• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.770-772
• /
• 2015

어미로부터 생후 21일령 또는 28일령에 젖을 때는 이유자돈들만을 개별적인 돈사에서 합사하는 경우, 낯선 환경 및 새로운 동료들과의 서열 구분을 위한 공격적인 행동이 매우 빈번하게 발생한다. 이로 인한 돼지의 성장 저하는 농가의 소득 하락으로 이어져 국내 외 양돈 농가의 큰 문제로 인식되고 있다. 본 논문에서는 키넥트 카메라에서 취득할 수 있는 영상의 깊이정보를 이용하여 이유자돈들의 공격적인 행동을 조기 탐지할 수 있는 프로토타입 모니터링 시스템을 제안한다. 먼저 제안한 시스템은 키넥트의 적외선 센서에서 실시간으로 취득하는 깊이 정보로부터 움직임이 있는 객체들만을 탐지하고, 해당 객체들의 ROI를 설정한다, 둘째, ROI를 이용하여 5가지 특정 정보(객체의 평균, 최고, 최소 속도, 객체 속도의 표준편차, 두 객체 사이의 최소 거리)를 추출한다. 셋째, 취득한 특징 정보는 이진 클래스 분류 문제로 해석하여, 기계학습의 대표적인 모델인 SVM을 탐지기로 사용하였다. 실제 이유자돈사에서 취득한 키넥트 영상을 이용하여 모의 실험을 수행한 결과 안정적인 성능을 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.5
• /
• pp.35-42
• /
• 2013

Shot boundary detection is an essential step for efficient browsing, sorting, and classification of video data. Robust shot detection method should overcome the disturbances caused by pixel brightness and object movement between frames. In this paper, two shot boundary detection methods are presented to address these problem by using segmentation, object movement, and pixel brightness. The first method is based on the histogram that reflects object movements and the morphological dilation operation that considers pixel brightness. The second method uses the pixel brightness information of segmented and whole blocks between frames. Experiments on digitized video data of National Archive of Korea show that the proposed methods outperforms the existing pixel-based and histogram-based methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.124-127
• /
• 2008

DoS/DDoS로 대표되는 트래픽 폭주 공격은 대상 시스템뿐만 아니라 네트워크 대역폭, 프로세서 처리능력, 시스템 자원 등에 악영향을 줌으로써 네트워크에 심각한 장애를 유발할 수 있다. 따라서 신속한 트래픽 폭주 공격의 탐지는 안정적인 서비스 제공 및 시스템 운영에 필수요건이다. 전통적인 패킷 수집을 통한 DoS/DDoS의 탐지방법은 공격에 대한 상세한 분석은 가능하나 설치의 확장성 부족, 고가의 고성능 분석시스템의 요구, 신속한 탐지를 보장하지 못한다는 문제점을 갖고 있다. 본 논문에서는 15초 단위의 SNMP MIB 객체 정보를 바탕으로 SVDD(support vector data description)를 이용하여 보다 빠르고 정확한 침입탐지와 쉬운 확장성, 저비용탐지 및 정확한 공격유형별 분류를 가능케 하는 새로운 시스템을 설계 및 구현하였다. 실험을 통하여 만족스러운 침입 탐지율과 안전한 false negative rate, 공격유형별 분류율 수치 등을 확인함으로써 제안된 시스템의 성능을 검증하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.11
• /
• pp.795-800
• /
• 2013

Early detection of oestrus in Korean cows is one of the important issues in maximizing the economic benefit. Although various methods have been proposed, we still need to improve the performance of the oestrus detection system. In this paper, we propose a video surveillance system which can detect unusual behavior of multiple cows including the mounting activity. The unusual behavior detection is to detect the dangerous or abnormal situations of cows in video coming in real time from a surveillance camera promptly and correctly. The prototype system for unusual behavior detection gets an input video from a fixed location camera, and uses the motion vector to represent the motion information of cows in video, and finally selects a SVDD (one of the most well-known types of one-class SVM) as a detector by reinterpreting the unusual behavior into an one class decision problem from the practical points of view. The experimental results with the videos obtained from a farm located in Jinju illustrate the efficiency of the proposed method.

