• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.674-677
• /
• 2003

This work presents a method of point-to-surface assignment for 3D inspection of solder pastes on PCB. A bounding box enclosing the solder paste tightly on all sides is introduced to avoid incorrect point-to-surface assignment. The shape of bounding box for solder paste brick is variable according to geometry of measured points. The surface geometry of the bounding box is obtained by using five peaks selected from the histogram of normalized gradient vectors for measured points. By using the bounding box enclosing the solder paste. the task of point-to-surface assignment is successfully executed. Subsequently, the geometrical features are obtained via surface fitting.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.63-68
• /
• 2017

In this paper, we propose a bounding box prediction algorithm using multiple probability maps to improve object detection result of object detector. Although the performance of object detectors has been significantly improved, it is still not perfect due to technical problems and lack of learning data. Therefore, we use the result correction method to obtain more accurate object detection results. In the proposed algorithm, the preprocessed bounding box created as a result of object detection by the object detector is clustered in various form, and a conditional probability is given to each cluster to make multiple probability map. Finally, multiple probability map create new bounding box of object using morphological elements. Experiment results show that the newly predicted bounding box reduces the error in ground truth more than 45% on average compared to the previous bounding box.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.3
• /
• pp.210-220
• /
• 2003

This work presents a method of point to surface assignment fur 3D metrology of solder pastes on PCB. A bounding box enclosing the solder paste tightly on all sides is introduced to avoid incorrect assignment. The shape of bounding box fur solder paste brick is variable according to geometry of measured points. The surface geometry of bounding box is obtained by using five peaks selected in the histogram of normalized gradient vectors. By using the bounding box enclosing the solder pastes, the task of point-to-surface assignment has been successfully conducted, then geometrical features are obtained through the task of surface fitting.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.595-598
• /
• 2020

IoU (Intersection over Union) is the most commonly used index in target detection. The core requirement of target detection is what is in the image and where. Based on these two problems, classification training and positional regression training are needed. However, in the process of position regression, the most commonly used method is to obtain the IoU of the predicted bounding box and ground-truth bounding box. Calculating bounding box regression losses should take into account three important geometric measures, namely the overlap area, the distance, and the aspect ratio. Although GIoU (Generalized Intersection over Union) improves the calculation function of image overlap degree, it still can't represent the distance and aspect ratio of the graph well. As a result of technological progress, Bounding-Box is no longer represented by coordinates x,y,w and h of four positions. Therefore, the IoU can be further optimized with the center point and aspect ratio of Bounding-Box.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1658-1667
• /
• 2008

Reconstruction of 3D objects from a single view image is generally an ill-posed problem because of the projection distortion. A monocular vision based 3D object localization method is proposed in this paper, which approximates an object on the ground to a simple bounding solid and works automatically without any prior information about the object. A spherical or cylindrical object determined based on a circularity measure is approximated to a bounding cylinder, while the other general free-shaped objects to a bounding box or a bounding cylinder appropriately. For a general object, its silhouette on the ground is first computed by back-projecting its projected image in image plane onto the ground plane and then a base rectangle on the ground is determined by using the intuition that touched parts of the object on the ground should appear at lower part of the silhouette. The base rectangle is adjusted and extended until a derived bounding box from it can enclose the general object sufficiently. Height of the bounding box is also determined enough to enclose the general object. When the general object looks like a round-shaped object, a bounding cylinder that encloses the bounding box minimally is selected instead of the bounding box. A bounding solid can be utilized to localize a 3D object on the ground and to roughly estimate its volume. Usefulness of our approach is presented with experimental results on real image objects and limitations of our approach are discussed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.289-296
• /
• 2022

In this paper, we developed a deep learning-based recyclable object detection model. The model is developed based on YOLOv5 that is a one-stage detector. The deep learning model detects and classifies the recyclable object into 7 categories: paper, carton, can, glass, pet, plastic, and vinyl. We propose two methods for recyclable object detection models to solve problems during training. Bounding Box CutMix solved the no-objects training images problem of Mosaic, a data augmentation used in YOLOv5. Standardized Distance-based IoU replaced DIoU using a normalization factor that is not affected by the center point distance of the bounding boxes. The recyclable object detection model showed a final mAP performance of 0.91978 with Bounding Box CutMix and 0.91149 with Standardized Distance-based IoU.

• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.281-288
• /
• 2022

According to statistics conducted by the Korea Coast Guard, the number of accidents on small boats under 5 tons is increasing every year. This is because only a small number of people are on board. The previously developed maritime distress and safety systems are not well distributed because passengers must be equipped with additional remote equipment. The purpose of this study is to develop a distress awareness system that recognizes man over-board situations in real time. This study aims to present the part of the passenger tracking system among the small ship's distress awareness situational system that can generate passenger's location information in real time using deep learning based object detection and tracking technologies. The system consisted of the following steps. 1) the passenger location information is generated in the form of Bounding box using its detection model (YOLOv3). 2) Based on the Bounding box data, Deep SORT predicts the Bounding box's position in the next frame of the image with Kalman filter. 3) When the actual Bounding Box is created within the range predicted by Kalman-filter, Deep SORT repeats the process of recognizing it as the same object. 4) If the Bounding box deviates the ship's area or an error occurs in the number of tracking occupant, the system is decided the distress situation and issues an alert. This study is expected to complement the problems of existing technologies and ensure the safety of individuals aboard small boats.

• Korean Journal of Computational Design and Engineering
• /
• v.2 no.3
• /
• pp.161-174
• /
• 1997

In this paper, the techniques for graphic simulation of material removal process are described. The concepts of the bounding box and base plane are proposed. With these concepts, a real-time shaded display of a Z-map model being milled by a cutting tool following an NC path can be implemented very efficiently. The base planes make it possible to detect the visible face of Z-map model effectively. And the bounding box of tool sweep volume provides minimum area of screen to be updated. The proposed techniques are suitable for implementation in raster graphic device and need a few memories and a small amount of calculation. Proposed method is written in C and executable on MS-Windows95 and Window-NT.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.80-81
• /
• 2019

본 논문에서는 자연스러운 장면 영상에서 임의의 방향성을 가진 텍스트를 검출하기 위한 기법을 제안한다. 텍스트 검출을 위한 기본적인 프레임 워크는 Faster R-CNN[1]을 기반으로 한다. 먼저 RPN(Region Proposal Network)을 통해 다른 방향성을 가진 텍스트를 포함하는 bounding box를 생성한다. 이어서 RPN에서 생성한 각각의 bounding box에 대해 세 가지의 서로 다른 크기로 pooling된 특징지도를 추출하고 병합한다. 병합한 특징지도에서 텍스트와 텍스트가 아닌 대상에 대한 score, 정렬된 bounding box 좌표, 기울어진 bounding box 좌표를 모두 예측한다. 마지막으로 NMS(Non-Maximum Suppression)을 이용하여 검출 결과를 획득한다. COCO Text 2017 dataset[2]을 이용하여 학습 및 테스트를 진행하였으며 주관적으로 평가한 결과 기울어진 텍스트에 적합하게 회전된 영역을 얻을 수 있음을 확인하였다.