• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.5
• /
• pp.443-450
• /
• 2014

To fulfill the recent increasement in the public and private demands for various spatial data, the central and local governments started to produce those data. The low-level land cover map has been produced since 2000, yet the production of high-level land covered map has started later in 2010, and recently, a few regions was completed recently. Although many studies have been carried to improve the quality of land that covered in the map, most of them have been focused on the low-level and mid-level classifications. For that reason, the study for high-level classification is still insufficient. Therefore, in this study, we suggested the automatic extraction of land readjustment for paddy land that updated in the mid-level land mapping. At the study, the RapidEye satellite images, which consider efficient to apply in the agricultural field, were used, and the high pass filtering emphasized the outline of paddy field. Also, the binary images of the paddy outlines were generated from the Otsu thresholding. The boundary information of paddy field was extracted from the image-to-map registrations and masking of paddy land cover. Lastly, the snapped edges were linked, as well as the linear features of paddy outlines were extracted by the regional Hough line extraction. The start and end points that were close to each other were linked to complete the paddy field outlines. In fact, the boundary of readjusted paddy fields was able to be extracted efficiently. We could conclude in that this study contributed to the automatic production of a high-level land cover map for paddy fields.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.718-729
• /
• 2006

There has been increasing interest in automatic term recognition (ATR), which recognizes technical terms for given domain specific texts. ATR is composed of 'term extraction', which extracts candidates of technical terms and 'term selection' which decides whether terms in a term list derived from 'term extraction' are technical terms or not. 'term selection' is a process to rank a term list depending on features of technical term and to find the boundary between technical term and general term. The previous works just use statistical features of terms for 'term selection'. However, there are limitations on effectively selecting technical terms among a term list using the statistical feature. The objective of this paper is to find effective features for 'term selection' by considering various aspects of technical terms. In order to solve the ranking problem, we derive various features of technical terms and combine the features using machine-learning algorithms. For solving the boundary finding problem, we define it as a binary classification problem which classifies a term in a term list into technical term and general term. Experiments show that our method records 78-86% precision and 87%-90% recall in boundary finding, and 89%-92% 11-point precision in ranking. Moreover, our method shows higher performance than the previous work's about 26% in maximum.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.687-696
• /
• 2014

This paper presents a semantic object extraction method using user's stroke input, color, and depth information. It is supposed that a semantically meaningful object is surrounded with a few strokes from a user, and has similar depths all over the object. In the proposed method, deciding the region of interest (ROI) is based on the stroke input, and the semantically meaningful object is extracted by using color and depth information. Specifically, the proposed method consists of two steps. The first step is over-segmentation inside the ROI using color and depth information. The second step is semantically meaningful object extraction where over-segmented regions are classified into the object region and the background region according to the depth of each region. In the over-segmentation step, we propose a new marker extraction method where there are two propositions, i.e. an adaptive thresholding scheme to maximize the number of the segmented regions and an adaptive weighting scheme for color and depth components in computation of the morphological gradients that is required in the marker extraction. In the semantically meaningful object extraction, we classify over-segmented regions into the object region and the background region in order of the boundary regions to the inner regions, the average depth of each region being compared to the average depth of all regions classified into the object region. In experimental results, we demonstrate that the proposed method yields reasonable object extraction results.

• Membrane Journal
• /
• v.21 no.2
• /
• pp.171-176
• /
• 2011

Membrane fouling is formed due to pore blocking and cake formation by suspended material or contaminant in the membrane boundary layer. Membrane fouling is main obstacle for the wider application of industrial water treatment. The objective of this paper is to study the direct monitoring technique for the measuring the membrane fouling in real time. We investigated the extracted image of R, G, and B by visible light irradiation of 360 nm wavelength to measure the membrane fouling in real time by transparent foulant. The intensity of B of 400~499 nm wavelength range was stronger than that of R and G. The fluorescence image extraction analysis appeared to be a very attractive technique for monitoring the membrane fouling in real time.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.625-630
• /
• 2009

