• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1184-1186
• /
• 2022

횡단보도에서의 보행자 교통사고 방지를 위한 다양한 방법들이 연구되고 있다. 본 논문에서는 점멸 신호등 상황에서 보행자 교통사고를 감소시키기 위해 영상을 이용한 심층 신경망 기반 횡단보도 보행자 검출 방법을 소개한다. YOLOv5 와 Faster R-CNN 각각을 기반으로 다양한 버전의 횡단보도 보행자 검출기를 구현하고, 이번 실험에서 중점이 되는 이들의 수행 시간을 비교 평가하고 mAP@0.5 가 어느 정도인지 판단하여 가장 적합한 모델을 판단한다. 실험 결과 실시간 처리 측면에서 YOLOs 모델이 84 fps 를 달성함으로써 실시간 보행자 검출에 가장 좋은 성능을 보였다. 횡단보도의 상황은 상시 빠르게 변하므로 가장 빠른 처리 성능을 기록한 YOLOv5s 모델이 실시간 횡단보도 보행자 검출 시스템에 가장 적합한 것으로 판단된다.

• International conference on construction engineering and project management
• /
• 2017.10a
• /
• pp.124-132
• /
• 2017

This paper describes the Around View Monitoring (AVM) system for hydraulic excavators that prevents the safety accidents caused by blind spots and increases the operational efficiency. To verify the developed system, experiments were conducted with its prototype. The experimental results demonstrate its applicability in the field with the following values: 7m of a visual range, 15fps of image refresh rate, 300ms of working information data reception rate, and 300ms of surface condition data reception rate.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.650-652
• /
• 2022

최근 데이터를 기반 응용개발이 다양한 분야에서 진행되고 있으며, 수집 데이터는 주요한 의사결정에 사용되고 있다. 이러한 데이터 기반 응용은 데이터의 무결성(data integrity)의 보장과 데이터 생산 과정에서의 진본 확인을 위한 체계가 요구된다. 본 논문에서는 영상 데이터의 무결성 검증 시스템을 구성하는 Logger 설계와 개발을 기술한다. 개발된 Logger 는 해시값을 통해 영상 데이터의 신뢰성을 만족할 수 있다면 영상 데이터를 통해 학습되어 생성된 학습 모델에 대한 신뢰성 또한 보장할 수 있다. Logger 는 라즈베리파이 환경에서 구현한 후 FPS 를 변경하며, 무결성 검증을 실험한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.35-36
• /
• 2023

Unreal Engine 5의 Level Streaming 기능은 플레이어가 플레이 도중 메모리에 Map을 로드/언 로드하는 등의 작업을 처리하는 기능이다. 이때 Level Streaming은 커다란 Map의 당장 필요한 부분에만 메모리에 로드하고, 렌더링하여 특히 Seamless Open world 장르에서 많이 사용된다. 본 논문에서 제안하는 방식은 이 Level Streaming 기능을 이용하여 현재 개발 진행 중인 Rogue-Like 장르 게임에서 비동기 방식의 로딩 화면과 Stage 전환을 통해 좀 더 부드러운, 즉 더 높은 Frames per Second(fps)를 플레이어에게 제공하기 위한 새로운 스테이지 시스템의 구현방식을 연구한다.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.621-622
• /
• 2024

본 논문은 Exemplar Transformer를 활용하여 단일 프로세서 환경에서 동작하는 시각적 객체 추적(Visual Object Tracking) 모델인 ETTrack(Exemplar Transformer Track)을 리눅스(우분투 20.04) 운영체제를 사용하는 임베디드 시스템 라떼판다 알파(LattePanda Alpha)에 탑재하였다. 데스크톱 프로세서인 Intel i7-8700와 라떼판다 알파의 Intel m3-8100y에서의 객체 추적 성능과 속도를 AUC(Area Under the ROC Curve)와 FPS를 통해서 비교평가하였다. 평가 결과 기존 트랜스포머 기반 추적 모델(TransT)과 유사한 성능, 3 FPS 빠른 추적 속도를 나타내는 것을 구현 증명하였다.

