• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.215-216
• /
• 2020

Optical Flow는 컴퓨터 비전 분야의 많은 응용기술에 사용된다. 객체 탐지, 추적, 연속 영상 보간, 3D Reconstruction과 같은 최근에 활발히 연구되는 여러 분야에서 사용되는 기반 기술이다. 최근 딥러닝을 기반으로 한 다양한 연구가 활발히 진행되어 왔으며 높은 정확도를 보이고 있다. 이런 분야들은 많은 경우에 실시간 시스템에 적용되어 이미지로부터 정보를 연산한다. 본 논문은 MaskFlownet, SelFlow, LiteFlowNet2 등과 같은 높은 정확도를 가진 신경망 네트워크로 추정된 Optical Flow를 살펴본다. 각 신경망 네트워크로 얻어진 정확도를 비교하고 디스플레이 기술과 이미지 센서 기술의 발전으로 사용 수요가 많아진 고화질의 이미지를 실시간으로 처리하는 경우, 적용 가능한 Optical Flow의 성능을 분석하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.79-80
• /
• 2024

인공지능과 디지털 변환의 추세가 소매업계에서 온라인으로의 전환을 가속화하고 있다. 이러한 변화에 부응하여 본 논문에서는 O2O(Online-to-Offline) 상점을 위한 상품명 인식 기술을 제안한다. 제안하는 방법은 이미지 내 특징점과 이들 주변의 픽셀 정보를 포함하는 특징 디스크립터를 활용하여 상품 이미지와 진열대 사진을 비교하는 것에 초점을 맞춘다. 사용된 주요 알고리즘은 SURF와 BFMatcher, KnnMatch 방법으로, 이들은 각각 이미지의 특징점을 탐지하고 매칭하는 데 사용된다. 실험을 통해 적절한 임계값을 설정하여 높은 신뢰도의 매칭 결과를 선별하는 방법을 제시하였으며, 이를 통해 O2O 상점에서 상품 관리와 인식을 향상시키는 데 기여할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.639-640
• /
• 2024

인위적인 공격뿐만 아니란 현실 세계에서도 이미지에 노이즈가 추가되는 경우가 있다. 이를 해결하기 위한 많은 연구가 이루어지고 있지만, 적대적 공격에 강건한 모델은 기존의 모델에 비해 원본 이미지에 대해 정확도가 떨어진다는 문제점이 있다. 따라서 본 논문은 생성 모델을 활용하여 적대적 예제에 강건한 모듈을 제안한다. 또한, 적대적 공격을 탐지하는 모듈을 활용하여 적대적 예제뿐만 아니라 원본 이미지에 대해서도 정확도를 높이는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.447-449
• /
• 2024

본 논문에서 다양한 환경적 요인에서 촬영한 이미지 데이터를 활용하여 신호등 위치의 정확한 탐지 및 신호등의 색상 인식을 통해 교통 신호를 판별하는데 사용되는 컴퓨터 비전 기반의 신호등 인식 시스템 알고리즘을 제안하였다. 이를 통해 기존에 신호를 인식하던 LiDAR 및 RADAR 센서를 대신해 카메라를 사용함으로써 자율주행 차의 제작비용 감소를 기대할 수 있다. 또한 다양한 환경의 이미지 데이터를 통해 실험을 진행하였고 이러한 실험결과를 분석하고 적용함으로써 악천후에서의 효과적인 신호등 인식 시스템을 구축하는데 기여하고자 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.219-223
• /
• 2020

To guarantee AI model's prominent recognition rate and recognition precision, obtaining the large number of data is essential. In this paper, we propose transfer learning-based object detection algorithm for maintaining outstanding performance even when the volume of training data is small. Also, we proposed a tranfer learning network combining Resnet-50 and YOLO(You Only Look Once) network. The transfer learning network uses the Leeds Sports Pose dataset to train the network that detects the person who occupies the largest part of each images. Simulation results yield to detection rate as 84% and detection precision as 97%.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.19-27
• /
• 2021

In this paper, we propose a method for detecting characters in images and detecting facial regions, which consists of two tasks. First, we separate two different characters to detect the face position of the characters in the frame. For fast detection, we use You Only Look Once (YOLO), which finds faces in the image in real time, to extract the location of the face and mark them as object detection boxes. Second, we present three image processing methods to detect accurate face area based on object detection boxes. Each method uses HSV values extracted from the region estimated by the detection figure to detect the face region of the characters, and changes the size and shape of the detection figure to compare the accuracy of each method. Each face detection method is compared and analyzed with comparative data and image processing data for reliability verification. As a result, we achieved the highest accuracy of 87% when using the split rectangular method among circular, rectangular, and split rectangular methods.

• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.1-6
• /
• 2021

In the modern society, traffic problems are occurring as vehicle ownership increases. In particular, the incidence of highway traffic accidents is low, but the fatality rate is high. Therefore, a technology for detecting an abnormality in a vehicle is being studied. Among them, there is a vehicle anomaly detection technology using deep learning. This detects vehicle abnormalities such as a stopped vehicle due to an accident or engine failure. However, if an abnormality occurs on the road, it is possible to quickly respond to the driver's location. In this study, we propose a deep learning-based vehicle anomaly detection using road CCTV data. The proposed method preprocesses the road CCTV data. The pre-processing uses the background extraction algorithm MOG2 to separate the background and the foreground. The foreground refers to a vehicle with displacement, and a vehicle with an abnormality on the road is judged as a background because there is no displacement. The image that the background is extracted detects an object using YOLOv4. It is determined that the vehicle is abnormal.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.1-6
• /
• 2003

In this Paper, the moving image is detected by a collision preventive system. The noise of these images is reduced by a mean filter. In case of detecting a movement with a binary difference image the moving area is detected exactly by the labeling and the projective method. When the image move slowly with the tracking mode of the system, the center of the tracking window move to the previous tracking window. And the tracking windows are divided into a tracking mode and a coasting mode which are determine by the Contrast-Difference Correlation of the date obtained from a difference image. The coasting mode determine whether continue the tracking step or not comparing the coasting-time values to reducing the error by the disturbance. The coasting and tracking of these moving images are verified by the result of the simulation.

• Convergence Security Journal
• /
• v.7 no.3
• /
• pp.95-100
• /
• 2007

Alternate Data Streams (ADS) in NTFS originally has developed to provide compatibility with Macintosh Hierarchical File System. However, it is being used by the malware writers in order to support hiding malwares or data for the purpose of anti-forensics. Therefore identifying if hidden ADSs exist and extracting them became one of the most important component in computer forensics. This paper proposes a method to detect ADSs using MFT information. Experiment reveals that proposed method is better in performance and detection rate then others. This method supports not only identification of ADSs which are being used by the operating systems but also investigation of both live systems and evidence images. Therefore it is appropriate for using forensic purpose.