Evaluating Compact Convolutional Neural Networks for Object Recognition Using Sensor Data on Resource-Constrained Devices

Abstract

The goal of this paper is to evaluate various compact CNN architectures for object recognition trained on a small resource-constrained platform, the NVIDIA Jetson Xavier. Rigorous experimentation identifies the best compact CNN models that balance accuracy and speed on embedded IoT devices. The key objectives are to analyze resource usage such as CPU/GPU and RAM used to train models, the performance of the CNNs, identify trade-offs, and find optimized deep learning solutions tailored for training and real-time inference on edge devices with tight resource constraints.

Keywords

• machine learning
• compact convolutional networks
• object recognition resource-constraint devices
• IoT
• sensor data processing