Title
Dataset Augmentation for Detecting Small Objects in Fisheye Road Images
Authors
[ 1 ] Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ 2 ] Instytut Robotyki i Inteligencji Maszynowej, Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ SzD ] doctoral school student | [ P ] employee
Scientific discipline (Law 2.0)
[2.2] Automation, electronics, electrical engineering and space technologies
Year of publication
2026
Chapter type
chapter in monograph / paper
Publication language
english
Keywords
EN
- fisheye object detection
- small object detection
- dataset augmentation
Abstract
EN In this work, we focus on detecting small road objects in fisheye cameras using the FishEye8K dataset. The images within the FishEye8K dataset pose significant challenges due to heavy distortion and blurring. We first thoroughly analyze the dataset and then design a data augmentation pipeline tailored specifically to simulate the characteristics of FishEye8K images in other datasets. Our approach involves using fisheye distortion alongside several pixel-level transformations, which we apply to other traffic-oriented datasets like Vis-Drone, UAVDT, and WoodScape. Additionally, we employ GAN-based data augmentation techniques to transform the original dataset, simulating multiple weather and lighting conditions. Finally, we conduct a comprehensive analysis to assess the suitability of typical small object detection methods for this particular problem domain. Our method was developed for AiCityChallenge2024, and we achieved an F1 score of 58.2% on the FishEye8K test-challenge subset with the Co-DETR model trained with our data augmentation pipeline. The code is available at3.
Date of online publication
01.11.2025
Pages (from - to)
92 - 105
Ministry points / chapter
20
System created by Poznań University of Technology
and Poznan Supercomputing and Networking Center
Log in through eKonto to add to SIS