Semantic Analysis System to Recognize Moving Objects by Using a Deep Learning Model

Abstract

This study focuses on enhancing the accuracy and efficiency of semantic analysis systems for recognizing moving objects within video sequences. The primary aim is to improve object detection capabilities in dynamic environments using a hybrid model that integrates Convolutional Neural Networks (CNNs) with Support Vector Machines (SVMs). Our contribution involves developing and testing an advanced detection algorithm that utilizes the Faster Region-based Convolutional Neural Network (R-CNN) framework combined with SVM classifiers for refined object recognition and interaction assessment in complex video scenes. We implemented the system using Python 3.7 and tested it on approximately 350 video frames. The findings demonstrate that our model significantly outperforms existing methods such as Scale-Invariant Feature Transform (SIFT), Centrifugal Compressor Performance (CCP), and Local Binary Pattern (LBP) in terms of detection accuracy. The proposed model consistently outperformed traditional methods such as SIFT, CCP, and LBP across various noise levels, maintaining higher accuracy, particularly in high-noise environments. At 80% noise, the proposed model demonstrated a marked advantage in detection accuracy compared to the baseline methods. Overall, the model showcased robust performance with less degradation in accuracy even under significant processing errors, validating its effectiveness in noisy and dynamic settings.

Keywords

• R-CNN algorithm
• deep learning
• semantic analysis
• SVM classifier
• synthesis technique