A synthetic data approach for object detection in super low resolution images

Davoudi Kashkoli, Mosayeb and Javied, Asad and Barrera-Animas, Ari Yair and Davila Delgado, Juan Manuel (2024) A synthetic data approach for object detection in super low resolution images. In: ICIAI 2024: 2024 the 8th International Conference on Innovation in Artificial Intelligence, 16th-18th March 2024, Tokyo, Japan.

Preview

Text 3655497.3655502.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (2MB)

Abstract

This paper presents a synthetic data approach to train object detection models to address the challenges with object detection in super low-resolution images. With a particular emphasis on person detection, the study uses 28 photorealistic 3D models of individuals, optimised for efficient rendering and minimal memory consumption. These models are seamlessly integrated into a 3D terrain model, mimicking diverse real-world situations. To ensure scalability and diversity, the methodology incorporates domain randomisation techniques, encompassing variations in factors like lighting conditions, seasonal effects, camera angles, lens specifications, and different image resolutions. The process of dataset generation is automated through a Python script in Blender, offering systematic scene configuration and camera positioning. The dataset created consists of 10,560 images across four resolutions. The evaluation was carried out using popular object detection algorithms, including Faster RCNN and RetinaNet, within the Detectron2 framework. Results highlight the effectiveness of synthetic datasets in training and testing object detection algorithms, showcasing visual comparisons, Average Precision (AP) metrics, and training performance statistics. Notably, RetinaNet outperforms Faster RCNN, achieving higher accuracy. This research offers invaluable insights into synthetic dataset generation and its application for object detection in low-resolution images.

Item Type:	Conference or Workshop Item (Paper)
Identification Number:	10.1145/3655497.3655502
Dates:	Date Event 1 March 2024 Accepted 4 August 2024 Published Online
Uncontrolled Keywords:	Computer Vision, Object detection, Synthetic approaches
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
Divisions:	Faculty of Business, Law and Social Sciences > College of Business, Digital Transformation & Entrepreneurship
Depositing User:	Gemma Tonks
Date Deposited:	16 May 2025 11:41
Last Modified:	16 May 2025 11:50
URI:	https://www.open-access.bcu.ac.uk/id/eprint/16357

Actions (login required)

View Item