• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 춘계학술대회
• /
• pp.152-156
• /
• 2011

AVM(Around View Monitoring) 시스템은 차량 주변에 대한 영상을 운전자에게 제공함으로써 안전 운전을 도와주는 시스템이다. 측면 거울이나 실내 거울을 통해서 볼 수 없는 사각 지대는 운전자의 안전 운행에 위협이 된다. 사각지대는 특히 후진 주행, 주차, 좁은 골목길 주행, 굽은 길 회전 등에서 차량 파손 및 인사 사고의 원인이 된다. 이러한 위험을 피하기 위해 후방의 장애물을 감지하는 후방 센서나 후방 카메라 등과 같은 운전자의 시야를 개선하는 ECU들이 개발되어 사용되고 있다. 이러한 ECU들의 도움을 받더라도 차량의 전, 후, 좌, 우 사방의 상황을 동시에 볼 수 없기 때문에 사고를 피하기 위해 운전자들은 주의를 기울여 운전해야 한다. 본 논문에서는 운전자의 안전 운행을 돕기 위해 차량 주변 영상을 실시간으로 제공하는 4SM 시스템을 설계하고 구현한다. 본 논문에서 제안하는 4SM 시스템은 차량의 전, 후, 좌, 우에 장착된 4대의 카메라로부터 입력된 영상을 통합하여 Bird's Eye View 영상을 운전자가 한 눈에 차량 주변 상황을 인식할 수 있도록 한다.

• International Journal of Automotive Technology
• /
• 제7권3호
• /
• pp.361-367
• /
• 2006

This paper describes a novel stereo vision based localization of free parking site, which recognizes the target position of automatic parking system. Pixel structure classification and feature based stereo matching extract the 3D information of parking site in real time. The pixel structure represents intensity configuration around a pixel and the feature based stereo matching uses step-by-step investigation strategy to reduce computational load. This paper considers only parking site divided by marking, which is generally drawn according to relevant standards. Parking site marking is separated by plane surface constraint and is transformed into bird's eye view, on which template matching is performed to determine the location of parking site. Obstacle depth map, which is generated from the disparity of adjacent vehicles, can be used as the guideline of template matching by limiting search range and orientation. Proposed method using both the obstacle depth map and the bird's eye view of parking site marking increases operation speed and robustness to visual noise by effectively limiting search range.

• Advances in Automotive Engineering
• /
• 제1권1호
• /
• pp.143-152
• /
• 2018

In this study an economical image stitching algorithm for use in automotive industry is developed for retrofittable panoramic image assistance applications. The aim of this project is to develop a driving assistance system known as Panoramic Parking Assistance (PPA) which is cheap, retrofittable and compatible for every type of automobiles. PPA generates bird's eye view image using cameras installed on the automobiles. Image stitching requires to get bird's eye view position of the vehicle. Panoramic images are wide area images that cannot be available by taking one shot, attained by stitching the overlapping areas. To achieve correct stitching many algorithms are used. This study includes some type of these algorithms and presents a simple one that is economical and practical. Firstly, the mathematical model of a wide view of angle camera is provided. Then distorted image correction is performed. Stitching is implemented by using the SIFT and SURF algorithms. It has been seen that using such algorithms requires complex image processing knowledge and implementation of high quality digital processors, which would be impracticle and costly for automobile use. Thus a simpler algorithm has been developed to decrase the complexity. The proposed algorithm uses one matching point for every couple of images and has ease of use and does not need high power processors. To show the efficiency, images coming from four distinct cameras are stitched by using the algorithm developed for the study and usability for automotive application is analyzed.

• 대한임베디드공학회논문지
• /
• 제17권1호
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• 한국정보기술학회 영문논문지
• /
• 제10권2호
• /
• pp.167-175
• /
• 2020

In this paper, we propose a traffic accident detection on vehicle-mounted camera. In the proposed method, the minimum bounding box coordinates the central coordinates on the bird's eye view and motion vectors of each vehicle object, and ego-motions of the vehicle equipped with dash-cam are extracted from the dash-cam video. By using extracted 4 kinds features as the input of Bi-LSTM (bidirectional LSTM), the accident probability (score) is predicted. To investigate the effect of each input feature on the probability of an accident, we analyze the performance of the detection the case of using a single feature input and the case of using a combination of features as input, respectively. And in these two cases, different detection models are defined and used. Bi-LSTM is used as a cascade, especially when a combination of the features is used as input. The proposed method shows 76.1% precision and 75.6% recall, which is superior to our previous work.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.71-72
• /
• 2020

본 논문에서는 자동차 블랙박스를 사용하여 촬영된 비디오에서 자동차 사고 발생 여부를 판단하는 방법을 제안한다. 제안한 방법은 우선 객체 추적 과정에서 구한 조감도 좌표를 사용하여 각 차량 사이의 거리에 기반을 두고 교통사고 여부를 판단한다. 그런데 거리만을 사용하여 사고 여부를 판단하는 경우 자동차가 밀집된 주·정차 환경에서는 오검출의 확률이 높아질 수 있다. 이를 위해 각 차량에 대한 움직임 벡터를 계산하고 벡터 간의 정보(사잇각과 크기 등)를 사용하여 차량의 주·정차 여부를 판단한 후 사고 검출 대상에서 배제할 수 있도록 한다. 주·정차 판단 여부를 통해 사고 검출의 정확도를 향상할 수 있는 것을 실험적으로 확인하였다.

