# Real-time Aerial Detection and Reasoning on Embedded-UAVs

arXiv: https://arxiv.org/abs/2305.12414 · HTML: https://mlsanity.com/paper/2305.12414/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 59 references that are in the map.
- First posted on arXiv 21 May 2023.

## Builds on (most cited first, 20 of 20)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [Multi-Context Attention for Human Pose Estimation](https://mlsanity.com/paper/1702.07432/) (2017)
- [Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection](https://mlsanity.com/paper/1706.03038/) (2017)
- [Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition](https://mlsanity.com/paper/1611.09078/) (2016)
- [Recurrent Batch Normalization](https://mlsanity.com/paper/1603.09025/) (2016)
- [Detecting events and key actors in multi-person videos](https://mlsanity.com/paper/1511.02917/) (2015)
- [Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network](https://mlsanity.com/paper/1512.07928/) (2015)
- [Good Practice in CNN Feature Transfer](https://mlsanity.com/paper/1604.00133/) (2016)
- [Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks](https://mlsanity.com/paper/1709.01421/) (2017)
- [A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understanding](https://mlsanity.com/paper/2209.05222/) (2022)
- [Learning Non-Stationary Time-Series with Dynamic Pattern Extractions](https://mlsanity.com/paper/2111.10559/) (2021)
- [Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV](https://mlsanity.com/paper/1808.05756/) (2018)
- [L4KDE: Learning for KinoDynamic Tree Expansion](https://mlsanity.com/paper/2203.00975/) (2022)

## Built on by (most cited first, 3 of 3)

- [Psy-LLM: Scaling up Global Mental Health Psychological Services with AI-based Large Language Models](https://mlsanity.com/paper/2307.11991/) (2023)
- [UAVs Meet Agentic AI: A Multidomain Survey of Autonomous Aerial Intelligence and Agentic UAVs](https://mlsanity.com/paper/2506.08045/) (2025)
- [Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection](https://mlsanity.com/paper/2506.16737/) (2025)

## Abstract (arXiv)

We present a unified pipeline architecture for a real-time detection system on an embedded system for UAVs. Neural architectures have been the industry standard for computer vision. However, most existing works focus solely on concatenating deeper layers to achieve higher accuracy with run-time performance as the trade-off. This pipeline of networks can exploit the domain-specific knowledge on aerial pedestrian detection and activity recognition for the emerging UAV applications of autonomous surveying and activity reporting. In particular, our pipeline architectures operate in a time-sensitive manner, have high accuracy in detecting pedestrians from various aerial orientations, use a novel attention map for multi-activities recognition, and jointly refine its detection with temporal information. Numerically, we demonstrate our model's accuracy and fast inference speed on embedded systems. We empirically deployed our prototype hardware with full live feeds in a real-world open-field environment.