# MOSAIC: Spatially-Multiplexed Edge AI Optimization over Multiple Concurrent Video Sensing Streams

arXiv: https://arxiv.org/abs/2305.03222 · HTML: https://mlsanity.com/paper/2305.03222/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2023.

## Built on by (most cited first, 2 of 2)

- [PixelGen: Rethinking Embedded Camera Systems](https://mlsanity.com/paper/2402.03390/) (2024)
- [Mondrian: On-Device High-Performance Video Analytics with Compressive Packed Inference](https://mlsanity.com/paper/2403.07598/) (2024)

## Abstract (arXiv)

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and complexity of DNN models. One promising approach involves criticality-aware processing, where the computation is directed selectively to critical portions of individual image frames. We introduce MOSAIC, a novel system for such criticality-aware concurrent processing of multiple vision sensing streams that provides a multiplicative increase in the achievable throughput with negligible loss in perception fidelity. MOSAIC determines critical regions from images received from multiple vision sensors and spatially bin-packs these regions using a novel multi-scale Mosaic Across Scales (MoS) tiling strategy into a single canvas frame, sized such that the edge device can retain sufficiently high processing throughput. Experimental studies using benchmark datasets for two tasks, Automatic License Plate Recognition and Drone-based Pedestrian Detection, show that MOSAIC, executing on a Jetson TX2 edge device, can provide dramatic gains in the throughput vs. fidelity tradeoff. For instance, for drone-based pedestrian detection, for a batch size of 4, MOSAIC can pack input frames from 6 cameras to achieve (a) 4.75x higher throughput (23 FPS per camera, cumulatively 138FPS) with less than 1% accuracy loss, compared to a First Come First Serve (FCFS) processing paradigm.