<p>This systematic review deconstructs object detection research's evolution, methodology, and challenges by integrating evidence from high-impact repositories. Publication trends, dataset usage, and domination of leading venues like CVPR and ICCV in driving the field are addressed. Comparative performance assessment of YOLO, Faster R-CNN, and DETR considers their performance, scalability, and computational expense and highlights areas of hardware acceleration and real-time deployment gaps. Significant challenges such as dataset biases, computing expense, and real-time processing limitations are rigorously examined with suggested solutions. Unlike past reviews, this effort presents a structured integration of object detection advancement, clearly defining areas of research gaps and new opportunities. By introducing an unbiased overview of strengths and limitations, this review is a precious resource for researchers keen to contribute to the further advancement of object detection.</p>