• 한국의류학회지
• /
• 제36권8호
• /
• pp.828-836
• /
• 2012

This study provided the data for the planning of knit apparel by analyzing structural effects of intarsia and jacquard knit on mechanical properties, subjective hand measurements, and preference. Intarsia and 7 types of color jacquard (floating jacquard, normal jacquard, bird's eye jacquard, tubular jacquard, ladder's back jacquard, blister jacquard, and transfer jacquard) were used. The samples (with a gauge of 14) were knitted using 100% wool 2/48's yarn by a Shima Seiki SIG computer knitting machine. Mechanical properties and hand values were measured by a KES-FB system. Subjective hand and favorable images were surveyed based on women in their 20s and 30s. The data were analyzed by a factor analysis, ANOVA and correlation analysis using SPSS 12.0. The subjective hand of intarsia and jacquard knits was categorized into 'thermofeeling', 'weight/flexibility', and 'durability'. The results of the favorable image survey for F/W outer knitwear showed that tubular jacquard was most favorable; however, the transfer jacquard was least favorable. Among the three factors that explain the subjective hand, thermofeeling had a strong influence on the favorable image of consumers. Bird's eye jacquard and tubular jacquard turned out to be most suitable for suits, intarsia and floating jacquard were suitable for cardigans and sweaters, ladder's back jacquard was suitable for hats or mufflers, and transfer jacquard was suitable for home fashion rather than garments.

• 한국의류학회지
• /
• 제31권9_10
• /
• pp.1475-1486
• /
• 2007

This study aims to develop knitted ware design to meet desire to express diversity in the modern fashion design so that we designed knitted ware by applying african geometric pattern and color to suggest new knitted ware design. We collect data about african texture pattern through technical books, publications, internet, and preceding research and visit and investigate the African museum. We investigate knitted Jacquard texture through preceding research and collect sample and data which is insufficient in the data source. The conclusions in this study are summarized as follows: First, African textile pattern is formulated with animism based on their religious view of art for a basis and African regards nature like animal and plant as a motive and interprets nature in the so that they can create symbolized geometric features that constitute African texture pattern. Those patterns is composed of extremely geometric figures so that they we fit to apply for color jacquad knit design. Second, color knitted jacquad can be distinguished by knitting method and status of knitting as 7 kinds of techniques such as Nomal, Bird'eye, Floating, Tubular, Ladder's back, Blister, Transfer Jacquard, and as a result of preceding research and knitting texture directly, jacquard technique makes different texture under same condition like consistent spinning rate and same crochet hook. Third, Bird'eye Jacquard used generally to make knitted ware and Ladder's back Jacquard, Tubular Jacquard used to make knitted ware light are fit to apply them to 7GG and 12GG machines. We design a cloak as a outer garment, a coat shaped like one-piece dress and a coat with hood by using Tubular Jacquard which can make thick texture and design a jacket, a skirt and a one-piece dress by using Bird'eye Jacquard. we make a light and flimsy one-piece dress by using Ladder's back Jacquard. Fourth, we apply the contrast of $4{\sim}6$ color and line and the contrast of texture and raw material to jacquard in order to emphasize texture property and visual property.

• 한국의상디자인학회지
• /
• 제17권4호
• /
• pp.77-90
• /
• 2015

This study is to designed to provide foundation for knit design which can apply the thickness and flexibility of jacquard knit by analyzing and comparing mechanical properties of 7 types of jacquard (normal jacquard, bird's eye jacquard, floating jacquard, tubular jacquard, ladder's back jacquard, blister jacquard, transfer jacquard) widely used in knit design to achieve the results. The sample was projected by using 7 gauge and SES-122S type computer knitting machine house tooth pattern with two colors were applied to 7 types of jacquard using Acrylic/Wool(30%/70%) $2/50.5^{\prime}s{\times}4ply\;yarn$ by Shimaseiki MFG., Ltd computer knitting machine. The mechanical properties of 7 types of jacquard samples were measured using KES-FB (Kawabata Evaluation System for Fabric, Kata Tech Co. Ltd). HV(Hand Value) and THV (Total Hand Value) were calculated by using the formula of KN-402-KT and KN-301-WINTER respectively. The measurements were evaluated by 0-to-5 rating scale. As result, the floating jacquard was found to have excellent drape, making it suitable for express feminine silhouette with its most flexible and smooth touch. On the other hand, bird's eye jacquard is adequate for a suit jacket and coat regarding its excellent volume and flexibility. Blister jacquard and tubular jacquard are thick, heavy and stiff knit and both are suitable for simple box-style design. Ladder's back jacquard, however, is more appropriate for expressing the design of feminine charm and voluminous design. Based on the result of this study, it is supposed to provide basic information for development of knit industry regarding jacquard knit by designing the creative knit wear with high production efficiency.