# Tiny-YOLO object detection supplemented with geometrical data

arXiv: https://arxiv.org/abs/2008.02170 · HTML: https://mlsanity.com/paper/2008.02170/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Few-shot Adaptive Object Detection with Cross-Domain CutMix](https://mlsanity.com/paper/2208.14586/) (2022)
- [From Tiny Machine Learning to Tiny Deep Learning: A Survey](https://mlsanity.com/paper/2506.18927/) (2025)
- [Precision and Adaptability of YOLOv5 and YOLOv8 in Dynamic Robotic Environments](https://mlsanity.com/paper/2406.00315/) (2024)
- [Webcam-based Pupil Diameter Prediction Benefits from Upscaling](https://mlsanity.com/paper/2408.10397/) (2024)
- [Starkit: RoboCup Humanoid KidSize 2021 Worldwide Champion Team Paper](https://mlsanity.com/paper/2110.08377/) (2021)
- [LTV-YOLO: A Lightweight Thermal Object Detector for Young Pedestrians in Adverse Conditions](https://mlsanity.com/paper/2601.11662/) (2026)

## Abstract (arXiv)

We propose a method of improving detection precision (mAP) with the help of the prior knowledge about the scene geometry: we assume the scene to be a plane with objects placed on it. We focus our attention on autonomous robots, so given the robot's dimensions and the inclination angles of the camera, it is possible to predict the spatial scale for each pixel of the input frame. With slightly modified YOLOv3-tiny we demonstrate that the detection supplemented by the scale channel, further referred as S, outperforms standard RGB-based detection with small computational overhead.