Yuta Sukizaki
Papers
1
Total Citations
4
H-Index
1
About
Yuta Sukizaki is a researcher at the forefront of applying deep learning and edge computing to critical infrastructure monitoring. His primary research focuses on computer vision for power transmission line (PTL) inspection, specifically leveraging lightweight object detection models like YOLOv3 for real-time component detection on resource-constrained devices. Sukizaki’s most cited work, "Power Transmission Line Component Detection using YOLO V3 on Raspberry Pi" (2023, 4 citations), demonstrates a practical, low-cost alternative to traditional inspection methods such as line-crawling robots or helicopters. By successfully deploying a neural network on a Raspberry Pi, he shows how edge AI can enable continuous, automated monitoring of PTL components like insulators and dampers, potentially reducing maintenance costs and improving grid reliability. This contribution is particularly notable for bridging the gap between advanced deep learning algorithms and real-world, field-deployable hardware. Sukizaki’s work highlights the growing trend of bringing intelligence directly to the sensor, making infrastructure inspection more accessible and efficient. His research is highly relevant for students and engineers interested in embedded AI, smart grids, and the practical application of computer vision in energy systems.
Research Focus
Key Achievements
Top Papers
- 1