• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.107-113
• /
• 2023

This paper proposes a method for detecting smoking behavior in images using artificial intelligence technology. Since smoking is not a static phenomenon but an action, the object detection technology was combined with the posture estimation technology that can detect the action. A smoker detection learning model was developed to detect smokers in images, and the characteristics of smoking behaviors were applied to posture estimation technology to detect smoking behaviors in images. YOLOv8 was used for object detection, and OpenPose was used for posture estimation. In addition, when smokers and non-smokers are included in the image, a method of separating only people was applied. The proposed method was implemented using Google Colab NVIDEA Tesla T4 GPU in Python, and it was found that the smoking behavior was perfectly detected in the given video as a result of the test.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.515-518
• /
• 2003

좋은 3D 엔진이란 객체들의 상호 작용을 실세계와 유사하게 표현하는 물리라 엔진을 말하다. 충돌은 이런 상호작용 중의 하나이며, 충돌 유무 검사와, 충돌 지점, 충돌후의 반응을 다룬다. 대부분의 물리학 엔진과 같이 충돌 검사도 정확하게 검출하려면 많은 시간이 소요된다. 그래서 개발자들은 정밀도와 시간을 절충할 수 있는 기법을 사용한다. 이렇게 사용되는 기법들이 얼마만큼의 효율성을 가지는지 검증하는 방법은 많이 제시되지 않았다. 본 논문에서는 효율성의 기준을 연산 시간과 정확도로 책정했으며, 실제 개발에 적용되고 있는 알고리즘을 게임에서 발생하는 표본 상황에 적용하여 테스트 한 결과를 분석하고, 게임에 응용될 수 있는 모델을 제시한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.67-70
• /
• 2022

NLP 분야에서 적극 활용되기 시작한 Transformer 모델을 Vision 분야에서 적용하기 시작하면서 object detection과 segmentation 등 각종 분야에서 기존 CNN 기반 모델의 정체된 성능을 극복하며 향상되고 있다. 또한, label 데이터 없이 이미지들로만 자기지도학습을 한 ViT(Vision Transformer) 모델을 통해 이미지에 포함된 여러 중요한 객체의 영역을 검출하는 saliency map을 추출할 수 있게 되었으며, 이로 인해 ViT의 자기지도학습을 통한 object detection과 semantic segmentation 연구가 활발히 진행되고 있다. 본 논문에서는 ViT 모델 뒤에 classifier를 붙인 모델에 일반 학습한 모델과 자기지도학습의 pretrained weight을 사용해서 전이학습한 모델의 시각화를 통해 각 saliency map들을 비교 분석하였다. 이를 통해, 클래스 분류 학습 기반 전이학습이 transformer의 saliency map에 미치는 영향을 확인할 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.539-540
• /
• 2023

최근 물체 인식 모델의 성능을 개선하기 위한 다양한 연구가 진행 중이다. 본 논문에서는 K-means 기반 앵커박스 선정 기법을 적용한 새로운 물체 인식 모델 성능 개선 방법을 제안한다. 제안된 방법은 항만 내 설치된 컨테이너 사고를 예방하기 위한 컨테이너 사고위험도 분류 모델에 적용하여 성능 평가를 하였다. 특히, 컨테이너 사고위험도 분류 모델은 작은 물체를 인식해야 하며 이런 환경에서는 기존 물체 인식 모델 성능이 낮게 나타난다. 본 논문에서는 제안한 K-means 기반 앵커박스 선정 기법을 적용하여 물체 인식 모델 성능이 개선됨을 확인하였디.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.3
• /
• pp.23-29
• /
• 2019

Conventional crack detection methods have a problem of consuming a lot of labor, time and cost. To solve these problems, an automatic detection system is needed to detect cracks in images obtained by using vehicles or UAVs(unmanned aerial vehicles). In this paper, we have studied road crack detection with unmanned aerial photographs. Aerial images are generated through preprocessing and labeling to generate morphological information data sets of cracks. The generated data set was applied to the mask R-CNN model to obtain a new model in which various crack information was learned. Experimental results show that the cracks in the proposed aerial image were detected with an accuracy of 73.5% and some of them were predicted in a certain type of crack region.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2021

Recently, due to COVID-19, studies have been popularly worked to apply neural network to mask wearing automatic detection system. For applying neural networks, the 1-stage detection or 2-stage detection methods are used, and if data are not sufficiently collected, the pretrained neural network models are studied by applying fine-tuning techniques. In this paper, the system is consisted of 2-stage detection method that contain MTCNN model for face recognition and ResNet model for mask detection. The mask detector was experimented by applying five ResNet models to improve accuracy and fps in various environments. Training data used 17,217 images that collected using web crawler, and for inference, we used 1,913 images and two one-minute videos respectively. The experiment showed a high accuracy of 96.39% for images and 92.98% for video, and the speed of inference for video was 10.78fps.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.123-132
• /
• 2017

Traffic lights contain very important information for safety driving. So, the delivery of the information to drivers in real-time is a very critical issue for advanced driver assistance systems. However, traffic light detection is quite difficult because of the small sized traffic lights and the occlusion in real world. In this paper, a traffic light detection method using modified color based saliency map and morphological information is proposed. It shows 98.14% of precisions and 83.52% of recalls on computer simulations.

• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.107-112
• /
• 2012

An active object tracking algorithm using Pan and Tilt camera based in the stepwise application of region and color information from realtime image sequences is proposed. To reduce environment noises in input sequences, Gaussian filtering is performed first. An image is divided into background and objects by using the adaptive Gaussian mixture model. Once the target object is detected, an initial search window close to an object region is set up and color information is extracted from the region. We track moving objects in realtime by using the CAMShift algorithm which enables to trace objects in active camera with the color information. The proper tracking is accomplished by controlling the amount of pan and tilt to be placed the center position of object into the middle of field of view. The experimental results show that the proposed method is more effective than the hand-operated window method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.268-271
• /
• 2016

In video sequences, foreground object detection being composed of a background model and a background subtraction is an important part of diverse computer vision applications. However, object detection might fail in sudden illumination changes. In this letter, an illumination-robust background detection is proposed to address this problem. The method can provide quick adaption to current illumination condition using two background models with different adaption rates. Since the proposed method is a non-parametric approach, experimental results show that the proposed algorithm outperforms several state-of-art non-parametric approaches and provides low computational cost.