Multiclass Vehicle Classification Across Different Environments

Vehicle detection and classification are necessary components in a variety of useful applications related to traffic, security, and autonomous driving systems. Many studies have focused on recognizing vehicles from the point of view of a single perspective, such as the rear of other cars from the driving seat, but not from all possible perspectives, including the aerial view. In addition, they are usually given prior knowledge of a specific kind of vehicle, such as the fact that it is a car, as opposed to being a bus, before deducing other information about it. One of the popular classification techniques used is boosting, where weak classifiers are combined to form a strong classifier. However, most boosting applications consider complex classification problems to be a combination of binary problems. This paper explores in detail the development of a multi-class classifier that recognizes vehicles of any type, from any view, without prior information, and without breaking the task into binary problems. Instead, a single multi-class application of the GentleBoost algorithm is used. This system is compared to a similar system built from a combination of separate classifiers that each classifies a single vehicle. The results show that a single, multi-class classifier clearly outperforms a combination of separate classifiers, and proves that a simple boosting classifier is sufficient for vehicle recognition, given any type of vehicle from any perspective of viewing, without the need of representing the problem as a complex 3D model.

@article{Azim2021,
  title     = {Multiclass Vehicle Classification Across Different Environments},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {12},
  number    = {3},
  year      = {2021},
  publisher = {The Science and Information Organization},
  author    = {Aisha S. Azim and Afshan Jafri and Ashraf Alkhairy},
  doi       = {10.14569/IJACSA.2021.0120379},
  url       = {https://doi.org/10.14569/IJACSA.2021.0120379}
}