• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.376-378
• /
• 2022

Artificial intelligence technology is widely used in various fields such as artificial intelligence speakers, artificial intelligence chatbots, and autonomous vehicles. Among these AI application fields, the image processing field shows various uses such as detecting objects or recognizing objects using artificial intelligence. In this paper, data synthesized by a virtual human is used as a method to analyze images taken in a specific space.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.251-254
• /
• 2005

본 논문은 유비쿼터스 컴퓨팅 환경 기반에서의 온라인 얼굴인식 시스템 구현을 기술한다. 구현된 시스템은 CMOS 카메라를 장착한 PDA를 이용하여 얼굴영상을 획득하고 이 영상을 무선랜을 이용하여 인증 서버로 전송하여 서버로부터 인증된 결과를 받도록 하였다. 먼저 클라이언트 측인 PDA에서는 등록과 인증을 확인할 수 있도록 임베디드 비주얼 프로그램으로 사용자 인터페이스를 구축하였다. 다음으로 서버 영역에서는 얼굴인식에서 탁월한 성능을 보이는 PCA와 LDA 알고리즘을 사용하여 PDA로부터 전송 받은 얼굴 데이터를 학습하고 인식한 결과를 재전송하는 부분이 구현되었다. 시스템 구현에서 실시간성을 확보하기 위해 PDA에서는 영상을 압축률 효과가 좋은 JPG 형식의 데이터로 서버에 전송하였다. 본 논문에서 구현한 시스템은 학습과정에서 미리 구한 고유값을 이용하여 테스트 얼굴영상을 같은 공간에 투영시켜 서로간의 유사도를 비교하도록 하여 얼굴인식 속도 및 성능을 개선하였다.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.119-120
• /
• 2007

본 논문에서는 실내의 고정된 단일 칼라 카메라에서 획득된 비디오 스트림으로부터 사람의 행동을 인식하기 위한 시스템을 제안한다. 제안된 시스템은 사람의 시공간적 상태 변화와 사람의 시선 방향을 이용하여 규칙기반으로 행동을 인식한다. 사람의 의미 있는 상태변화를 이벤트로, 이벤트의 시퀀스 즉, 사람의 행동을 시나리오로 정의하였다. 따라서 입력비디오 스트림에서 사람의 상태변화로 이벤트를 검출하고, 검출된 이벤트의 시퀀스로 사람의 행동을 인식한다. 사람의 시선은 얼굴과 머리 영역의 색정보를 이용한 시선 방향 추정 방법으로 찾아지며, 사람의 상태 변화는 사람의 위치와 키 등을 이용하여 검출된다. 본 시스템은 실내 환경에서 획득한 비디오에서 실험하였으며, 실험결과 시선 방향에 의해 서로 다른 행동을 구분하여 인식할 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.448-450
• /
• 2012

본 논문에서는 Kinect 방식의 RGB-D 영상센서를 사용하여, 깊이(Depth) 영상으로부터 3차원 객체의 기하정보를 표현하는 표면 정규 벡터(Surface Normal Vector)를 추출하고, 그 결과를 영상화하는 방법을 제안하며, 제안된 방법으로 생성된 영상으로부터 깊이 영상의 특징점 및 특징 기술자를 추출하여 3차원 객체 인식 성능을 향상시키는 방법을 제안한다. 또한 생성된 RGB-D 특징 기술자들을 객체 단위로 구분 가능한 코드북(CodeBook) 학습을 통한 인식방법을 제안하여 객체의 인식 성능을 높이는 방법을 제안한다. 제안하는 RGB-D 기반의 특징 추출 및 학습 방법은 텍스쳐 유무, 카메라 회전 및 이동 변화 등의 환경변화에 강건함을 실험적으로 증명하였으며, 이 방법은 Kinect 방식의 RGB-D 영상을 사용하는 3차원 객체/공간 인식 및 추적, 혹은 이를 응용하는 증강현실 시스템에 적용하여 사용될 수 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.110-123
• /
• 2019

