• Smart Media Journal
• /
• v.11 no.11
• /
• pp.25-31
• /
• 2022

Deep learning-based image processing is essential for autonomous vehicles. To process road images in real-time in a System-on-Chip (SoC) environment, we need to execute deep learning models on a NPU (Neural Procesing Units) specialized for deep learning operations. In this study, we imported seven open-source image processing deep learning models, that were developed on GPU servers, to Texas Instrument Deep Learning (TIDL) NPU environment. We confirmed that the models imported in this study operate normally in the SoC virtual environment through performance evaluation and visualization. This paper introduces the problems that occurred during the migration process due to the limitations of NPU environment and how to solve them, and thereby, presents a reference case worth referring to for developers and researchers who want to port deep learning models to SoC environments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7385-7392
• /
• 2014

Extension IFC schema of subsidiary facilities were developed for the purpose of establishing an information model standard for roads. The IFC entities, types and properties for subsidiary facilities were defined through an analysis of the road design documents for the extraction physical component and design information. The converter and viewer for applying the new schema were then developed. Subsidiary facilities BIM models were converted to new IFC models to verify the research results. Standard BIM-based delivery and verification systems are enabled by using a standard model converted by new schema. Furthermore, it can establish an open BIM environment using an IFC over the entire life cycle of the civil engineering project.

• Journal of Auto-vehicle Safety Association
• /
• v.7 no.4
• /
• pp.26-30
• /
• 2015

Exceeding the speed limit during vehicle driving is a key factor in the severity of lots of road accidents, and SLIF(Speed Limit Information Function) application is in the initial phase in Korea. SLIF helps the drivers to observe a speed limit when they are driving by providing alert and informing the current limit speed information based on external data using camera and/or digital map, for that reason, environmental conditions could be causes of SLIF malfunctions. In this study, design adequacy analysis of SLIF in respect of false recognition as the Korea traffic environment has been performed. As tentative results, road conditions and structure of speed limit sign as well as system performance often caused misrecognition.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.29 no.5
• /
• pp.51-59
• /
• 2001

This paper presents a design of the Dasan Children\`s Park which is located Shindang- dong, lung-gu, Seoul which has an area of about 3,678$m^2$. Objectives for the design were to make nature-friendly space, learning space, interesting play space, space for every child, adventure play space, traditional play space, sense of place, and recycle space. For the space compositions a children\`s garden, a traditional play space, and a science play space were located around the S shaped main route. Facilities relating nature, science, culture. environment and adventure play were arranged in the 3 main spaces. The Children\`s Garden is a green space for learning and playing with natural elements. It is composed of a ecological learning space, a children\`s story garden, a children\`s song road, an environmental labyrinth, and a pall space leer handicap children. The Science Play Place is a place space for learning scientific theories through plays to which scientific theories were applied. It is composed of a total play structure, a math experience playground, a \"Keojunggi\" play space, a sound reflecting experience space, arid an infant playground. The Traditional Play Madang(space) is a space for traditional plays. It is composed of a traditional play pattern, a sun dial, and a floor fountain. The Recycle Road is a dragon shaped road fort learning about resource recycling and conservation. It is composed of a dragon head, body, tail space and a dragon bead(cint mani).int mani).

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.725-730
• /
• 2005

In case of the national roads which is opened in the past, there are carried out the expansion and improvement for enlargement of the traffic demand by industrial development and safety road operation to narrow of road width and serious change of the road alignment with effect of topography and graphical features of a mountain. A protection method using vegetation in the cut-slope has been constructed for harmony of ambient environment after cutting the slope recently. But it requires a study because the surface lose and the failure have been occurred in the large cut-slope which is covered by vegetation. In this study it was presented a countermeasure and examined a stability of contained uncertainty in the cut-slope according to the failure example of the cut-slope which is covered by vegetation. The additional research will be necessary against the development of the investigation technique which executes the stability investigation of the cut-slope which is covered by vegetation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.5
• /
• pp.453-464
• /
• 2012

This is a research of an adaptive longitudinal control system for situated cognition in wide range, traffic accidents reduction and safety driving environment by integrated system which graft a road infrastructure's information based on IT onto the intelligent vehicle combined automobile and IT technology. The road infrastructure installed by laser scanner in intersection, speed limited area and sharp curve area where is many risk of traffic accident. The road infra conducts objects recognition, segmentation, and tracking for determining dangerous situation and communicates real-time information by Ethernet with vehicle. Also, the data which transmitted from infrastructure supports safety driving by integrated with laser scanner's data on vehicle bumper.

• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.536-545
• /
• 2013

In this study, an integrated motor control algorithm for an in-wheel electric vehicle is suggested. It consists of slip control that controls the in-wheel motor torque using the road friction coefficient and slip ratio; yaw rate control that controls the in-wheel motor torque according to the road friction coefficient and the yaw rate error; and velocity control that controls the vehicle velocity by a weight factor based on the road friction coefficient and the yaw rate error. A co-simulator was developed, which combined the vehicle performance simulator based on MATLAB/Simulink and the vehicle model of CarSim. Based on the co-simulator, a human-in-the-loop simulation environment was constructed, in which a driver can directly control the steering wheel, the accelerator pedal, and the brake pedal in real time. The performance of the integrated motor control algorithm for the in-wheel electric vehicle was evaluated through human-in-the-loop simulations.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.5 no.1
• /
• pp.19-27
• /
• 2002

To investigate the dominant species and factors related with plant coverage by road structures and forest environment factors, forest roads elapsed from one year to twelve year after construction had been selected in six county(Gochang-gun, Muju-gun, Imsil-gun, Jangsu-gun, Jeongup-shi and Jinan-gun), and 20m segments were continuously set up in each road. The results obtained from this study are summarized as follows: The species diversity of Gochang, Muju, Imsil, Jangsu, Jeongup and Jinan were 1.304, 1.267, 1.308, 1.193, 1.289 and 1.018, respectively. In process of years, plant coverage was increased gradually and average of plant coverage was 15.3% in forest roads which elapsed three year, and was 86.5% in forest roads which elapsed nine year after construction. The dominant species in the cutting slope of surveyed area were covered with Arundinella hirta, Pinus rigida, Miscanthus sinensis var. purpurascens, Artemisia princeps var. orientalis, Pinus densiflora, Oplismenus undulatifolius, Rubus coreanus, Lysimachia clethroides, Lespedeza bicolor, and Alnus hirsuta of the 152 species. The high correlated factors between plant coverage and variables in cutting slopes appeared elapsed year, soil hardness, mean annual precipitation, vertical grade, inslope and arid humidity in surveyed area.

• KIEAE Journal
• /
• v.14 no.3
• /
• pp.55-63
• /
• 2014

This study selected and analyzed filter media that can be applied in non-point pollution reduction devices aimed at processing the source of pollution on site for road runoff that increases rapidly in rainfall-runoff in order to improve the water quality of urban areas. First, the factors that affect the quality of runoff caused by sources of non-point pollution include physical and social factors such as the usage of land around the area of water collection, type of pavement and movement of cars and people, as well as rainfall characteristics such as frequency, intensity, amount and duration of rainfall. Second, the purification tests of the filter media were processed for pH, BOD, COD and T-P, and the filter media showed to have initial purification effect at that items. However, the filter media showed to be very effective for the processing of SS, T-N, Zn and Cd from the beginning to the end. Third, for filter media, zeolite and vermiculite showed to be effective for processing SS, T-N, Zn and CD constantly, and composite filter media including zeolite showed to have strong processing effects. The authors conclude that this study can be applied to technical areas and policies aimed at reducing non-point pollution in urban areas and can also contribute to allowing eco-friendly management of rainfall as well as improvement of water quality.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2949-2952
• /
• 2000

A new neural networks and learning algorithm are proposed in order to measure nonlinear heights of complexed road environments in realtime without pre-information. This new neural networks is Error Self Recurrent Neural Networks(ESRN), The structure of it is similar to recurrent neural networks: a delayed output as the input and a delayed error between the output of plant and neural networks as a bias input. In addition, we compute the desired value of hidden layer by an optimal method instead of transfering desired values by back-propagation and each weights are updated by RLS(Recursive Least Square). Consequently. this neural networks are not sensitive to initial weights and a learning rate, and have a faster convergence rate than conventional neural networks. We can estimate nonlinear models in realtime by ESRN and learning algorithm and control nonlinear models. To show the performance of this one. we control 7 degree of freedom full car model with several control method. From this simulation. this estimation and controller were proved to be effective to the measurements of nonlinear road environment systems.