Abstract:
Vehicle detection is one of the key factors in AI-based transport systems, in currently time with the advanced changing in image processing, computer vision, and image patterns identification in machines & deep learning has higher increased in different Moods to detect the vehicle from a few years, the machine learning algorithms SVM, Random Forest, Gradient bosting machine, KNN and gaussian mixture model further in deep learning as CNN, RNN, YOLO Faster R-CNN and Mask R-CNN algorithms specially used in vehicle detection. This paper research study provides the best algorithms for vehicle detection in different moods from the experiment research results, the SVM algorithms and RF cover 90% accuracy, in weather mood and sunny mood as relate to others algorithms of traditional methods. In the Progressive method, in deep learning YOLO acquired 95%, 94%, and 93% and 92% results in weather mood. Also, in sunny mood Faster R-CNN it contains 97%, 93%, 91% and 93% accuracy from the trained model using accuracy, Precision, Recall, and F1 Score vehicle detection accuracy; this desired output of experiment results is obtained from the 70 of 30 ratios of the dataset and implemented it to trained such algorithm's, at last from results output this study showcases the best one algorithm technique for effective output in vehicle detection.
Page(s):
32-37
DOI:
DOI not available
Published:
Journal: University of Sindh Journal of Information and Communication Technology, Volume: 7, Issue: 1, Year: 2023