Object detection is a computer vision methodology that employs deep neural networks to identify and categorize objects within images. Object detection is a pivotal technology that significantly influences the identification of vehicles and pedestrians at traffic signals, the recognition of signposts by advanced driver assistance systems (ADAS), the detection of suspicious activities and intruders in surveillance, and the monitoring of animals in agriculture, among other applications. Object detection employing traditional deep learning methodologies demands greater time and expense. Nonetheless, these drawbacks can be readily mitigated by applying quantum supremacy. The quantum machine learning (QML) model employs quantum superposition and entanglement to develop innovative solutions for the challenges encountered by classical models. Five machine learning models, namely, the Convolutional Neural Network (CNN), Quanvolutional Neural Network (QNN), Quantum Convolutional Neural Network (QCNN), Fully Connected Network (FCN), and Quantum Fully Connected Network (QFCN), are utilized for object detection, and their performance is compared. Quantum models surpass classical models, and the hybrid QFCN model demonstrates superior efficiency and accuracy compared to classical models. We have attained a quantum speedup of 82.12% through the utilization of quantum models. The research and analysis of our experiment were conducted using local simulators and quantum simulators, specifically the Tensor Network 1 (TN1) and the State Vector 1 (SV1) simulator offered by Amazon Web Services (AWS) Braket, a novel and uncharted platform.