• IEIE Transactions on Smart Processing and Computing
• /
• 제5권4호
• /
• pp.256-266
• /
• 2016

Concurrently detected and annotated abnormal events can have a significant impact on surveillance systems. By considering the specific domain of pedestrian trajectories, this paper presents two main contributions. First, as introduced in much of the work on trajectory-based anomaly detection in the literature, only information about pedestrian paths, such as direction and speed, is considered. Differing from previous work, this paper proposes a framework that deals with additional types of trajectory-based anomalies. These abnormal events take places when a person enters prohibited areas. Those restricted regions are constructed by an online learning algorithm that uses surrounding information, including detected pedestrians and background scenes. Second, a simple data-boosting technique is introduced to overcome a lack of training data; such a problem particularly challenges all previous work, owing to the significantly low frequency of abnormal events. This technique only requires normal trajectories and fundamental information about scenes to increase the amount of training data for both normal and abnormal trajectories. With the increased amount of training data, the conventional abnormal trajectory classifier is able to achieve better prediction accuracy without falling into the over-fitting problem caused by complex learning models. Finally, the proposed framework (which annotates tracks that enter prohibited areas) and a conventional abnormal trajectory detector (using the data-boosting technique) are integrated to form a united detector. Such a detector deals with different types of anomalous trajectories in a hierarchical order. The experimental results show that all proposed detectors can effectively detect anomalous trajectories in the test phase.

• 대한인간공학회지
• /
• 제29권4호
• /
• pp.647-654
• /
• 2010

In a service environment, the spatial layout is an important factor that has a great impact on customers' behavioral characteristics including wayfinding and purchasing. Previous studies have shown a gap between marketing, focusing solely on profitability and satisfaction, and architecture, looking only into efficiency of pedestrian flow. To balance such disparity, this study suggests an integrated approach for assessing behavioral patterns in complex service environments. With the objective that complex service environments should aim to increase its profitability and efficiency while guaranteeing customer satisfaction, quantitative metrics was developed for evaluation. The metrics was defined to use data from behavior observation including path tracking, population counting, and gaze analysis, while previous studies have relied on abstract survey methods that were prone to sampling errors and loss of data. For validation of the metrics in a real world setting, a case study was conducted at 4 train stations in Korea. In the case study, experiments were conducted to gather the required data in all 4 train stations, while their physical layouts were also analyzed. With the results from the case study, comparative evaluation of the 4 train stations in terms of behavioral efficiency was possible, together with a discussion on the effect of their physical settings.

• 정보처리학회논문지B
• /
• 제11B권3호
• /
• pp.317-326
• /
• 2004

본 논문에서는 이동 카메라에서 취득한 영상에서 컬러 정보를 이용하여 다수의 보행자를 검출하고 특정 보행자를 추적하는 방법을 제안한다. 먼저 연속한 동영상 입력에 대해 BMA(Block Matching Algorithm)을 이용하여 움직임 벡터를 추출하고 움직임 보상을 한 후 차 영상을 생성한다. 다음은 이진 영상으로 변환한 후 불필요한 잡음 능을 제거하친, 프로젝션을 수행하여 보행자를 검출한다. 만약 검출된 보행자가 서로 인접하거나 겹쳐졌을 경우 RGB 컬러 정보를 이용하여 분리시킨다. 검출된 다수의 보행자로부터 특정 보행자를 추적하기 위해 보행자 가운데 영역의 RGB 컬러 정보를 이용하여 추적한다. 제안된 방법에 대하여 비디오 카메라로 녹화한 영상을 컴퓨터에서 입력받아 검출과 추적 실험을 수행한 결과, 검출 성공률이 97％, 검출 실패율이 3％로 나타났고 추적 또한 우수함을 입증하였다.

• 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.

• 통합자연과학논문집
• /
• 제12권4호
• /
• pp.105-115
• /
• 2019

In this paper, a prediction system is proposed to control the brightness of smart street lamps by predicting the moving path through the reduction of consumption power and information of pedestrian's past moving direction while meeting the function of existing smart street lamps. The brightness of smart street lamps is adjusted by utilizing the walk tracking vector and soft hand-off characteristics obtained through the motion sensing sensor of smart street lamps. In addition, the motion vector is used to analyze and predict the pedestrian path, and the GPU is used for high-speed computation. Pedestrians were detected using adaptive Gaussian mixing, weighted difference imaging, and motion vectors, and motions of pedestrians were analyzed using the extracted motion vectors. The preprocessing process using linear interpolation is performed to improve the performance of the proposed prediction system. Fuzzy prediction system and neural network prediction system are designed in parallel to improve efficiency and rough set is used for error correction.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 추계학술발표대회
• /
• pp.141-142
• /
• 2016

본 논문은 보행자의 이동경로 추적을 위해 PDR(Pedestrian Dead Reckoning) 알고리즘을 탑재한 임베디드 모듈과 연결 가능한 안드로이드 어플리케이션을 구현하였다. 임베디드 모듈은 IMU센서를 통해 얻은 값을 통해 보행자의 위치를 구하고 어플리케이션에 전송한다. 어플리케이션은 임베디드 모듈로부터 위치 값을 받아 스마트폰 화면에 실시간으로 사용자의 위치를 디스플레이 한다. 어플리케이션을 구현하여 필드 테스트를 진행한 결과 보행자의 이동경로를 비교적 정확하게 추적하였다.

