Deputy General Manager (R&D) | CC Ventures | South Korea
Mr. HyungJun Jin is a dedicated researcher in computer vision and robotics with strong expertise in precision agriculture and intelligent robotic systems. He holds a background in Mechanical Design Engineering and Electronics and Information Engineering with excellent academic records, further strengthened by a master’s thesis focused on deep learning-based semantic segmentation for crop–weed identification. His professional experience includes contributing to multi-sensor monitoring systems for livestock housing, intelligent weeding robots for farmland, and AI-based environmental sensing and disease detection systems in crops and livestock. His research interests span computer vision, deep learning, autonomous robotics, agricultural intelligence, and smart farming technologies aimed at improving efficiency and sustainability. He has been recognized with the President’s Award for Academic Excellence and the Outstanding Paper Award at ICROS, highlighting his research excellence and innovation. Skilled in deep learning frameworks such as TensorFlow, Keras, and PyTorch, as well as robotics systems like ROS2, Jetson Nano, and Arduino, he combines theoretical knowledge with practical implementation in various interdisciplinary projects. He also possesses strong programming and simulation skills, along with experience in datasets, model construction, and sensor integration for real-world applications. His contributions reflect a commitment to advancing AI-driven robotics for agriculture and livestock industries. He has 37 citations, 3 documents, and an h-index of 3.
Profiles: Google Scholar | Scopus
Featured Publications
Ilyas, T., Jin, H., Siddique, M. I., Lee, S. J., Kim, H., & Chua, L. (2022). DIANA: A deep learning-based paprika plant disease and pest phenotyping system with disease severity analysis. Frontiers in Plant Science, 13, 983625.
Lee, J., Ilyas, T., Jin, H., Lee, J., Won, O., Kim, H., & Lee, S. J. (2022). A pixel-level coarse-to-fine image segmentation labelling algorithm. Scientific Reports, 12(1), 8672.
Jin, H. J., & Kim, H. S. (2021). A study on paprika disease detection with YOLOv4 model using a customed pre-training method. In Proceedings of the 2021 21st International Conference on Control, Automation and Systems (ICCAS) (pp. xxx–xxx). IEEE.
Jin, H., & Kim, H. (2021). Weed label data generation using image thresholding method. Proceedings of the Institute of Control, Robotics and Systems Regional Conference, 74.
Jin, H., Kim, S., & Kim, H. (2020). Comparison of accuracy on CIFAR-10 datasets according to depth of ResNet network. Proceedings of the Institute of Control, Robotics and Systems National Conference, 108–109.