Researches of image-based 3D reconstruction have recently produced a number of good results, but they assumed that the accurate foreground to be reconstructed is already extracted from each input image. This paper proposes a novel approach to extract more accurate foregrounds by iteratively performing foreground extraction and 3D reconstruction in a manner similar to an EM algorithm on regions segmented in an initial stage, called segments. Here, the segments should preserve foreground boundaries to compensate for the boundary errors generated by visual hull, simple 3D reconstruction to minimize the computational time, and should also be composed of the small number of sets to minimize the user input. Therefore, we utilize image segmentation using the graph-cuts method, which minimizes energy function composed of data and smoothness terms, and the two methods are iteratively performed until the energy function is optimized. In the experiments, more accurate results of the foreground, especially in boundaries, were obtained, although the proposed method used a simple 3D reconstruction method.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1239-1246
• /
• 2015

Cell counting is extensively used to analyze cell growth in biomedical research, and as a result automated cell counting methods have been developed to provide a more convenient and means to analyze cell growth. However, there are still many challenges to improving the accuracy of the cell counting for cells that proliferate abnormally, divide rapidly, and cluster easily, such as cancer cells. In this paper, we present an automated cell counting method for HeLa cells, which are used as reference for cancer research. We recognize and classify the morphological conditions of the cells by using a cell segmentation algorithm based on cell membrane extraction, and we then apply a cell back-tracking algorithm to improve the cell counting accuracy in cell clusters that have indistinct cell boundary lines. The experimental results indicate that our proposed segmentation method can identify each of the cells more accurately when compared to existing methods and, consequently, can improve the cell counting accuracy.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.253-264
• /
• 2009

This paper presents an algorithm, aims at practical applications, for the high speed processing and performance enhancement of lane detection base on vision processing system. As a preprocessing for high speed lane detection, the vanishing line estimation and the optimal extraction of region of interest for lane boundary (ROI-LB) can be processed to reduction of detection region in which high speed processing is enabled. Image feature information is extracted only in the ROI-LB. Road lane is extracted using a non-parametric model fitting and Hough transform within the ROI-LB. With simultaneous processing of noise reduction and edge enhancement using the Laplacian filter, the reliability of feature extraction can be increased for various road lane patterns. Since outliers of edge at each block can be removed with clustering of edge orientation for each block within the ROI-LB, the performance of lane detection can be greatly improved. The various real road experimental results are presented to evaluate the effectiveness of the proposed method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.3 s.33
• /
• pp.59-67
• /
• 2005

Building information is primary source in many applications such as mapping, telecommunication, car navigation and virtual city modeling. While aerial CCD images which are captured by passive sensor(digital camera) provide horizontal positioning in high accuracy, it is far difficult to process them in automatic fashion due to their inherent properties such as perspective projection and occlusion. On the other hand, LIDAR system offers 3D information about each surface rapidly and accurately in the form of irregularly distributed point clouds. Contrary to the optical images, it is much difficult to obtain semantic information such as building boundary and object segmentation. Photogrammetry and LIDAR have their own major advantages and drawbacks for reconstructing earth surfaces. The purpose of this investigation is to automatically obtain spatial information of 3D buildings by fusing LIDAR data with aerial CCD image. The experimental results show that most of the complex buildings are efficiently extracted by the proposed method and signalize that fusing LIDAR data and aerial CCD image improves feasibility of the automatic detection and extraction of buildings in automatic fashion.

• Fire Science and Engineering
• /
• v.20 no.3 s.63
• /
• pp.15-20
• /
• 2006

In this study the flow characteristics of smoke and heat on a bank type platform of the underground subway station are studied numerically by considering two different emergency operation modes. Effects of the natural flow through the tunnel and the stair ways are considered in the numerical simulations by using the measured velocities presented in Part I as the boundary condition. Distributions of heat, smoke, visible range and toxic gas on the platform are analysed for different smoke extraction flowrates corresponding to the two different emergency operation modes. The numerical results show that the extraction flowrate affects the smoke control performance significantly by improving the smoke removal performance as the extraction flowrate is increased.