Expanding a robot's life: Low power object recognition via FPGA-based\n DCNN deployment

2018/03/23 by Panagiotis Mousouliotis, Konstantinos Panayiotou, Mousouliotis, Panagiotis G. +7
Computer Science · Engineering · #Advanced Memory and Neural Computing #Advanced Neural Network Applications #CCD and CMOS Imaging Sensors #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.1804.00512

openalex publication_date 2018/03/23 · openalex created_date 2022/09/29 · openalex updated_date 2026/07/28

Abstract

FPGAs are commonly used to accelerate domain-specific algorithmic\nimplementations, as they can achieve impressive performance boosts, are\nreprogrammable and exhibit minimal power consumption. In this work, the\nSqueezeNet DCNN is accelerated using an SoC FPGA in order for the offered\nobject recognition resource to be employed in a robotic application.\nExperiments are conducted to investigate the performance and power consumption\nof the implementation in comparison to deployment on other widely-used\ncomputational systems.\n

Related

• Binary Neural Network in Robotic Manipulation: Flexible Object Manipulation for Humanoid Robot Using Partially Binarized Auto-Encoder on FPGA
• Robotic Computing on FPGAs: Current Progress, Research Challenges, and Opportunities
• Proposal of ROS-compliant FPGA Component for Low-Power Robotic Systems
• Real Time FPGA Based CNNs for Detection, Classification, and Tracking in Autonomous Systems: State of the Art Designs and Optimizations
• Red grape detection with accelerated artificial neural networks in the FPGA's programmable logic