• 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 the Korean Institute of Landscape Architecture
• /
• v.49 no.6
• /
• pp.37-48
• /
• 2021

Roadside pollution has been identified as the main cause of PM_2.5 in urban areas. Green infrastructure has been understood to mitigate air pollution from roadside traffic effectively, but complication depend on environmental variables. This study aimed to investigate the characteristic of PM_2.5 by the type of space in an urban park located in Songsanghyeon Plaza, surrounded by a 12-lane road on all sides. Type of space was typically classified as roadside square (A), sunken square (B), a mix of trees and hedges/shrubs (C), trees only (D), and grass square (E) according to the land-use type and layers of trees. PM_2.5 was measured for nine days, three days for three different Air Quality Forecasts-Good level (0~15㎍/m³), Moderate level (16~35㎍/m³), and Unhealthy level (36~75㎍/m³). The analysis result was as follows. At good levels, there was statistical significance in the order of D, E < B, C < A. In the case of moderate levels and unhealthy levels, D and E were statistically lower than other land-use types. The characteristic of PM_2.5 in the urban park by type of space was affected by atmospheric flow into the road. The relatively high concentration of A and C was located near the roads. Although B was far away from the road, the reason for the high concentration of PM_2.5 was that no structures blocked the air pollution. Thanks to the type of space C, filtering the air pollution from the roads, the concentration of PM_2.5 in D and E was relatively low.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.172-191
• /
• 2023

This study was undertaken to strategize the mixed traffic operation of autonomous vehicles in the pilot zone. This was achieved by analyzing the changes expected when autonomous vehicles are mixed in the autonomous vehicle pilot zone. Although finding a safe and efficient traffic operation strategy is required for the pilot zone to serve as a test bed for autonomous vehicles, there is no available operation strategy based on the mixture of autonomous vehicles. In order to presents a traffic operation strategies for each period of autonomous vehicle introduction, traffic efficiency and safety analysis was performed according to the autonomous vehicle market percentage rate. Based on the analysis results, the introduction stage was divided into introductory stage, transition period, and stable period based on the autonomous vehicle market share of 30% and 70%. This study presents the following traffic operation strategies. Considering the traffic flow operation strategy, we suggest the advancement of the existing road infrastructure at the introductory stage, and operating an autonomous driving lane and the mileage system during the transition period. We also propose expanding the operation of autonomous driving lanes and easing the speed limit during the stable period. In the traffic safety strategy, we present a manual and legal system for responding to autonomous vehicle accidents in the introductory stage, an analysis of the causes of autonomous vehicle accidents and the implementation of preventive policies in the transition period, and the advancement of the autonomous system and the reinforcement of the security system during the stable period. Through the traffic operation strategy presented in this study, we foresee the possibility of preemptively responding to the changes of traffic flow and traffic safety expected due to the mixture of autonomous vehicles in the autonomous vehicle pilot zone in the future.

• Applied Biological Chemistry
• /
• v.9
• /
• pp.125-147
• /
• 1968

This experiment was carried out as a part of the studies on reasonable application of nitrogen in rice plant to determine: (I) Nitrogen absorption. and rooting of rice seedlings as affected by urea foliar application at late seedling stage (II) Effect of leaf prunning and foliar application of urea at late heading stage on the maturation and yield of rice (III) Effect of foliar application of urea and its time during the stage of ear formation on yield of rice plant. Results obtained are summarized as follows. Exp.I: Nitrogen absorption and rooting of rice seedlings as affected be urea foliar application at late seedling stage. 1 : The foliar application of urea plots$(T_{1},T_2)$ snowed mare N-content than non-urea foliar application plot(T0) at lane seedling stage, being significant among treatments and foliar application of urea seemed more effective in increasing the N-content of seedlings. and promoted root settlement and early growth alter the transplanting. 2 : The carbon contents of the plants of $T_1$, and $T_2$ at late seedling stage increased than T0, and the carbon contents. of $T_1$ and $T_2$ plots became higher in amount in proportion to the nitrogen absorption as compared with those of $T_0$. 3 : C/N ratio appeared significant among soil application plots($N_1, \;N_2$) and foliar application of urea plots ($T_1$, $T_2$ and $T_0$). C/N ratio was lower in case of increased amount of nitrogen. The higher contents of nitrogen and carbon and lower C/N ratio resulted in the increment of root numbers and root lengths. Exp.II: Effect of leaf prunning and foliar application of urea at late heading stage on the maturation and yield of rice. 1 : There was a highly significant decrease in the maturing rate by severe leaf prunning. In the mean time, significant increase in maturing rate was observed with urea foliar application and it was found the more frequent application the more effective for higher maturing rate with a moderate significance. A correlationship between the level of prunning and maturing rate was enumerated to 0.961 of correlation coefficient, which indicated an increased maturing rate by the increased number of remaining leaves. 2 : The 1.000 grain weight, grain weight and hulled rice yield increased by leaf prunning in order (plot a$A_1$, $A_3$, $A_2$ and $A_0$ were 89.8%, 89.4%, 87.8% and 87.5% respectively, showing the highest of rate in $A_1$ and $A_3$ in methods of ear fertilization and being highly significant between its treatment. 3 : 1000 grain weights were highly significant between time of application, showing a tendency of increase of weights with the time lagging until days before earings as that of maturing rates. High significance was recognized between methods of ear fertilization, showing the highest in $A_2$ 23.18 gr. 4 : Yields per $3.3m^2$ were not significant between time of ear fertilization, whereas were highly significant between methods of ear fertilization. Those of $A_1$, $A_3$, $A_2$ and $A_0$ were 1.486 kg, 1.491 kg, 1.381 kg and 1.328 kg, respectively, showing the highest in $A_1$ and $A_3$. 5 : Hulling ratios showed significant different between time of ear fertilization, showing the highest in $T_2$, whereas those of methods of ear fertilization were highly significant between its treatment, Those of $A_1$, $A_3$, $A_2$ and $A_0$ were 84.72%, 84.06%, 83.29%, and 82.56% respectively, showing the highest m $A_2$ and $A_3$ among others. 6 : Yields of hulled rice per $3.3m^2$ showed significant different between time of ear fertilization, showing the highest in $T_1$ 1.192 kg. Whereas, those were highly significant between methods of ear fertilization. Those of $A_1$, $A_3$, $A_2$ and $A_0$ were 1.259 kg, 1.254 kg, 1.149 kg and 1.095 kg, respectively, showing the highest in $A_1$ and $A_2$. 7 : Contents of nitrogen on rice plant increased in case of nitrogen application as ear fertilizer and showed that the case of urea foliar application was more effective than that of soil application, showing the increased nitrogen content of rice plant was accompanied by carbon content.