Douglas De Rizzo Meneghetti
Papers
2
Total Citations
14
H-Index
2
About
Douglas De Rizzo Meneghetti is a researcher specializing in computer vision and embedded systems, with a particular focus on making deep learning accessible under hardware-constrained environments. His work addresses a critical challenge in modern robotics and autonomous systems: deploying powerful neural network-based object detection on devices lacking high-performance graphics processing units. Meneghetti's most notable contributions center on the design and evaluation of reduced convolutional neural network architectures capable of achieving competitive detection accuracy without relying on specialized GPU hardware. His 2020 study on detecting soccer balls using lightweight neural networks, which has garnered 10 citations, demonstrated that state-of-the-art object detection performance can be preserved even under significant computational restrictions — a finding highly relevant to mobile robotics applications. This built upon his earlier 2019 comparative study of reduced network architectures, which further established the feasibility of efficient deep learning in resource-limited scenarios. While Meneghetti's citation record is still developing, his research tackles a genuinely pressing problem at the intersection of deep learning and embedded systems, offering practical pathways for researchers and engineers working to deploy intelligent vision systems on cost-effective, power-constrained hardware platforms.
Research Focus
Key Achievements
Top Papers
- 1
- 2