Treffer: A systematic review: object detection.

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. [ABSTRACT FROM AUTHOR]

Copyright of AI & Society is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)