This research tackles the challenge of classifying truck vehicles using a comprehensive machine learning-based CNN algorithm approach. Initially, we collected a raw dataset of 560 images of various truck vehicles, which was expanded to 844 images through data augmentation techniques, including automatic orientation adjustments and resizing each image to 640x640 pixels. To achieve correct labeling for model training, the dataset underwent further refinement through thorough annotation. To determine which model was the most successful, a number of machine learning techniques were investigated and contrasted, including deep learning, support vector machines, and decision trees. The preprocessed dataset was used to optimize and train the selected model. We used measures like accuracy, precision, recall, and F1-score to evaluate the model's performance. The results showed that our all-inclusive algorithmic strategy outperformed conventional techniques in effectively addressing the unique difficulties of truck vehicle categorization. This study concludes that integrating advanced machine learning techniques with domain-specific knowledge in transportation results in a robust and adaptive classification system, enhancing accuracy and paving the way for broader applications in the transportation and logistics industry.