Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
Authors:
- Julian MoosmannJMJulian Moosmann
- Pietro BonazziPBPietro Bonazzi
- Yawei LiYLYawei Li
- Sizhen BianSBSizhen Bian
- Philipp MayerPMPhilipp Mayer
- Michele MagnoMMMichele Magno
Preprint
Abstract
Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- 7 J/inference end-to-end gesture recognition from dynamic vision sensor data using ternarized hybrid convolutional neural networksFuture Generation Computer Systems, 2023
- Deep learning based object detection for resource constrained devices: Systematic review, future trends and challenges aheadNeurocomputing, 2023
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- Adopting smart glasses responsibly: potential benefits, ethical, and privacy concerns with Ray-Ban storiesAI and Ethics, 2022
- A Review of Yolo Algorithm DevelopmentsProcedia Computer Science, 2022
- Pruning and quantization for deep neural network acceleration: A surveyNeurocomputing, 2021
- A wearable biosensing system with in-sensor adaptive machine learning for hand gesture recognitionNature Electronics, 2020
- Augmented reality smart glasses for operators in production: Survey of relevant categories for supporting operatorsProcedia CIRP, 2020
- Computer vision algorithms and hardware implementations: A surveyIntegration, 2019
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009