• 전기학회논문지
• /
• 제58권5호
• /
• pp.1010-1018
• /
• 2009

An inertial navigation system for pedestrian position tracking is proposed, where the position is computed using inertial sensors mounted on shoes. Inertial navigation system(INS) errors increase with time due to inertial sensor errors, and therefore it needs to reset errors frequently. During normal walking, there is an almost periodic zero velocity instance when a foot touches the floor. Using this fact, estimation errors are reduced and this method is called the zero velocity updating algorithm. When implementing this zero velocity updating algorithm, it is important to know when is the zero velocity interval. The gait states are modeled as a Markov process and each state is estimated using the hidden Markov model smoother. With this gait estimation, the zero or nearly zero velocity interval is more accurately estimated, which helps to reduce the position estimation error.

• 한국융합학회논문지
• /
• 제10권3호
• /
• pp.39-47
• /
• 2019

본 논문에서는 실시간으로 보행자를 추적할 때 배경 제거를 이용하여 변형된 HOG(Histogram of Oriented Gradients) 특징 추출을 제안하였다. 기존의 HOG 특징 추출은 연산량이 많아 추적 속도가 느린 문제가 있다. 배경 제거를 통해 연산량 감소와 추적률을 향상시키기 위해 연구하였다. 불필요한 영역에서의 특징 추출을 감소시키기 위해 HSV 색공간에서 S 채널과 V 채널을 이용하여 영역 제거를 진행하였다. 영상의 평균 S 채널과 V 채널로 배경 제거 후 입력 영상이 전체적으로 어두워 객체 추적에 실패하는 경우가 있다. 이러한 경우를 방지하기 위해 히스토그램 평활화를 하였다. 제거된 영역에서 추출되는 HOG 특징이 감소되고, 객체에서는 명확한 HOG 특징이 추출되어 객체 추적 속도와 추적률이 향상되었다. 본 실험에서는 다수의 보행자나 한명의 보행자가 존재하는 영상, 배경이 복잡한 영상, 흔들림이 심한 영상을 가지고 실험하였다. 제안하는 방법은 기존의 HOG-SVM 방법과 비교하여 처리 속도는 약 41.84% 향상되었으며 오 추적률은 약 52.29% 감소되어 개선된 추적률을 보였다.

• 제어로봇시스템학회논문지
• /
• 제22권9호
• /
• pp.773-777
• /
• 2016

In this paper, a novel multi-object tracking method to track an unknown number of objects is proposed. To handle multiple object states and uncertain observations efficiently, a probability hypothesis density (PHD) filter is adopted and modified. The PHD filter is capable of reducing false positives, managing object appearances and disappearances, and estimating the multiple object trajectories in a unified framework. Although the PHD filter is robust in cluttered environments, it is vulnerable to false negatives. For this reason, we propose to exploit local observations in an RFS of the observation model. Each local observation is generated by using an online trained object detector. The main purpose of the local observation is to deal with false negatives in the PHD filtering procedure. The experimental results demonstrated that the proposed method robustly tracked multiple objects under practical situations.

• Spatial Information Research
• /
• 제21권3호
• /
• pp.11-19
• /
• 2013

도로에서 발생되는 차량간 충돌사고, 교통 소통 상황, 보행자 사고 등 다양한 도로 상황을 모니터링 및 자동으로 인식하여 교통정보를 제공하거나 긴급구난 서비스를 제공하기 위한 다양한 기술이 개발되고 있다. 도로 모니터링을 통한 다양한 객체 추적 및 상황인식을 위해서는 잡음 및 겹침 등에 강인한 객체 추적 기술이 요구된다. 본 논문에서는 외부 환경에서 Background Subtraction, LK-Optical Flow, 지역 기반 히스토그램 특징의 결합을 통해 추적을 위한 몇 가지 추정 인자를 생성하고 이를 통해 변화가 있는 객체, 잡음에도 비교적 강인한 추적 방법을 제안한다. 구체적으로는 객체의 초기 움직임 정보를 검출하기 위해 옵티컬 플로우를 적용하여 컬러 정보 및 밝기 변화에 무관한 이동 정보를 측정한다. 측정된 정보를 기반으로 하여 지역 히스토그램 기반 검증을 통해 신뢰도를 판단한다. 신뢰도가 낮을 경우 배경 제거 정보와 지역 히스토그램 트래커의 정보를 혼합하여 새로운 위치를 추정한다. 실험을 통해 제안된 기법이 객체를 추적하고 있는 도중 나타날 수 있는 충돌, 새로운 특징의 등장, 크기 변화 상황에 강인하게 동작함을 제시한다.