• Journal of the Korea Society of Computer and Information
• /
• v.14 no.8
• /
• pp.43-50
• /
• 2009

Text information in a digital video provides crucial information to acquire semantic information of the video. In the proposed method. text candidate regions are extracted from input sequence by using characteristics of stroke and text candidate regions are localized by using projection to produce text bounding boxes. Bounding boxes containing text regions are verified geometrically and each bounding box existing same location is tracked by calculating matching measure. which is defined as the mean of absolute difference between bounding boxes in the current frame and previous frames. Finally. text regions are enhanced using temporal redundancy of bounding boxes to produce final results. Experimental results for various videos show the validity of the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.50-53
• /
• 2022

In order to detect an object in yolv5, a process of annotating location information on an existing image is required when learning an image. The most representative method is to draw a bounding box on an image to store location information as meta information. However, if the boundary of the object is ambiguous, it will be difficult to make a bounding box. A representative example would be to classify parts that are not fire and parts that are fire. Therefore, in this paper, images of 100 samples judged to have caught fire were learned by varying the number of boxes. The results showed better fire detection performance in the model where the bounding box was trained by annotating it with three boxes by segmenting it slightly more than annotating it with one box by holding the edge as large as possible during annotating it with one box.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.476-478
• /
• 2023

딥러닝은 컴퓨터 비전의 상당한 발전을 기여했지만, 딥러닝 모델을 학습하려면 대규모 데이터 세트가 필요하다. 이를 해결하기 위해 데이터 증강 기술이 주목받고 있다. 본 논문에서는 객체 추출 바운딩 박스와 원본 이미지의 바운딩 박스를 결합하여 합성 데이터 생성기법을 제안한다. 원본 이미지와 동일한 범주의 데이터셋에서 참조 이미지의 객체를 추출한 다음 생성 모델을 사용하여 참조 이미지와 원본 이미지의 특징을 통합하여 새로운 합성 이미지를 만든다. 실험을 통해, 생성 기법을 통한 딥러닝 모델의 성능향상을 보여준다.

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.71-80
• /
• 2011

Recent terrain rendering applications such as 3D games and virtual reality, use GPU-based ray-casting method for rendering high-quality scenes in realtime. As the size of terrain dataset grows bigger, the rendering speed will be decreased by the increase of the number of texture samplings. To accelerate the conventional ray-casting, we propose an efficient ray casting method with subdivided bounding boxes which are based-on GPU quadtree traversal. The subdivision of the terrain's bounding box can reduce the empty spaces effectively. By performing the ray-casting with this compact bounding box, we can efficiently reduce computation with empty space skipping. Unlike the recent quadtree-based empty space skipping techniques which perform the tree traversal at each ray, our method traverses the tree only once per frame. Therefore, we can save much computational time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.562-564
• /
• 2022

조호환경이란 환자의 지속적인 추적 및 관찰이 필요한 환경으로써, 병원 입원실, 요양원 등을 의미한다. 조호환경 내 환자의 이상 증세가 발생하는 시간 및 이상 증세의 종류는 예측할 수 없기에 인력을 통한 상시 관리는 필수적이다. 또한, 환자의 이상 증세 발견 시간은 발병 시점부터의 소요 시간이 생사와 즉결되기에 빠른 발견이 매우 중요하다. 하지만, 인력을 통한 상시 관리는 많은 경제적 비용을 수반하기에 독거 노인, 빈민층 등 요양 비용을 충당하지 못하는 환자들이 수혜받는 것은 어려우며, 인력을 통해 이루어지기 때문에 이상 증세 발병 즉시 발견에 한계를 가진다. 즉, 기존까지 조호환경 내 환자 관리 방식은 경제적 비용과 이상 증세 발병 즉시 발견에 한계를 가진다는 문제점을 가진다. 따라서 본 논문은 YOLO 모델의 조호환경 내 환자 탐지 성능 비교 및 바운딩 박스 앙상블 기법을 제안한다. 이를 통해, 딥러닝 모델을 통한 환자 상시 관리가 이루어지기에 높은 경제적 비용문제를 해소할 수 있다. 또한, YOLO 모델 바운딩 박스 앙상블 기법 WBF를 통해 폐색이 짙은 조호환경 영상 데이터 내에 객체 탐지 영역 정확도 향상 방법을 연구하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.1
• /
• pp.44-52
• /
• 2008

In this paper we consider detecting collisions between characters whose motion is specified by motion capture data. Since we are targeting on massive crowd simulation, we only consider rough collisions, modeling the characters as a disk in the floor plane. To provide efficient collision detection, we introduce a hierarchical bounding volume, the Motion Oriented Bounding Box tree (MOBB tree). A MOBBtree stores space-time bounds of a motion clip. In crowd animation tests, MOBB trees performance improvements ranging between two and an order of magnitude.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1141-1147
• /
• 2020

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.93-101
• /
• 2023

In this paper, we propose a method of creating a 3D bounding box for an object using a vanishing point to increase the accuracy of object recognition in an image when recognizing an traffic object using a video camera. Recently, when vehicles captured by a traffic video camera is to be detected using artificial intelligence, this 3D bounding box generation algorithm is applied. The vertical vanishing point (VP1) and horizontal vanishing point (VP2) are derived by analyzing the camera installation angle and the direction of the image captured by the camera, and based on this, the moving object in the video subject to analysis is specified. If this algorithm is applied, it is easy to detect object information such as the location, type, and size of the detected object, and when applied to a moving type such as a car, it is tracked to determine the location, coordinates, movement speed, and direction of each object by tracking it. Able to know. As a result of application to actual roads, tracking improved by 10%, in particular, the recognition rate and tracking of shaded areas (extremely small vehicle parts hidden by large cars) improved by 100%, and traffic data analysis accuracy was improved.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.05a
• /
• pp.1329-1330
• /
• 2010

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.280-287
• /
• 2023

Deep learning advancements can solve computer vision problems, but large-scale datasets are necessary for high accuracy. In this paper, we propose an image generation technique using object bounding boxes and image edge components. The object bounding boxes are extracted from the images through object detection, and image edge components are used as input values for the image generation model to create new image data. As results of experiments, the images generated by the proposed method demonstrated similar image quality to the source images in the image quality assessment, and also exhibited good performance during the deep learning training process.