• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.200-208
• /
• 2022

In this study, an automatic information collection system and geographic information construction algorithm for the transportation disadvantaged using electric mobility aids are implemented using an object recognition model. Recognizes objects that the disabled person encounters while moving, and acquires coordinate information. It provides an improved route selection map compared to the existing geographic information for the disabled. Data collection consists of a total of four layers including the HW layer. It collects image information and location information, transmits them to the server, recognizes, and extracts data necessary for geographic information generation through the process of classification. A driving experiment is conducted in an actual barrier-free zone, and during this process, it is confirmed how efficiently the algorithm for collecting actual data and generating geographic information is generated.The geographic information processing performance was confirmed to be 70.92 EA/s in the first round, 70.69 EA/s in the second round, and 70.98 EA/s in the third round, with an average of 70.86 EA/s in three experiments, and it took about 4 seconds to be reflected in the actual geographic information. From the experimental results, it was confirmed that the walking weak using electric mobility aids can drive safely using new geographic information provided faster than now.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.681-692
• /
• 2017

In recent years, large-scale construction projects such as road pavement construction and new city construction have been carried out nationwide with by the expansion of social overhead facilities and base on the economic development planning, resulting in a rapid increase in artificial slope damage. The existing vegetation-based re-installation method of the slope surface greening method reveals various problems such as lack of bonding force, drying, and lack of organic matter. In this study, research was carried out using vegetation-based material and environmentally friendly soil additives, were are used in combination with natural humus, Bark compost, coco peat, and vermiculite. Uniaxial compressive strength was measured according to the mixing ratio of soil additives and the strength was analyzed. Experiments were carried out on the characteristics of the soil material to gauge the slope protection properties by using the soil compaction test method wherein the soil and the soil additive materials are mixed in relation to the soil height, the number of compaction, the compaction method (layer) and the curing condition. As a result of the experiment, excellent strength performance was demonstrated in soil additives using gypsum cement, and it satisfied vegetation growth standards by using performance enhancer and pH regulator. It was confirmed that the strength increases with the mixing of soil and soil additive, and the stability of slope protection can be improved.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.285-295
• /
• 2023

With the development of technology, efforts to reduce the exposure dose received by patients in CT scans are continuing with the development of new reconstruction techniques. Recently, deep learning reconstruction techniques have been developed to overcome the limitations of repetitive reconstruction techniques. This study aims to evaluate the usefulness of images according to reconstruction techniques in pediatric chest CT images. Patient study conducted a study on 85 pediatric patients who underwent chest CT scan at P-Hospital in Gyeongsangnam-do from January 1, 2021 to December 31, 2022. The phantom used in the Phantom Study is the Pediatrics Whole Body Phantom PBU-70. After the test, the images were reconstructed with FBP, ASIR-V (50%) and DLIR (TF-Medium, High), and the images were evaluated by obtaining SNR and CNR values by setting ROI of the same size. As a result, TF-H of deep learning reconstruction techniques had the lowest noise value compared to ASIR-V (50%) and TF-M in all experiments, and SNR and CNR had the highest values. In pediatric chest CT scans, TF images with deep learning reconstruction techniques were less noisy than ASiR-V images with adaptive statistical iterative reconstruction techniques, CNR and SNR were higher, and the quality of images was improved compared to conventional reconstruction techniques.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.1
• /
• pp.9-20
• /
• 2023

For highway concrete structures, the deterioration of the structure is accelerated due to the increase in the use of deicing materials, and sectional repair work is being frequently carried out to restore performance. However, after the repair work, re-damage such as cracks, delamination, and poor bond performance is exhibited in the repaired sectional area. In this study, overseas repair material requirements were first analyzed, and present domestic requirements were improved repair material performance through field surveys of common concrete structures, laboratory experiments, and test construction on a disused concrete bridge. In addition, performancebased quality requirements were presented so that all materials that meet the required performance can be applied, and different test methods for each material were unified into concrete test methods for consistent test results analysis. The considered performance requirements were compression strength, bending strength, and bond strength for structural properties, and length change rate, crack resistance, thermal expansion coefficient, and elasticity coefficient were for dimensional behavior. For resistance to chloride penetration resistance and freeze-thaw resistance were presented as durability. The proposed requirements for concrete repair materials are expected to contribute to the improvement of the quality of concrete sectional repair work in Korea.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2021.04a
• /
• pp.24-24
• /
• 2021

