Enhancing Multi-Object Detection in Video Content: Exploring Hybrid Techniques and Method Combinations for Improved Classification Accuracy

Abstract

The classification of objects within video content holds significant importance, particularly in the context of automated visual surveillance systems. Object classification refers to the procedure of categorizing objects into predefined and semantically meaningful groups based on their features. While humans find object classification in videos to be straightforward, machines face complexity and challenges in this task due to various factors like object size, occlusion, scaling, lighting conditions, and more. Consequently, the demand for analyzing video sequences has spurred the development of various techniques for object classification. This paper proposes hybrid techniques for multi object detection. The experimental analysis focused on a vehicles-openimages dataset containing 627 different catagories of vehicles. The results emphasize the profound impact of method combinations on image classification accuracy. Two primary methods, wavelet transformation and Principal Component Analysis (PCA), were employed alongside Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The evaluation encompassed performance metrics, including accuracy, precision, recall, specificity, and F1 score. In the analysis, Wavelet + RNN" combination consistently achieved the highest accuracy across all performance metrics, including accuracy percentage (96.76%), precision (96.76%), recall (86.32%), F1 score (87.12%), and specificity (87.43%). In addition, the hybrid classifiers were subjected for image classification of different vehicle catagories. In the analysis of different catagories, Wavelet + RNN" emerges as the standout performer, consistently achieving high accuracy percentages across all object categories, ranging from 82.87% for identifying People to 90.12% for recognizing Trucks.