this paper. To resolve the network synchronization problem, we differentiate the service level of sensor traffic based on Weight Round Robin (WRR) scheduling at the routers. The weighting factor allocated to each queue is calculated by a proposed Delay-based Weight Allocation (DWA) algorithm. From the simulations, we show the traffic differentiation model can mitigate the non-synchronization of sensor data. Finally, we analyze expected traffic behaviors of the tracking system in terms of acoustic sampling interval and visual image size.

• 한국항행학회논문지
• /
• 제23권1호
• /
• pp.77-83
• /
• 2019

본 논문에서는 컬러 히스토그램과 CNN 모델을 이용한 객체 추적 기법 알고리즘을 제안한다. CNN (convolutional neural network) 모델기반 객체 추적 알고리즘인 GOTURN (generic object tracking using regression network)의 정확도를 높이기 위해 컬러 히스토그램 기반 mean-shift 추적 알고리즘을 합성하였다. 두 알고리즘을 SVM (support vector machine)을 통해 분류하여 추적 정확도가 더 높은 알고리즘을 선택하도록 설계하였다. Mean-shift 추적 알고리즘은 객체 추적에 실패할 때 경계 박스가 큰 범위로 움직이는 경향이 있어 경계 박스의 이동거리에 제한을 두어 정확도를 향상시켰다. 또한 영상 평균 밝기, 히스토그램 유사도를 고려하여 두 알고리즘의 추적 시작 위치를 초기화하여 성능을 높였다. 결과적으로 기존 GOTURN 알고리즘보다 본 논문에서 제안한 알고리즘이 전체적으로 정확도가 1.6% 향상되었다.

• 제어로봇시스템학회논문지
• /
• 제11권11호
• /
• pp.930-935
• /
• 2005

In this paper, position tracking control of an autonomous helicopter is presented. Combining an LQR method and a proportional control forms a simple PD control. Since LQR control gains are set for the velocity control of the helicopter, a position tracking error occurs. To minimize a position tracking error, neural network is introduced. Specially, in the frame of the reference compensation technique for teaming neural network compensator, a position tracking error of an autonomous helicopter can be compensated by neural network installed in the remotely located ground station. Considering time delay between an auto-helicopter and the ground station, simulation studies have been conducted. Simulation results show that the LQR with neural network performs better than that of LQR itself.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.357-360
• /
• 2007

An asset tracking using wireless sensor network is concerned with geographical locations of sensor nodes. The limited size of sensor nodes makes them attractable for tracking service, at the same time their size causes power restrictions, limited computation power, and storage restrictions. Due to such constrained capabilities, the wireless sensor network basically assumes the failure of sensor nodes. This causes a set of concerns in designing asset tracking system on wireless sensor network and one of the most critical factors is location uncertainty of sensor nodes. In this paper, we classify the location uncertainty problem in asset tracking system into following cases. First, sensor node isn't read at all because of sensor node failure, leading to misunderstanding that asset is not present. Second, incorrect location is read due to interference of RSSI, providing unreliable location of asset. We implemented and installed our asset tracking system in a real environment and continuously monitored the status of asset and measured error rate of location of sensor nodes. We present experimental results that demonstrate the location uncertainty problem in asset tracking system using wireless sensor network.

• 전자통신동향분석
• /
• 제37권1호
• /
• pp.73-83
• /
• 2022

Visual object tracking can be utilized in various applications and has attracted considerable attention in the field of computer vision. Visual object tracking technology is classified in various ways based on the number of tracking objects and the methodologies employed for tracking algorithms. This report briefly introduces the visual object tracking challenge that contributes to the development of single object tracking technology. Furthermore, we review ten Siamese network-based algorithms that have attracted attention, owing to their high tracking speed (despite the use of neural networks). In addition, we discuss the prospects of the Siamese network-based object tracking algorithms.

• 한국정보통신학회논문지
• /
• 제14권9호
• /
• pp.2120-2126
• /
• 2010

본 논문은 무선 센서네트워크에서 Zigbee를 적용한 위치추정시스템을 구현 하고자 하였다. 무선 센서네트워크는 유비쿼터스 환경에서 사용자기반의 위치인식 서비스를 제공한다. 위치인식 서비스는 사물이나 사람의 위치를 추정하고 이를 표현하여 제공한다. 본 논문에서 구현된 위치추정시스템은 실내 및 실외를 음영지역 없이 이동노드의 추정이 가능하도록 구현하였다. 실내추정의 경우 RSSI신호를 이용하며 실외추정의 경우 GPS를 연동하여 위치를 추정하였다. 또한 Zigbee를 적용하여 무선 센서네트워크 환경을 구축하고 이동노드의 위치를 제공받아 실시간 위치추정이 가능하도록 하였다.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.247-256
• /
• 2022

Visual tracking of selected target objects is fundamental challenging problems in computer vision. Object tracking localize the region of target object with bounding box in the video. We propose a Siam-FPN based custom fully CNN to solve visual tracking problems by regressing the target area in an end-to-end manner. A method of preserving the feature information flow using a feature map connection structure was applied. In this way, information is preserved and emphasized across the network. To regress object region and to classify object, the region proposal network was connected with the Siamese network. The performance of the tracking algorithm was evaluated using the OTB-100 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.621 in Success Plot and 0.838 in Precision Plot were achieved.

• 전자공학회논문지A
• /
• 제29A권11호
• /
• pp.70-77
• /
• 1992

Generally, the conventional tracking algorithms are very limited in the practical applications because of that the computation load is exponentially increased as the number of targets being tracked is increase. Recently, to overcome this kind of limitation, some new tracking methods based on neural network algorithms which have learning and parallel processing capabilities are introduced. By application of neural networks to multi-target tracking problems, the tracking system can be made computationally independent of the number of objects being tracked, through their characteristics of massive parallelism and dense interconnectivity. In this paper, a new neural network tracking algorithm, which has capability of adaptive target tracking with little increase of the amount of calculation under the clutter and noisy environments, is suggested and the possibility of real-time multi-target tracking system based on neural networks is also demonstrated through some good computer simulation results.