Traffic data is the most basic element necessary for transportation planning and traffic system operation. Recently, a method of estimating traffic flow characteristics using distance to a leading vehicle measured by an ADAS camera has been attempted. This study investigated the feasibility of the ADAS vehicle reflecting the distance error of image-based vehicle identification technology as a means to estimate the traffic flow through the normalized root mean square error (NRMSE) based on the number of lanes, traffic demand, penetration rate of probe vehicle, and time-space estimation area by employing the microscopic simulation model, VISSIM. As a result, the estimate of low density traffic flow (i.e., LOS A, LOS B) is unreliable due to the limitation of the maximum identification distance of ADAS camera. Although the reliability of the estimates can be improved if multiple lanes, high traffic demands, and high penetration rates are implemented, artificially raising the penetration rates is unrealistic. Their reliability can be improved by extending the time dimension of the estimation area as well, but the most influential one is the driving behavior of the ADAS vehicle. In conclusion, although it is not possible to accurately estimate the traffic flow with the ADAS camera, its applicability will be expanded by improving its performance and functions.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1099-1110
• /
• 2023

The recognition system of autonomous driving and robot navigation performs vision work such as object recognition, tracking, and lane detection after multi-sensor fusion to improve performance. Currently, research on a deep learning model based on the fusion of a camera and a lidar sensor is being actively conducted. However, deep learning models are vulnerable to adversarial attacks through modulation of input data. Attacks on the existing multi-sensor-based autonomous driving recognition system are focused on inducing obstacle detection by lowering the confidence score of the object recognition model.However, there is a limitation that an attack is possible only in the target model. In the case of attacks on the sensor fusion stage, errors in vision work after fusion can be cascaded, and this risk needs to be considered. In addition, an attack on LIDAR's point cloud data, which is difficult to judge visually, makes it difficult to determine whether it is an attack. In this study, image scaling-based camera-lidar We propose an attack method that reduces the accuracy of LCCNet, a fusion model (camera-LiDAR calibration model). The proposed method is to perform a scaling attack on the point of the input lidar. As a result of conducting an attack performance experiment by size with a scaling algorithm, an average of more than 77% of fusion errors were caused.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.491-500
• /
• 2021

In this study, we propose a method for detecting fall behavior using MS Kinect v2 RGBD Camera-based Human-Skeleton Keypoints and a 2-Stacked Bi-LSTM model. In previous studies, skeletal information was extracted from RGB images using a deep learning model such as OpenPose, and then recognition was performed using a recurrent neural network model such as LSTM and GRU. The proposed method receives skeletal information directly from the camera, extracts 2 time-series features of acceleration and distance, and then recognizes the fall behavior using the 2-Stacked Bi-LSTM model. The central joint was obtained for the major skeletons such as the shoulder, spine, and pelvis, and the movement acceleration and distance from the floor were proposed as features of the central joint. The extracted features were compared with models such as Stacked LSTM and Bi-LSTM, and improved detection performance compared to existing studies such as GRU and LSTM was demonstrated through experiments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.191-197
• /
• 2015

In this paper, we propose the system which recognize the gaze using Random Forests in vehicular environment based on smart-phone. Proposed system is mainly composed of the following: face detection using Adaboost, face component estimation using Histograms, and gaze recognition based on Random Forests. We detect a driver based on the image information with a smart-phone camera, and the face component of driver is estimated. Next, we extract the feature vectors from the estimated face component and recognize gaze direction using Random Forest recognition algorithm. Also, we collected gaze database including a variety gaze direction in real environments for the experiment. In the experiment result, the face detection rate and the gaze recognition rate showed 82.02% and 84.77% average accuracies, respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.488-498
• /
• 2007

This paper presents a novel approach for representing the spatio-temporal topology of the camera network with overlapping and non-overlapping fields of view (FOVs) in Ubiquitous Smart Space (USS). The topology is determined by tracking moving objects and establishing object correspondence across multiple cameras. To track people successfully in multiple camera views, we used the Merge-Split (MS) approach for object occlusion in a single camera and the grid-based approach for extracting the accurate object feature. In addition, we considered the appearance of people and the transition time between entry and exit zones for tracking objects across blind regions of multiple cameras with non-overlapping FOVs. The main contribution of this paper is to estimate transition times between various entry and exit zones, and to graphically represent the camera topology as an undirected weighted graph using the transition probabilities.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1601-1607
• /
• 2009

Vision system is an object recognition system analyzing image information captured through camera. Vision system can be applied to various fields, and automobile types recognition is one of them. There have been many research about algorithm of automobile types recognition. But have complex calculation processing. so they need long processing time. In this paper, we designed vision box based on embedded system. and suggested automobile types recognition system using the vision box. As a result of pretesting, this system achieves 100% rate of recognition at the optimal condition. But when condition is changed by lighting and angle, recognition is available but pattern score is lowered. Also, it is observed that the proposed system satisfy the criteria of processing time and recognition rate in industrial field.