<p>Object detection is a significant problem in the area of computer vision tasks, which has gained much attraction in recent times. The rapid breakthrough in object detection technology over the past 20 years has greatly impacted the field of computer vision. Advancements in object representation and deep neural network models have led to significant progress being made in object detection more effective. In this literature review, we present a summary of recent research on advanced detection methods for various phenomena. We classify these methods into four primary groups: traditional (non-neural) based, single-stage detector (neural-based) in which discusses all yolo versions up to version 10, two-stage detector (neural-based),transformer-based and also object detection of most papular backbone networks. We discuss the theoretical foundation of various algorithms used for object detection models and evaluate the effectiveness of different training approaches. We also consider the tradeoffs between speed and accuracy, along with other quality criteria. In this review paper, we discuss the most popular convolutional neural networks (CNNs) for the purpose of object detection. We provide an analysis of the advantages and limitations of each model. We have also included simple visual representations to help explain the enhancements made to object detection techniques through deep learning. Lastly, we have recommended some useful resources to learn about the latest research and developments in this field.</p>