# Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices

arXiv: https://arxiv.org/abs/2509.01371 · HTML: https://mlsanity.com/paper/2509.01371/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 57 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [Efficient ConvNet-based Object Detection for Unmanned Aerial Vehicles by Selective Tile Processing](https://mlsanity.com/paper/1911.06073/) (2019)
- [Fast and accurate object detection in high resolution 4K and 8K video using GPUs](https://mlsanity.com/paper/1810.10551/) (2018)
- [Amadeus: Scalable, Privacy-Preserving Live Video Analytics](https://mlsanity.com/paper/2011.05163/) (2020)

## Built on by (most cited first, 1 of 1)

- [DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms](https://mlsanity.com/paper/2604.25300/) (2026)

## Abstract (arXiv)

Real-time video analytics on high-resolution cameras has become a popular technology for various intelligent services like traffic control and crowd monitoring. While extensive work has been done on improving analytics accuracy with timing guarantees, virtually all of them target static viewpoint cameras. In this paper, we present Uirapuru, a novel framework for real-time, edge-based video analytics on high-resolution steerable cameras. The actuation performed by those cameras brings significant dynamism to the scene, presenting a critical challenge to existing popular approaches such as frame tiling. To address this problem, Uirapuru incorporates a comprehensive understanding of camera actuation into the system design paired with fast adaptive tiling at a per-frame level. We evaluate Uirapuru on a high-resolution video dataset, augmented by pan-tilt-zoom (PTZ) movements typical for steerable cameras and on real-world videos collected from an actual PTZ camera. Our experimental results show that Uirapuru provides up to 1.45x improvement in accuracy while respecting specified latency budgets or reaches up to 4.53x inference speedup with on-par accuracy compared to state-of-the-art static camera approaches.