• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.255-264
• /
• 2011

In this paper, we propose a forward vehicle detection algorithm using column detection and bird's-eye view mapping based on stereo vision. The algorithm can detect forward vehicles robustly in real complex traffic situations. The algorithm consists of the three steps, namely road feature-based column detection, bird's-eye view mapping-based obstacle segmentation, obstacle area remerging and vehicle verification. First, we extract a road feature using maximum frequent values in v-disparity map. And we perform a column detection using the road feature as a new criterion. The road feature is more appropriate criterion than the median value because it is not affected by a road traffic situation, for example the changing of obstacle size or the number of obstacles. But there are still multiple obstacles in the obstacle areas. Thus, we perform a bird's-eye view mapping-based obstacle segmentation to divide obstacle accurately. We can segment obstacle easily because a bird's-eye view mapping can represent the position of obstacle on planar plane using depth map and camera information. Additionally, we perform obstacle area remerging processing because a segmented obstacle area may be same obstacle. Finally, we verify the obstacles whether those are vehicles or not using a depth map and gray image. We conduct experiments to prove the vehicle detection performance by applying our algorithm to real complex traffic situations.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.89-103
• /
• 2020

As we face an aging society, the demand for personal mobility for disabled and aged people is increasing. In fact, as of 2017, the number of electric wheelchair in the country continues to increase to 90,000. However, people with disabilities and seniors are more likely to have accidents while driving, because their judgment and coordination are inferior to normal people. One of the causes of the accident is the interference of personal vehicle steering control due to unbalanced road surface conditions. In this paper, we introduce a encoder type semantic segmentation algorithm that can recognize road conditions at high speed to prevent such accidents. To this end, more than 1,500 training data and 150 test data including road surface damage were newly secured. With the data, we proposed a deep neural network composed of encoder stages, unlike the Auto-encoding type consisting of encoder and decoder stages. Compared to the conventional method, this deep neural network has a 4.45% increase in mean accuracy, a 59.2% decrease in parameters, and an 11.9% increase in computation speed. It is expected that safe personal transportation will be come soon by utilizing such high speed algorithm.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.93-106
• /
• 2021

Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1398-1400
• /
• 1996

In this paper, a method of the decision of the road direction for ALV(Autonomous Land Vehicle) road following by region-based segmentation is presented. The decision of the road direction requires extracting road regions from images in real-time to guide the navigation of ALV on the roadway. Two thresholds to discriminate between road and non-road region in the image are easily decided, using knowledge of problem region and polygonal approximation that searches multiple peaks and valleys in histogram of a road image. The most likely road region of the binary image is selected from original image by these steps. The location of a vanishing point to indicate the direction of the road can be obtained applying it to X-Y profile of the binary road region again. It can successfully steer a ALV along a road reliably, even in the presence of fluctuation of illumination condition, bad road surface condition such as hidden boundaries, shadows, road patches, dirt and water stains, and unusual road condition. Pyramid structure also saves time in processing road images and a real-time image processing for achieving navigation of ALV is implemented. The efficacy of this approach is demonstrated using several real-world road images.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.71-79
• /
• 2019

By using convolutional neural networks (CNNs) based on semantic segmentation, road surface damage detection has being studied. In order to generate the CNN model, it is essential to collect the input and the corresponding labeled images. Unfortunately, such collecting pairs of the dataset requires a great deal of time and costs. In this paper, we proposed a road surface damage detection technique based on semi-supervised learning using pseudo labels to mitigate such problem. The model is updated by properly mixing labeled and unlabeled datasets, and compares the performance against existing model using only labeled dataset. As a subjective result, it was confirmed that the recall was slightly degraded, but the precision was considerably improved. In addition, the $F_1-score$ was also evaluated as a high value.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.939-951
• /
• 2022

The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1509-1516
• /
• 2017

In first-person perspective training system, the users needs realistic experience. For providing this experience, the system should offer the users virtual and real images at the same time. We propose an automatic a persons's arm segmentation and image composition method. It consists of arm segmentation part and image composition part. Arm segmentation uses an arbitrary image as input and outputs arm segment or alpha matte. It enables end-to-end learning because we make use of FCN in this part. Image composition part conducts image combination between the result of arm segmentation and other image like road, building, etc. To train the network in arm segmentation, we used arm images through dividing the videos that we took ourselves for the training data.

• 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.26 no.2
• /
• pp.165-173
• /
• 2008

This study aims at generating automatically three dimensional geometric models of roads using LIDAR data and a digital map. The main processes in the proposed method are (1) generating a polygon encompassing a road region using a road layer from the digital map, (2) extracting LIDAR points within the road region using the polygon, (3) organizing the points into surface patches and grouping the patches into surface clusters, (4) searching the road surface clusters and generating the surface model from the points linked to the clusters, (5) refining the boundary using a digital map. By applying the proposed method to real data, we successfully generated the linear and surface information of the roads.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.871-879
• /
• 1997

The comversion of printed maps into computerixed data bases is an enormous rask. Thus the autmaotion of the conversion process is essential. Efficient computer representation of printed maps and line drawings depends on codes assigened to chracaters, symbools, and vestor representation of the graphics. In many cases, maps ard constructed in a number of layers, where each layer is printed in a distinct color, and it represents a subste of the map infromation. In order to properly repressnet road information from color map images, an automatic road extraction algorithm is proposed. Road image is separated from graghics by color segmentation, and then restored by the proposed concurrent conditional dilation operation. The internal and external noise of the road image is eliminated by opening and closing operation. By thining and vectorizing line segments, the desited road information is extracted.