• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.6
• /
• pp.606-616
• /
• 2022

Semantic segmentation in autonomous driving for unstructured environments is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues, we propose a deep learning framework for semantic segmentation that involves a pooled class semantic segmentation with five classes. The evaluation of the framework is carried out on two off-road driving datasets, RUGD and TAS500. The results show that our proposed method achieves high accuracy and real-time performance.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.105-115
• /
• 2011

In Vision-based Intelligent Transportation System(ITS) the segmentation of road region is a very basic functionality. Accordingly, in this paper, we propose a region segmentation method using adaptive pattern extraction technique to segment road regions and sky regions from original images. The proposed method consists of three steps; firstly we perform the initial segmentation using Mean Shift algorithm, the second step is the candidate region selection based on a static-pattern matching technique and the third is the region growing step based on a dynamic-pattern matching technique. The proposed method is able to get more reliable results than the classic region segmentation methods which are based on existing split and merge strategy. The reason for the better results is because we use adaptive patterns extracted from neighboring regions of the current segmented regions to measure the region homogeneity. To evaluate advantages of the proposed method, we compared our method with the classical pattern matching method using static-patterns. In the experiments, the proposed method was proved that the better performance of 8.12% was achieved when we used adaptive patterns instead of static-patterns. We expect that the proposed method can segment road and sky areas in the various road condition in stable, and take an important role in the vision-based ITS applications.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.249-257
• /
• 2017

This paper proposes a method to segment urban scenes semantically based on location prior information. Since major scene elements in urban environments such as roads, buildings, and vehicles are often located at specific locations, using the location prior information of these elements can improve the segmentation performance. The location priors are defined in special 2D coordinates, referred to as road-normal coordinates, which are perpendicular to the orientation of the road. With the help of depth information to each element, all the possible pixels in the image are projected into these coordinates and the learned prior information is applied to those pixels. The proposed location prior can be modeled by defining a unary potential of a conditional random field (CRF) as a sum of two sub-potentials: an appearance feature-based potential and a location potential. The proposed method was validated using publicly available KITTI dataset, which has urban images and corresponding 3D depth measurements.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.239-247
• /
• 2022

Cities are becoming more complex due to rapid industrialization and population growth in modern times. In particular, urban areas are rapidly changing due to housing site development, reconstruction, and demolition. Thus accurate road information is necessary for various purposes, such as High Definition Map for autonomous car driving. In the case of the Republic of Korea, accurate spatial information can be generated by making a map through the existing map production process. However, targeting a large area is limited due to time and money. Road, one of the map elements, is a hub and essential means of transportation that provides many different resources for human civilization. Therefore, it is essential to update road information accurately and quickly. This study uses Semantic Segmentation algorithms Such as LinkNet, D-LinkNet, and NL-LinkNet to extract roads from drone images and then apply hyperparameter optimization to models with the highest performance. As a result, the LinkNet model using pre-trained ResNet-34 as the encoder achieved 85.125 mIoU. Subsequent studies should focus on comparing the results of this study with those of studies using state-of-the-art object detection algorithms or semi-supervised learning-based Semantic Segmentation techniques. The results of this study can be applied to improve the speed of the existing map update process.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.2
• /
• pp.19-25
• /
• 2013

In this paper, we propose an approach to tracking road regions from video sequences. The proposed method segments and tracks road regions by utilizing the prior information from the result of the previous frame. For the efficiency of the system, we have a simple assumption that the road region is usually shown in the lower part of input images so that lower 60% of input images is set to the region of interest(ROI). After initial segmentation using flood-fill algorithm, we merge neighboring regions based on color similarity measure. The previous segmentation result, in which seed points for the successive frame are extracted, is used as prior information to segment the current frame. The similarity between the road region of the previous frame and that of the current frame is measured by the modified Jaccard coefficient. According to the similarity we refine and track the detected road regions. The experimental results reveal that the proposed method is effective to segment and track road regions in noisy and non-noisy environments.

• Proceedings of the KGS Conference
• /
• 2006.06a
• /
• pp.17-18
• /
• 2006

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1889-1900
• /
• 2022

Roads are an essential factor in the physical functioning of modern society. The spatial information of the road has much longer update cycle than the traffic situation information, and it is necessary to generate the information faster and more accurately than now. In this study, as a way to achieve that goal, the Pan-sharpening technique was applied to satellite images of Kompsat 3 and 3A to improve spatial resolution. Then, the data were used for road extraction using the semantic segmentation technique, which has been actively researched recently. The acquired Kompsat 3/3A pan-sharpened images were trained by putting it into a U-Net based segmentation model along with Massachusetts road data, and the applicability of the images were evaluated. As a result of training and verification, it was found that the model prediction performance was maintained as long as certain conditions were maintained for the input image. Therefore, it is expected that the possibility of utilizing satellite images such as Kompsat satellite will be even higher if rich training data are constructed by applying a method that minimizes the impact of surrounding environmental conditions affecting models such as shadows and surface conditions.

• Journal of Digital Convergence
• /
• v.12 no.1
• /
• pp.359-364
• /
• 2014

In this paper, we propose a method for extracting a road area by using the mean-shift method and connected-component method. Mean-shift method is very effective to divide the color image by the method of non-parametric statistics to find the center mode. Generally, the feature points of road are extracted by using the information located in the middle and bottom of the road image. And it is possible to extract a road region by using this feature-point and the partitioned color image. However, if a road region is extracted with only the color information and the position information of a road image, it is possible to detect not only noise but also off-road regions. This paper proposes the method to determine the road region by eliminating the noise with the closing / opening operation of the morphology, and by extracting only the portion of the largest area using a connected-components method. The proposed method is simulated and verified by applying the captured road images.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.73-82
• /
• 2021

Rural roads are the significant infrastructure for developing and managing the rural areas, hence the utilization of the remote sensing datasets for managing the rural roads is necessary for expanding the rural transportation infrastructure and improving the life quality of the rural residents. In this research, the two different methods such as image classification and image segmentation were compared for mapping the rural road based on the given high-resolution satellite image acquired in the rural areas. In the image classification method, the deep learning with the multiple neural networks was employed to the given high-resolution satellite image for generating the object classification map, then the rural roads were mapped by extracting the road objects from the generated object classification map. In the image segmentation method, the multiresolution segmentation was employed to the same satellite image for generating the segment image, then the rural roads were mapped by merging the road objects located on the rural roads on the satellite image. We used the 100 checkpoints for assessing the accuracy of the two rural roads mapped by the different methods and drew the following conclusions. The image segmentation method had the better performance than the image classification method for mapping the rural roads using the give satellite image, because some of the rural roads mapped by the image classification method were not identified due to the miclassification errors occurred in the object classification map, while all of the rural roads mapped by the image segmentation method were identified. However some of the rural roads mapped by the image segmentation method also had the miclassfication errors due to some rural road segments including the non-rural road objects. In future research the object-oriented classification or the convolutional neural networks widely used for detecting the precise objects from the image sources would be used for improving the accuracy of the rural roads using the high-resolution satellite image.