HSHyun-Sik Son

Hyun-Sik Son

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hyun-Sik Son has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Power Consumption Analysis and Optimal Operation Method of Wireless Multi-sensor Module

    by Hyun Sik Son, Duck-Keun Kim, Kwang Eun Ko, Seung-Hwan Yang

    Smart farms and smart factories utilize various environmental measurement and task recognition sensors. For situations requiring simultaneous measurements, a multi-sensor module that combines several sensors into one unit is advantageous. This study focuses on integrating various sensors into a single module and proposing an optimal usage method to minimize the power consumption of a wireless multi-sensor module capable of remote measurements. Analysis of the power consumption of individual sensor components revealed that when the measurement interval exceeds one minute, power consumption can be reduced by over 50.3% by turning off sensors during idle periods. If real-time responsiveness is not essential, the most efficient approach is to keep the entire module in sleep mode during these idle periods. A practical experiment was conducted using a multi-sensor module equipped with temperature and humidity, illuminance, CO2 concentration, and soil moisture sensors. When continuously powered, the module operated for 40 hours on a 3500 mAh Li-ion battery. However, by implementing sleep mode with a five-minute measurement interval, the operational duration extended to 562 hours.

  • Open Access

    Development of Soft Type Metering Device for Garlic Planter and Performance Analysis in Accordance with Design Parameters

    by Jung-Sang Yoo, Deok-Keun Kim, Hyun-Sik Son, Seung-Hwan Yang

    The main goal of a garlic planter is to plant garlic cloves individually with even spacing, requiring minimization of missed or multiple plantings. This study adopted an air-suction metering device to increase planting speed. To handle irregularly shaped garlic cloves effectively, soft silicone suction holes were fabricated and attached to the metering device. Performance was assessed by varying suction hole diameters (8, 11, 14, and 17 mm) and material hardness levels (1.4, 16.7, and 27.2 HA Shore A) at multiple-metering rates. The optimal metering rate of 98.2% was achieved with a 14 mm suction hole diameter and 16.7 HA hardness. This success was attributed to the soft suction hole effectively conforming to the garlic clove surface. The findings revealed a critical limitation: when metering rates exceeded 90%, multiple-metering rates increased linearly, indicating inherent constraints of air-suction techniques for single-seed metering. These results provide valuable insights into design parameters needed to improve reliability, operational efficiency, and mechanization performance of garlic planters. The metering device type is expected to be applicable to autonomous or unmanned agricultural machines, advancing agricultural mechanization capabilities.

  • Open Access

    Sector-Based Perimeter Reconstruction for Tree Diameter Estimation Using 3D LiDAR Point Clouds

    by Wonjune Kim, Hyun-Sik Son, Su-Yong An

    Accurate estimation of tree diameter at breast height (DBH) from LiDAR point clouds is essential for forest inventory, biomass assessment, and ecological monitoring. This paper presents a perimeter-based DBH estimation framework that achieves competitive accuracy against geometric fitting methods across three datasets. The proposed approach partitions the trunk cross-section into angular sectors and employs Gaussian Mixture Models (GMMs) to identify representative boundary points in each sector, weighted by radial proximity and statistical confidence. To handle occlusion and partial scans, missing sectors are reconstructed using symmetry-aware proxy generation. The final perimeter is modeled via either convex hull or B-spline interpolation, from which DBH is derived. Extensive experiments were conducted on two public TreeScope datasets and a custom mobile LiDAR dataset. Compared to the Density-Based Clustering Ring Extraction (DBCRE) baseline, our method reduced RMSE by 22.7% on UCM-0523M (from 2.60 to 2.01 cm), 34.3% on VAT-0723M (from 3.50 to 2.30 cm), and 29.6% on the Custom Dataset (from 2.16 to 1.52 cm). Ablation studies confirmed the individual and synergistic contributions of GMM clustering, radial consistency filtering, and proxy synthesis. Overall, the method provides a flexible alternative that reduces dependence on strict geometric assumptions, offering improved DBH estimation performance with moderate occlusion and incomplete, uneven boundary coverage.


  • Open Access

    Recognition of the Shape and Location of Multiple Power Lines Based on Deep Learning With Post-Processing

    by Hyun-Sik Son, Deok-Keun Kim, Seung-Hwan Yang, Young-Kiu Choi

    Power line collisions pose a significant threat to the safety of drones. This is because it is difficult for drone pilots to recognize power lines at long distances, even on sunny days, and power lines are less visible in rainy or foggy weather. Therefore, power line detection is necessary for safe drone flight. This article proposes an algorithm that can recognize various shapes and locations of multiple power lines while improving the recognition performance of power lines compared to previous studies. YOLO, a deep learning technology used for object detection, is used to recognize power lines as multiple bounding boxes, and center points of these bounding boxes are sorted and integrated. This algorithm improves the power line detection performance by excluding incorrectly detected power lines and restoring undetected parts of the power lines. The performance of the proposed method was evaluated using the intersection-over-union (IoU) and F1-score, which were 0.674 and 0.528, respectively. This performance was superior to those of U-Net, LaneNet and BiSeNet V2 which are deep learning technologies that segmentation. The proposed method was mounted on the embedded system of the test drone, and tests were conducted indoor and outdoor. Then, the average frames per second (FPS) value was calculated as 10.05. Various shapes and locations of multiple power lines can be recognized in real-time using the power line recognition method proposed in this paper.


  • Open Access

    Real-Time Power Line Detection for Safe Flight of Agricultural Spraying Drones Using Embedded Systems and Deep Learning

    by Hyun-Sik Son, Deok-Keun Kim, Seung-Hwan Yang, Young-Kiu Choi

    Power line detection is necessary for the safe flight of low-flying UAVs (Unmanned Aerial Vehicles). This paper deals with the power line recognition problem for the safety of agricultural spraying drones in agricultural environments. The dataset of power lines was obtained in an agricultural environment. The training dataset was constructed by labeling powerlines with bounding boxes of 6 sizes, ranging from 0.03 to 0.15 times the image. The model used for training was the tiny-YOLOv3 model. The model was verified using the mean average precision (mAP), which was used to verify the object recognition performance. Depending on the six sizes of bounding boxes, the mAPs were evaluated to be 70.22, 94.00, 86.75, 68.87, 61.65, and 53.40, respectively. The mAP was the highest at the bounding box of 0.05 times the image size, and it was confirmed that this size is most suitable for power line detection. The real-time frames per second (FPS) results of power lines detection are on average 12.5. This paper shows that the location detection of power lines is possible in real-time using deep-learning techniques with embedded systems.