Jonas Henrique Renolfi de Oliveira
Papers
2
Total Citations
14
H-Index
2
About
Jonas Henrique Renolfi de Oliveira is a researcher focused on the intersection of computer vision and embedded systems, specializing in making deep learning practical for resource-limited hardware. His work addresses a critical challenge in robotics and edge computing: deploying accurate object detection without relying on powerful GPUs. Oliveira’s most-cited paper, “Detecting soccer balls with reduced neural networks” (2020, 10 citations), systematically compares multiple lightweight convolutional architectures, demonstrating that state-of-the-art detection accuracy can be achieved on constrained platforms like mobile robots. His earlier study, “Object Detection under Constrained Hardware Scenarios” (2019, 4 citations), further benchmarks reduced network designs for environments where specialized hardware is unavailable. By rigorously evaluating trade-offs between model complexity and real-world performance, Oliveira provides a practical roadmap for deploying vision systems in drones, autonomous vehicles, and portable devices. His work is particularly notable for bridging the gap between high-accuracy deep learning and the strict memory, power, and processing limitations of embedded systems—a vital contribution as AI moves from data centers to the physical world.
Research Focus
Key Achievements
Top Papers
- 1
- 2