Vehicle make and model recognition using mixed sample data augmentation techniques

Abstract

<span lang="EN-US">Vehicle identification based on make and model is an integral part of an intelligent transport system that helps traffic monitoring and crime control. Much research has been performed in this regard, but most of them used manual feature extraction or ensemble convolution neural networks that result in increased execution time during inference. This paper compared three deep learning models and utilized different augmentation techniques to achieve state-of-the-art performance without ensembling or fusing the models. Experimentations are made without any augmentation, with standard augmentation, and by mixed sample data augmentation techniques. Gradient accumulation and stochastic weighted averaging with mixed precision are used to have a large batch size that helped to reduce training time. The dataset comprised 48 vehicles’ models running on the road of Pakistan. The highest accuracy and F1 score of 97% and 95% using the FMix augmentation technique with EfficientNetV2-S architecture gave the confidence that the proposed solution can be implemented in production. </span>

Ensemble Multifeatured Deep Learning Models and Applications: A Survey

“…Computer vision is a rapidly evolving field that aims to enable machines to interpret and understand still and stereo visual information from the surrounding world [40]. The primary goal of computer vision is to develop algorithms and techniques that can automatically extract meaningful information from images and videos, such as object recognition [41], scene understanding [2], and motion analysis [42]. However, computer vision faces several challenges, such as variations in lighting conditions, occlusions, and complex cluttered backgrounds [43], which make it difficult to achieve accurate and robust results.…”