Hybrid Deep Learning Object Detection Algorithm for Autonomous Vehicles with Hybrid Optimization Technique

In order to improve accuracy and efficiency in object detection tasks, this research study introduces a novel hybrid object detection deep learning technique that combines Convolutional Neural Networks (CNN) with Support Vector Machines (SVM). The suggested approach combines the strong classification ability of SVMs with the feature extraction capabilities of CNNs to provide a more efficient detection model. To further optimize the performance, a hybrid optimization algorithm is introduced, combining the Hybrid Bat AlgorithmGrey Wolf Optimizer (HBA-GWO) and Aquila Variabilis Optimizer-Particle Swarm Optimization (AVO-PSO). The HBA-GWO algorithm exploits the exploration abilities of the Bat Algorithm and the exploitation capabilities of the Grey Wolf Optimizer to efficiently search the solution space. In contrast, the AVO-PSO hybrid algorithm combines the strengths of the Aquila Variabilis Optimizer’s dynamic search strategies with the Particle Swarm Optimization’s global convergence ability. The integration of these two hybrid optimization strategies aims to fine-tune the hyperparameters of the CNN-SVM model, thereby enhancing detection accuracy and reducing computational costs. Experimental results on standard object detection benchmarks demonstrate the superior performance of the proposed hybrid model in terms of precision, recall, and F1 score and mAP compared to traditional deep learning and optimization methods. This research highlights the potential of hybrid models in advancing the field of object detection through the synergistic combination of machine learning algorithms and optimization techniques.