• 한국군사과학기술학회지
• /
• 제11권6호
• /
• pp.38-46
• /
• 2008

A distributed system for tracking multiple targets with a pair of multifunction radars is proposed and implemented. The system performs track-to-track association and track-to-track fusion at the fusion center to form fused tracks. The association and fusion are performed using target state information linked via communication nodes from a radar at a remote location. Many factors can affect the track-to-track association and fusion performances. They include delays in data transmission buffer of the remote radar, the error in estimating time-stamp of the remote radar, and the gating in track-to-track association. The effects on association and fusion performances due to these factors are investigated through extensive numerical simulations.

• 제어로봇시스템학회논문지
• /
• 제18권9호
• /
• pp.863-870
• /
• 2012

This paper presents a track-to-tack information fusion algorithm using tracks of 2D and 3D radars. Before track fusion, it is needed to match the dimension of the tracks, as the tracks generated by 2D and 3D radars have different dimensions. This paper suggests how the 2D tracks are converted to the 3D tracks for track fusion. Through simulation studies, we can verify that the performance of the proposed method.

• 한국군사과학기술학회지
• /
• 제11권1호
• /
• pp.85-92
• /
• 2008

An architecture for multiple radar tracking systems can be broadly categorized according to the methods in which the tracking functions are performed : central-level tracking and distributed tracking. In the central-level tracking, target tracking is performed using observations from all radar systems. This architecture provides optimal solution to target tracking. In distributed tracking, tracking is performed at each radar system and the composite track information is formed through track fusion integrating multiple radar-level tracks. Track-to-track fusion and track-to-track association are required to perform in this architecture. In this paper, issues and recent research on the two tracking architectures are surveyed.

• 제어로봇시스템학회논문지
• /
• 제20권2호
• /
• pp.126-131
• /
• 2014

This paper is concerned with a track management method for a naval combat system which receives the tracks information from multi-sensors and multi-tactical datalinks. Since the track management of processing the track information from diverse sources can be formulated as a data fusion problem, this paper will deal with the data fusion architecture, track association and track information determination algorithm for the track management of naval combat systems.

• 전자공학회논문지
• /
• 제49권9호
• /
• pp.335-343
• /
• 2012

본 논문은 근거리에서 접근하는 표적에 대한 레이더와 열영상의 관측데이터를 기반으로 정보융합을 수행하여 표적을 추적하는 알고리즘을 기술하고 있다. 일반적으로 칼만필터를 이용한 추적 융합 방법은 동기화된 레이더 및 열영상의 데이터를 근간으로 하고 있으며, 비동기적으로 동작하는 실제 시스템에 적용하기에는 많은 제한사항을 가지고 있다. 제안된 알고리즘에서의 중점사항은 동기화되어 있지 않은 서로 다른 두 센서인 레이더와 열영상의 관측데이터가 입력되었을 때 레이더의 거리정보와 추적상태벡터를 이용하여 관측값의 시간차이를 보상하여 관측치 융합 후 추적을 수행하는 것이다. 제안된 알고리즘의 성능평가를 위해 기존의 궤적기반 정보융합방법 및 측정치 융합기법과 성능을 비교하여 제시한다.

• 한국군사과학기술학회지
• /
• 제10권3호
• /
• pp.34-42
• /
• 2007

It is very important for the combat system to process extensive data exactly at short time for the better situation awareness compared with the threats in these days. This paper suggests to add radial velocity on the decision factor of sensor data fusion in the existing algorithm for the accuracy enhancement of the sensor data fusion in the combat system.

