TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation

TL;DR

TinyTracker demonstrates an ultra-fast, low-power edge vision system for gaze estimation using Sony's IMX500 sensor, achieving significant size reduction and efficiency improvements over traditional models and platforms.

Contribution

The paper introduces TinyTracker, a fully quantized, highly efficient gaze estimation model optimized for the IMX500 sensor, enabling real-time, low-power edge vision applications.

Findings

41x size reduction compared to iTracker

End-to-end latency of around 19ms on IMX500

System consumes only 4.9 mJ of energy

Abstract

Intelligent edge vision tasks encounter the critical challenge of ensuring power and latency efficiency due to the typically heavy computational load they impose on edge platforms.This work leverages one of the first "AI in sensor" vision platforms, IMX500 by Sony, to achieve ultra-fast and ultra-low-power end-to-end edge vision applications. We evaluate the IMX500 and compare it to other edge platforms, such as the Google Coral Dev Micro and Sony Spresense, by exploring gaze estimation as a case study. We propose TinyTracker, a highly efficient, fully quantized model for 2D gaze estimation designed to maximize the performance of the edge vision systems considered in this study. TinyTracker achieves a 41x size reduction (600Kb) compared to iTracker [1] without significant loss in gaze estimation accuracy (maximum of 0.16 cm when fully quantized). TinyTracker's deployment on the Sony IMX500 vision sensor results in end-to-end latency of around 19ms. The camera takes around 17.9ms to read, process and transmit the pixels to the accelerator. The inference time of the network is 0.86ms with an additional 0.24 ms for retrieving the results from the sensor. The overall energy consumption of the end-to-end system is 4.9 mJ, including 0.06 mJ for inference. The end-to-end study shows that IMX500 is 1.7x faster than CoralMicro (19ms vs 34.4ms) and 7x more power efficient (4.9mJ VS 34.2mJ)