# Small Object Detection for Near Real-Time Egocentric Perception in a Manual Assembly Scenario

arXiv: https://arxiv.org/abs/2106.06403 · HTML: https://mlsanity.com/paper/2106.06403/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval](https://mlsanity.com/paper/1812.00104/) (2018)
- [Context-Aware Single-Shot Detector](https://mlsanity.com/paper/1707.08682/) (2017)
- [Egocentric Human Segmentation for Mixed Reality](https://mlsanity.com/paper/2005.12074/) (2020)
- [Performance of object recognition in wearable videos](https://mlsanity.com/paper/2009.04932/) (2020)

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

- [The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination](https://mlsanity.com/paper/2606.22574/) (2026)

## Abstract (arXiv)

Detecting small objects in video streams of head-worn augmented reality devices in near real-time is a huge challenge: training data is typically scarce, the input video stream can be of limited quality, and small objects are notoriously hard to detect. In industrial scenarios, however, it is often possible to leverage contextual knowledge for the detection of small objects. Furthermore, CAD data of objects are typically available and can be used to generate synthetic training data. We describe a near real-time small object detection pipeline for egocentric perception in a manual assembly scenario: We generate a training data set based on CAD data and realistic backgrounds in Unity. We then train a YOLOv4 model for a two-stage detection process: First, the context is recognized, then the small object of interest is detected. We evaluate our pipeline on the augmented reality device Microsoft Hololens 2.