• 자동차안전학회지
• /
• 제13권4호
• /
• pp.7-13
• /
• 2021

This paper presents an vulnerable road user (VRU) classification and tracking algorithm using vision and LiDAR sensor fusion method for urban autonomous driving. The classification and tracking for vulnerable road users such as pedestrian, bicycle, and motorcycle are essential for autonomous driving in complex urban environments. In this paper, a real-time object image detection algorithm called Yolo and object tracking algorithm from LiDAR point cloud are fused in the high level. The proposed algorithm consists of four parts. First, the object bounding boxes on the pixel coordinate, which is obtained from YOLO, are transformed into the local coordinate of subject vehicle using the homography matrix. Second, a LiDAR point cloud is clustered based on Euclidean distance and the clusters are associated using GNN. In addition, the states of clusters including position, heading angle, velocity and acceleration information are estimated using geometric model free approach (GMFA) in real-time. Finally, the each LiDAR track is matched with a vision track using angle information of transformed vision track and assigned a classification id. The proposed fusion algorithm is evaluated via real vehicle test in the urban environment.

• 한국통신학회논문지
• /
• 제39C권1호
• /
• pp.17-27
• /
• 2014

협동교전능력과 네트워크 중심의 교전에 대한 관심과 더불어 분산형 추적 시스템에 대한 연구는 중요하다. 이러한 분산형 추적 시스템 연구에 있어서 네트워크의 거대화에 의해 비선형 시스템에서의 추적 필터와 자료융합기술 개발이 불가피하다. 따라서 본 논문에서는 협동교전능력 응용을 위해 측지좌표계 기반의 분산형 추적 시스템에 적합한 트랙 융합구조에서 비선형 시스템 환경 하에 운용할 수 있는 비선형 자료융합 기법의 문제를 정립하고 그에 적용 가능한 기법들을 소개하고 성능을 비교 분석한다. 비선형 시스템에서는 최적의 트랙 융합 기법을 구현하는데 있어서 상호 공분산을 구할 수 없다는 것이 가장 큰 문제점이다. 이와 같은 문제점을 해결하기 위해서 크게 간소화 기법과 근사화 기법의 두 가지 접근법이 있다. 간소화 기법에서는 sample mean과 Millman formula의 두 가지 추정치 융합 기법을 유도할 수 있고, 근사화 기법에서는 해석적 선형화 기법과 통계적 선형화 기법의 두 가지 추정치 융합 기법을 유도할 수 있다. 소개된 네 가지 융합 기법을 모의 실험한 결과 각 플랫폼의 추정치 공분산 정보만을 이용하여 필터의 매 단계에서 최적의 플랫폼을 선택할 수 있는 Millman formula 추정치 융합 기법과 적은 복잡도로 보다 정확히 플랫폼들의 상관 공분산을 근사화 할 수 있는 BCS 융합기법이 효율적임을 확인할 수 있다.

• 제어로봇시스템학회논문지
• /
• 제16권7호
• /
• pp.639-645
• /
• 2010

This paper presents the sensor fusion algorithm that recognizes a primary vehicle by fusing radar and monocular vision data. In general, most of commercial radars may lose tracking of the primary vehicle, i.e., the closest preceding vehicle in the same lane, when it stops or goes with other preceding vehicles in the adjacent lane with similar velocity and range. In order to improve the performance degradation of radar, vehicle detection information from vision sensor and path prediction predicted by ego vehicle sensors will be combined for target classification. Then, the target classification will work with probabilistic association filters to track a primary vehicle. Finally the performance of the proposed sensor fusion algorithm is validated using field test data on highway.

• 한국정밀공학회지
• /
• 제28권12호
• /
• pp.1372-1378
• /
• 2011

The smart air condition system is superior to conventional air condition system in the aspect of control accuracy, environmental preservation and it is foundation for intelligent vehicle such as electric vehicle, fuel cell vehicle. In this paper, failure analyses of smart air condition system will be performed and then sensor fusion technique will be proposed for fail safety of smart air condition system. A sensor fusion logic of air condition system by using CO sensor, $CO_2$ sensor and VOC, $NO_x$ sensor will be developed and simulated by fault injection simulation. The fusion technology of smart air condition system is generated in an experiment and a performance analysis is conducted with fusion algorithms. The proposed algorithm adds the error characteristic of each sensor as a conditional probability value, and ensures greater accuracy by performing the track fusion with the sensors with the most reliable performance.