• Journal of Auto-vehicle Safety Association
• /
• v.16 no.1
• /
• pp.29-34
• /
• 2024

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.7
• /
• pp.67-77
• /
• 2016

In this paper, we propose an algorithm for open/closed eye detection based on modified Hausdorff distance. The proposed algorithm consists of two parts, face detection and open/closed eye detection parts. To detect faces in an image, MCT (Modified Census Transform) is employed based on characteristics of the local structure which uses relative pixel values in the area with fixed size. Then, the coordinates of eyes are found and open/closed eyes are detected using MHD (Modified Hausdorff Distance) in the detected face region. Firstly, face detection process creates an MCT image in terms of various face images and extract criteria features by PCA(Principle Component Analysis) on offline. After extraction of criteria features, it detects a face region via the process which compares features newly extracted from the input face image and criteria features by using Euclidean distance. Afterward, the process finds out the coordinates of eyes and detects open/closed eye using template matching based on MHD in each eye region. In performance evaluation, the proposed algorithm achieved 94.04% accuracy in average for open/closed eye detection in terms of test video sequences of gray scale with 30FPS/$320{\times}180$ resolution.

• Journal of Acupuncture Research
• /
• v.24 no.3
• /
• pp.215-229
• /
• 2007

Objectives : Placebo phenomena have been considered as a confounding factor of clinical trial. Expectancy and belief of acupuncture have not been evaluated quantitatively. The present study was performed to analyze the emotional and cognitive factor .of acupuncture and investigate whether the expectancy of acupuncture treatment is associated with the cognition of acupuncture. Methods : The expectancy and the perception of bodily sensation (PBS) of 22 participants were assessed using self-reported questionnaire. The subjects used the self assessment manikin (SAM) to rate each of the standard affective image of the international affective picture system (lAPS) and other acupuncture-related image. Based on the degree of expectancy, the high expectant (HE) and the low expectant (LE) group were classified. The thermal and pressure pain threshold was objectively evaluated using radiant-heat device and algometer. The degree of expected pain of acupuncture and the actual pain of painful stimulation was subjectively evaluated using facial pain scales (FPS). Results : Using SAlVI analysis, we identified the negative correlation between hedonic valence and arousal dimension on acupuncture-related visual cue. The degree of the PBS and general pain threshold did not show any significant difference between the HE and the LE group. The HE group rated the acupuncture images as more pleasant, more arousing, than the LE group. In addition, we also found that the higher expectancy marked the lower FPS of the expected pain of acupuncture, but not of the actual pain of painful stimulation. Conclusions : Our preliminary study identified the psychological dimensions of acupuncture-related visual cue. These findings indicate that the expectancy of acupuncture could affect the cognition of acupuncture.

• Journal of Korea Game Society
• /
• v.12 no.5
• /
• pp.79-88
• /
• 2012

In this paper, we present a real-time hand pose recognition method to provide an intuitive user interface through hand poses or movements without a keyboard and a mouse. For this, the areas of right and left hands are segmented from the depth camera image, and noise removal is performed. Then, the rotation angle and the centroid point of each hand area are calculated. Subsequently, a circle is expanded at regular intervals from a centroid point of the hand to detect joint points and end points of the finger by obtaining the midway points of the hand boundary crossing. Lastly, the matching between the hand information calculated previously and the hand model of previous frame is performed, and the hand model is recognized to update the hand model for the next frame. This method enables users to predict the hidden fingers through the hand model information of the previous frame using temporal coherence in consecutive frames. As a result of the experiment on various hand poses with the hidden fingers using both hands, the accuracy showed over 95% and the performance indicated over 32 fps. The proposed method can be used as a contactless input interface in presentation, advertisement, education, and game applications.