• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.77-80
• /
• 2010

The demand for human security significantly promotes the development of surveillance applications using a multi-sensor integrated UAV system. For more sophisticated operations, the system should provide a sequence of images rectified in a ground coordinate system in realtime. This rectification requires accurate position and attitude of the camera at the time of exposure of each image, which can be estimated through an Aerial Triangulation process using the GPS/INS data and tie points between adjacent images. In this work, the KLT tracker is utilized to obtain the tie points. To satisfy the realtime requirements, we present an approach to speed up the tracker by supplying the initial guessed positions of tie points based on the exterior orientation. The experimental results show that, when the guessed positions are supplied, the KLT tracker consumed less computational time than the ordinary KLT which is more suitable to be incorporated into the realtime image georeferencing process.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.57-64
• /
• 2009

This paper presents the hardware implementation of the pyramidal KLT(Kanade-Lucas-Tomasi) feature tracker. Because of its high computational complexity, it is not easy to implement a real-time KLT feature tracker using general-purpose processors. A hardware implementation of the pyramidal KLT feature tracker using FPGA(Field Programmable Gate Array) is described in this paper with emphasis on 1) adaptive adjustment of threshold in feature extraction under diverse lighting conditions, and 2) modification of the tracking algorithm to accomodate parallel processing and to overcome memory constraints such as capacity and bandwidth limitation. The effectiveness of the implementation was evaluated over ones produced by its software implementation. The throughput of the FPGA-based tracker was 30 frames/sec for video images with size of $720{\times}480$.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.2
• /
• pp.49-56
• /
• 2008

Image registration is one of the critical techniques of image mosaic which has many applications such as generating panoramas, video monitoring, image rendering and reconstruction, etc. The fundamental tasks of image registration are point features extraction and tracking which take much computation time. KLT(Kanade-Lucas-Tomasi) feature tracker has proposed for extracting and tracking features through image sequences. The aim of this study is to demonstrate the usage of effective and robust KLT feature detector and tracker for an image registration using the sequence image frames captured by UAV video camera. In result, by using iterative implementation of the KLT tracker, the features extracted from the first frame of image sequences could be successfully tracked through all frames. The process of feature tracking in the various frames with rotation, translation and small scaling could be improved by a careful choice of the process condition and KLT pyramid implementation.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2008.10a
• /
• pp.245-246
• /
• 2008

The goal of this study is to explore the possibility of KLT tracker for tracking the features between two images including rotation and shift. As a test site, Jangsu-Gun area of South Korea is selected and the images taken from UAV camera are used for analysis. The analysis was carried out using KLT tracker developed in a PC environment. The results of the experiment used two images with the large overlapping area are compared with the results of two images with the little overlapping area and rotation. Overall, the research indicates that the integrated features of littlerotation and motion images can significantly increase during the tracking process. But using KLT tracker for extracting and tracking features between images with large rotation and motion, the number of tracked features are decreased.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.629-644
• /
• 2010

A real-time image georeferencing system requires all inputs to be determined in real-time. The intrinsic camera parameters can be identified in advance from a camera calibration process while other control information can be derived instantaneously from real-time GPS/INS data. The bottleneck process is tie point acquisition since manual operations will be definitely obstacles for real-time system while the existing extraction methods are not fast enough. In this paper, we present a fast-and-automated image matching technique based on the KLT tracker to obtain a set of tie-points in real-time. The proposed work accelerates the KLT tracker by supplying the initial guessed tie-points computed using the GPS/INS data. Originally, the KLT only works effectively when the displacement between tie-points is small. To drive an automated solution, this paper suggests an appropriate number of depth levels for multi-resolution tracking under large displacement using the knowledge of uncertainties the GPS/INS data measurements. The experimental results show that our suggested depth levels is promising and the proposed work can obtain tie-points faster than the ordinary KLT by 13% with no less accuracy. This promising result suggests that our proposed algorithm can be effectively integrated into the real-time image georeferencing for further developing a real-time surveillance application.

• Journal of Korea Multimedia Society
• /
• v.17 no.7
• /
• pp.787-796
• /
• 2014

Many mobile robot navigation methods utilize laser scanners, ultrasonic sensors, vision camera, and so on for detecting obstacles and path following. However, human utilizes only vision(e.g. eye) information for navigation. In this paper, we study a mobile robot control method based on only the camera vision. The Gaussian Mixture Model and a shadow removal technology are used to divide the foreground and the background from the camera image. The mobile robot uses a combined CAMSHIFT and KLT feature tracker algorithms based on the information of the foreground to follow a person. The algorithm is verified by experiments where a person is tracked and followed by a robot in a hallway.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.835-838
• /
• 2008

In this paper, we present automatic face detection and tracking which is robustness in rotation and translation. Detecting a face image, we used Haar-like feature, which is fast detect facial image. Also tracking, we applied Lucas-Kanade feature tracker and KLT algorithm, which has robustness for rotated facial image. In experiment result, we confirmed that face detection and tracking which is robustness in rotation and translation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4355-4374
• /
• 2018

Crowd escape event detection has become one of the hottest problems in intelligent surveillance filed. When the 'escape event' occurs, pedestrians will escape in a disordered way with different velocities and directions. Based on these characteristics, this paper proposes a Direction-Collectiveness Model to detect escape event in crowd scenes. First, we extract a set of trajectories from video sequences by using generalized Kanade-Lucas-Tomasi key point tracker (gKLT). Second, a Direction-Collectiveness Model is built based on the randomness of velocity and orientation calculated from the trajectories to express the movement of the crowd. This model can describe the movement of the crowd adequately. To obtain a generalized crowd escape event detector, we adopt an adaptive threshold according to the Direction-Collectiveness index. Experiments conducted on two widely used datasets demonstrate that the proposed model can detect the escape events more effectively from dense crowd.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.108-111
• /
• 2008

본 논문에서는 KLT(Kanade-Lucas-Tomasi) 추적기에서 특징점의 개수를 일정하게 유지시키기 위해 존재하는 특징점의 관리 부분을 FPGA(Field Programmable Gate Array)에 구현하기 위한 구조를 제안한다. FPGA 에 구현하기 위해 한정된 자원을 효과적으로 사용하도록 하는 것을 목표로 연산량이 많은 부분을 적은 연산량으로 구현 가능한 것으로 대체하고, 메모리의 크기와 접근 회수를 줄이기 위한 방법을 고려했다. 구현이 간단한 Harris 코너 검출기를 이용하여 특징점을 선택하고, 나눗셈 연산이 필요 없는 히스토그램을 이용하여 임계값을 설정해 특징점을 관리했다. C 언어로 시뮬레이션을 수행하여 제안한 방법을 확인했고, 기존의 특징점 관리 방법과의 비교를 통해 검증했다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.4
• /
• pp.11-16
• /
• 2008

The goal of this study is to evaluate the KLT(Kanade-Lucas-Tomasi) for extracting and tracking the features using various data acquired from UAV. Sequences of images were collected for Jangsu-Gun area to perform the analysis. Four data sets were subjected to extract and track the features using the parameters of the KLT. From the results of the experiment, more than 90 percent of the features extracted from the first frame could successfully track through the next frame when the shift between frames is small. But when the frame to frame motion is large in non-consecutive frames, KLT tracker is failed to track the corresponding points. Future research will be focused on feature tracking of sequence frames with large shift and rotation.