• 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 Korean Society of Transportation
• /
• v.24 no.1 s.87
• /
• pp.85-94
• /
• 2006

Currently, when the military performs military operations in wartime and peace time, it is important for him to obtain repeatedly updated traffic information for security of the military supply support. The purpose of this study is to present an acquisition way of the repeatedly updated traffic information which the military is available. To achieve this Purpose, firstly, this paper finded types of traffic information which the military demanded and limitations caused by an connection of traffic information network between the military and associated government agencies. Also. grasped ITS(Intelligent Transportation systems) equipment operation by associated government agencies (Ministry Construction & Transportation, Korea Highway Corporation, Seoul Metropolitan Government, National Police Agency, Korea Institute of Construction Technology) and connection situations of traffic information network among associated government agencies. On the basis of these materials, this study presented the most efficient connection method in the field of the space and the contents of traffic information between the military and associated government agencies and ITS connection system between the military and associated government agencies was contrived. Throughout the upper processes, this paper showed a method which is available for acquiring ITS traffic information of associated government agencies. In addition to the connection method of ITS traffic information network, resolutions for the problems caused by connection of ITS network were come up with. But the more deep study for this matter is needed since resolutions for the problems of the ITS network connection, which this paper presented, were very restricted.

• Journal of Advanced Navigation Technology
• /
• v.17 no.4
• /
• pp.404-412
• /
• 2013

Network RTK is widely used especially for static applications so far, however, the demand for high accuracy positioning for kinetic users such as land vehicles is growing for safety and convenience reasons. Kinematic users move along the roads and the network where they receive corrections can be changed. Compact Network RTK corrections should keep consistency while network change. In this paper, we introduced a method of generating Compact Network RTK corrections considering network ambiguity level adjustment by formulation of corrections. We verified the proposed method for reference station networks across whole country. We also generated Compact Network RTK corrections using simulation and real GPS data from reference stations in South Korea and evaluated performance of users. As a result, the discontinuity between corrections from two networks reduced to 0.25 cycle from several cycles. And user could achieve less than 8 cm (2DRMS) horizontal position accuracy continuously regardless of network change.

• Journal of the Korean Geographical Society
• /
• v.41 no.5 s.116
• /
• pp.582-599
• /
• 2006

Due to the growing popularity of mobile information technology, more people, especially in the general public, have access to computerized geospatial information systems for wayfinding tasks or urban navigation. One of the problems with the current services is that, whether the users are exploring or navigating, whether they are travelers who are totally new to a region or long-term residents who have a fair amount of regional knowledge, the same method is applied and the direction are given in the same way. However, spatial knowledge for a given urban region expands in proportion to residency. Urban navigation is highly dependent on cognitive mental images, which is developed through spatial experience and social communication. Thus, the wayfinding service for a regional community can be highly supported, using well-known regional places. This research is to develop the framework for urban navigation within a regional community. The concept of communal ontology is proposed to aid in urban regional navigation. The experimental work was implemented with case study to collect regional landmarks, develop the ontological model and represent it with formal structure. The final product of this study will provide the geographical information of a region to the other agent and be the fundamental information structure for cognitive urban regional navigation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.2
• /
• pp.97-104
• /
• 2015

Due to the introduction of various IT devices, including the recently smartphones and the widespread use of the car navigation system to the location-based information service space has been increased. Spatial information users have been requiring higher levels of quality. In this paper, we study how to build accurate three-dimensional space information by integrating MMS(Moblie Mapping System) survey and airborne survey data. Thus, to analyze the tendency of deviation between the MMS survey and airborne survey data observed in the experimental region, the deviation tendency of the data, it was confirmed that was not consistent. Deviation correction model to select how to change the georeferencing information directly contained in the GPS/INS processing results for the determination, classifies the standard is a method for acquiring the correction reference point coordinates using the calibration model, and analyzed their advantages and disadvantages. With the information of the reference point obtained by airborne photograph of a project, using the method of correcting the MMS survey data. Not only clear the deviation existing between the MMS survey data, it was possible to confirm that the deviation exists between the airborne survey data and MMS survey data was also almost erased.

• The Korean Journal of Air & Space Law and Policy
• /
• v.23 no.2
• /
• pp.115-136
• /
• 2008

The development of the aviation technology is beyond the people's imagination. For example, with some exaggeration, If the autopilot engage upon take off, You will realize that you are on the centerline of the foggy JFK runway 13R after 15 hours with only once or twice of intervention. But the more aviation technology develops, the more responsible the pilot will be who has the final authority of the aviation safety. In the JAL 706 accident caused by unidentified reason, the pilot increased pitch abruptly and overrode the control from the autopilot. The result of this process made the death of a flight attendant and some injuries of a few passengers. The district court found the pilot not guilty at the first trial on the ground that the control override was not connected to the possibility of foresight and avoidance of the human death. The pilot was proved to be innocent through the analysis of the DFDR and ADAS that the override did not precede the unidentified pitch up motion. The judicial precedent related to aviation accidents in Korea requires pilots' absolute and extended care compared to the ordinarily prudent or reasonably careful behaviors in the vehicle and medical accidents. Although there is some controversy about the standard care, the care required in the actual operation of high tech aircraft by a pilot should include objective and standard care and be judged by analysis of the scientific data. Although the pilot maintained the unusual hi speed that doesn't have safety margin and descended under turbulence in case of the JAL 706 accident, the court negatived its relation to the cause of pitch up. Also, the override of the control after initial pitch up might have caused the possibility of the death and injury, but the court denied it. Because of this complex cause of the aviation accidents, it is important for a court to figure out the core reason of the event and casual relationship with the pilot Now, It is required that the judgement of negligence in the aviation accidents should include an objective care with scientific data from simulated circumstances(or a simulator) as the Japanese court not from the theory of vehicle's negligence.