The Cassava (Manihot esculenta Crantz) is one of the major food crops in the tropical or subtropical regions. Recently, clean planting materials of improved cassava cultivars are in high demand. Problems in the propagation of cassava are virus vulnerable and low rates of seed germination. Thus, the study was undertaken to develop an efficient in vitro mass propagation protocol of Manihot esculenta Crantz. So we tried to optimize protocols for mass production from axillary buds of Cassava. Young and actively growing stem segments were excised from adult plants of cassava. Samples were cut into a 3~4 cm nodal segments with axillary buds, and cultivated in the different medium supplemented with various plant growth regulators for 4 weeks. For shoot multiplication, axillary buds approximately 1 cm in length were taken from in vitro derived shoots and subcultured. After 4~6 weeks, the shoot generation rate showed 55.6%. The shoot number and its length was 1.0/explant and 2.3 cm in the most favorable medium composition. The auxin β-indolebutyric acid(IBA) 0~2.0 mg/L was proved to be effective on root development. Plantlets with fibrous roots easily generated tuberous roots in vitro. The tuberous roots were induced only when both kinetin and IBA were used in combination. after 8 weeks, the root generation rate showed 100%. The root number and its length was 17.2/explant and 2.2 cm in the most promising medium composition. Our experiments confirmed that in vitro growth and multiplication of plantlets could depend on its reaction to the different medium composition, and this micropropagation techniques could be a useful system for healthy and vigorous plant production.

• Journal of Venture Innovation
• /
• v.5 no.2
• /
• pp.85-99
• /
• 2022

Dryers becoming commercially available for experimental and industrial use are classified to general drying oven, hot-air dryer, vacuum dryer, freezing dryer, etc. and kinds of them are various from the function, size and volume, etc. But the moisture measurement is not applied although it is important factor for the quality control and the performance improvement of products, and then now is very passive because the weight is weighed arbitrarily after dry-end. Generally the method for measuring moisture is divided by a direct measurement method and a indirect measurement method, and the former such as the change of weight or volume on the front and rear of separation of moisture, etc. is mainly used. Relatively a indirect measurement is very limited to apply due to utilize measurement apparatuses using temperature conductivity and micro-wave etc. In this research, we easily designed the moisture measurement system using the open-source based Arduino, and monitored moisture fluctuations and weight profiles in the real-time without the effect of external environment. Concretely the temperature-humidity and load cell sensors were packaged into a drying oven and the various change values were measured, and their sensors capable to operate 60℃ and 80℃ were selected to suitable for the moisture sensitive materials and the food dry. And also the performance safety using the organic samples of banana, pear, sawdust could be secured because the changes of evaporation rate as the dry time and temperature, and the measurement values of load cell appeared stable response characteristics through repeated experiments. Hereafter we judge that the reliability can be improved increasingly through the expansion of temperature-humidity range and the comparative analysis with CFD(Computational Fluid Dynamics) program.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.445-454
• /
• 2023

Recently, various fault diagnosis studies are being conducted utilizing data from collaborative robots. Existing studies performing fault diagnosis on collaborative robots use static data collected based on the assumed operation of predefined devices. Therefore, the fault diagnosis model has a limitation of increasing dependency on the learned data patterns. Additionally, there is a limitation in that a diagnosis reflecting the characteristics of collaborative robots operating with multiple joints could not be conducted due to experiments using a single motor. This paper proposes an LSTM diagnostic model that can overcome these two limitations. The proposed method selects representative normal patterns using the correlation analysis of vibration and current data in single-axis and multi-axis work environments, and generates residual patterns through differences from the normal representative patterns. An LSTM model that can perform gear wear diagnosis for each axis is created using the generated residual patterns as inputs. This fault diagnosis model can not only reduce the dependence on the model's learning data patterns through representative patterns for each operation, but also diagnose faults occurring during multi-axis operation. Finally, reflecting both internal and external data characteristics, the fault diagnosis performance was improved, showing a high diagnostic performance of 98.57%.