Measurement-driven Analysis of an Edge-Assisted Object Recognition System
This work addresses system-level optimization for real-time object recognition in edge computing, though it appears incremental as it builds on existing methods with specific parameter tuning.
The study tackled the trade-offs between latency and accuracy in an edge-assisted object recognition system by optimizing transmission delay and analyzing the effects of image encoding rate and neural network size, achieving at least 33% better performance over standard methods through careful tuning.
We develop an edge-assisted object recognition system with the aim of studying the system-level trade-offs between end-to-end latency and object recognition accuracy. We focus on developing techniques that optimize the transmission delay of the system and demonstrate the effect of image encoding rate and neural network size on these two performance metrics. We explore optimal trade-offs between these metrics by measuring the performance of our real time object recognition application. Our measurements reveal hitherto unknown parameter effects and sharp trade-offs, hence paving the road for optimizing this key service. Finally, we formulate two optimization problems using our measurement-based models and following a Pareto analysis we find that careful tuning of the system operation yields at least 33% better performance for real time conditions, over the standard transmission method.