In recent times, the integration of the software engineering concepts with remote sensing technology has resulted in novel methods for vehicle classification, enabling different applications ranging from traffic management to environmental monitoring. Remote sensing images (RSI) become useful in several applications of intelligent transportation systems (ITS) like traffic prediction, vehicle classification, road classification, etc. Robust and accurate vehicle classification in ITS using RSI gains considerable attention using computer vision (CV) and deep learning (DL) approaches. However, the detection capability is restricted to the absence of well-annotated samples, particularly in dense crowded scenes. Vehicle detection and vehicle classification are the two problems commonly addressed by the CV and DL models. In this aspect, this study develops an optimal DL-based vehicle detection and classification model on ITS (ODLVDC-ITS) using RSI. The key objective of the ODLVDC-ITS method lies in the automated classification of vehicles present in the RSI. To achieve this, the ODLVDC-ITS method comprises three main processes namely vehicle detection, parameter tuning, and vehicle classification. Primarily, the ODLVDC-ITS technique employs YOLO-v5 object detector to identify the vehicles in the images and its hyperparameters can be tuned by coyote optimization algorithm. The ODLVDC-ITS technique exploits Dendritic Neural (DRN) technique for vehicle classification process. Lastly, the hyperparameter tuning of DRN model performed via Aquila optimization algorithm (AOA). The simulation outcomes of the ODLVDC-ITS method are tested on open access dataset and the outcomes are investigated under various measures. A widespread experimental analysis stated the promising performance of ODLVDC-ITS approach on vehicle classification process.