• Journal of Platform Technology
• /
• v.12 no.3
• /
• pp.62-70
• /
• 2024

Recent surveillance systems employ multiple sensors, such as cameras and radars, to enhance the accuracy of intrusion detection. However, object recognition through camera (RGB, Thermal) sensors may not always be accurate during nighttime, in adverse weather conditions, or when the intruder is camouflaged. In such situations, it is possible to detect intruders by utilizing the trajectories of objects extracted from camera or radar sensors. This paper proposes a method to detect intruders using only trajectory information in environments where object recognition is challenging. The proposed method involves training an LSTM-Attention based trajectory classification model using normal and abnormal (intrusion, loitering) trajectory data of animals and humans. This model is then used to identify abnormal human trajectories and perform intrusion detection. Finally, the validity of the proposed method is demonstrated through experiments using real data.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.233-247
• /
• 2023

Recently, research on detecting objects in hidden spaces beyond the direct line-of-sight of observers has received attention. Most studies use optical equipment that utilizes the directional of light, but sound that has both diffraction and directional is also suitable for non-line-of-sight(NLOS) research. In this paper, we propose a novel method of detecting objects in non-line-of-sight (NLOS) areas using acoustic signals in the audible frequency range. We developed a deep learning model that extracts information from the NLOS area by inputting only acoustic signals and predicts the properties and location of hidden objects. Additionally, for the training and evaluation of the deep learning model, we collected data by varying the signal transmission and reception location for a total of 11 objects. We show that the deep learning model demonstrates outstanding performance in detecting objects in the NLOS area using acoustic signals. We observed that the performance decreases as the distance between the signal collection location and the reflecting wall, and the performance improves through the combination of signals collected from multiple locations. Finally, we propose the optimal conditions for detecting objects in the NLOS area using acoustic signals.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.989-1006
• /
• 2020

Building change monitoring based on building detection is one of the most important fields in terms of monitoring artificial structures using high-resolution multi-temporal images such as CAS500-1 and 2, which are scheduled to be launched. However, not only the various shapes and sizes of buildings located on the surface of the Earth, but also the shadows or trees around them make it difficult to detect the buildings accurately. Also, a large number of misdetection are caused by relief displacement according to the azimuth and elevation angles of the platform. In this study, object-based building detection was performed using the azimuth angle of the Sun and the corresponding main direction of shadows to improve the results of building change detection. After that, the platform's azimuth and elevation angles were used to detect changed buildings. The object-based segmentation was performed on a high-resolution imagery, and then shadow objects were classified through the shadow intensity, and feature information such as rectangular fit, Gray-Level Co-occurrence Matrix (GLCM) homogeneity and area of each object were calculated for building candidate detection. Then, the final buildings were detected using the direction and distance relationship between the center of building candidate object and its shadow according to the azimuth angle of the Sun. A total of three methods were proposed for the building change detection between building objects detected in each image: simple overlay between objects, comparison of the object sizes according to the elevation angle of the platform, and consideration of direction between objects according to the azimuth angle of the platform. In this study, residential area was selected as study area using high-resolution imagery acquired from KOMPSAT-3 and Unmanned Aerial Vehicle (UAV). Experimental results have shown that F1-scores of building detection results detected using feature information were 0.488 and 0.696 respectively in KOMPSAT-3 image and UAV image, whereas F1-scores of building detection results considering shadows were 0.876 and 0.867, respectively, indicating that the accuracy of building detection method considering shadows is higher. Also among the three proposed building change detection methods, the F1-score of the consideration of direction between objects according to the azimuth angles was the highest at 0.891.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.347-350
• /
• 2011

감시카메라 환경에서의 비정상 집단행동 탐지란 감시카메라로부터 유입되는 영상에서 다중 객체가 위험에 처한 상황을 신속하고 정확하게 탐지 및 인식하는 분야를 말한다. 본 논문에서는 CCTV 등과 같은 감시카메라 환경에서 움직임 벡터와 SVDD를 이용하여 집단내의 비정상 상황을 탐지하는 프로토타입 시스템을 제안한다. 제안된 시스템은 움직임 벡터를 이용하여 영상내의 움직임 정보를 추출 표현하였으며, 비정상 집단행동의 판별 문제를 실용적 차원의 단일 클래스 분류 문제로 재해석하여 단일 클래스 SVM의 대표적 모델인 SVDD를 탐지자로 설계하였다. 공개적으로 사용 가능한 벤치마크 데이터 셋인 PETS 2009와 UMN을 이용하여 본 논문에서 제안한 비정상 집단행동 탐지 시스템의 성능을 실험적으로 검증한다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.150-157
• /
• 2015

Pedestrian detection has largely been researched as one of the important technologies for autonomous driving vehicle and preventing accidents. There are two categories for pedestrian detection, camera-based and LIDAR-based. LIDAR-based methods have the advantage of the wide angle of view and insensitivity of illuminance change while camera-based methods have not. However, there are several problems with 3D LIDAR, such as insufficient resolution to detect distant pedestrians and decrease in detection rate in a complex situation due to segmentation error and occlusion. In this paper, two methods using GM-PHD filter are proposed to improve the poor rates of pedestrian detection algorithms based on 3D LIDAR. First one improves detection performance and resolution of object by automatic accumulation of points in previous frames onto current objects. Second one additionally enhances the detection results by applying the GM-PHD filter which is modified in order to handle the poor situation to classified multi target. A quantitative evaluation with autonomously acquired road environment data shows the proposed methods highly increase the performance of existing pedestrian detection algorithms.