Object Detection in Computer Vision: A Comprehensive Review of Algorithms, Datasets, and Evaluation Techniques.
- 1School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China.
- 2Department of Engineering & Technology, Trine University, Angola, IN 46703, USA.
- 3International Project Execution and Service Center, Qingdao TGOOD Electric Co., Ltd., Qingdao 266104, China.
Abstract
Object detection has evolved dramatically over three decades, transitioning from handcrafted features to deep learning, transformers, and now large language models. This paper provides a comprehensive systematic review of this evolution, covering traditional methods (SIFT, HOG, Viola-Jones), CNN-based single- and two-stage detectors (R-CNN family, YOLO v1-v12, SSD), transformer-based architectures (DETR, ViT, Swin), and emerging LLM-driven approaches (GPT-4V, Grounding DINO, YOLO-World). We benchmark and compare these methods using key metrics-mAP, IoU, FPS-and analyze over 50 datasets across generic, autonomous driving, medical, remote sensing, and agricultural domains. Our critical synthesis identifies persistent research gaps: lightweight edge deployment, sensor fusion for real-time systems, bias and fairness in AI, and multimodal vision-language integration. By consolidating three decades of progress and outlining future challenges, this survey serves as a valuable resource for researchers and practitioners seeking to develop accurate, efficient, and reliable object detection systems.
Related
- AI-Driven Intrusion Detection for Vehicular Networks: A Comprehensive Survey of Techniques, Datasets, Deployment Architectures, and Future Directions
- Enzymatic browning in fresh-cut fruits and vegetables: a comprehensive review of biochemical etiologies, detection techniques, and control strategies.
- Comparative evaluation of fractal analysis and canny edge-detection algorithms for the quantification and classification of bone trabecular patterns in cone-beam computed tomography
- Comparative evaluation of machine learning algorithms for Maize Lethal Necrosis Disease detection under class imbalance
- Kaiser Permanente National Cross-Vendor Validation of Mammography Artificial Intelligence Computer-Aided Diagnosis Algorithms in a US-Representative Population
BibTeX
@article{rahaman2026object,
title = {{Object Detection in Computer Vision: A Comprehensive Review of Algorithms, Datasets, and Evaluation Techniques.}},
author = {Md Faishal Rahaman and Xueyuan Li and Md Nagib Mahfuz Sunny and Muhammad Amjad and Xin Gao and Sakib Hasan},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/s26206663},
url = {https://europepmc.org/article/MED/42944526},
note = {CC BY},
}
RIS
TY - JOUR
TI - Object Detection in Computer Vision: A Comprehensive Review of Algorithms, Datasets, and Evaluation Techniques.
AU - Md Faishal Rahaman
AU - Xueyuan Li
AU - Md Nagib Mahfuz Sunny
AU - Muhammad Amjad
AU - Xin Gao
AU - Sakib Hasan
PY - 2026
DA - 2026/10/21
JO - Sensors (Basel, Switzerland)
DO - 10.3390/s26206663
UR - https://europepmc.org/article/MED/42944526
AB - Object detection has evolved dramatically over three decades, transitioning from handcrafted features to deep learning, transformers, and now large language models. This paper provides a comprehensive systematic review of this evolution, covering traditional methods (SIFT, HOG, Viola-Jones), CNN-based single- and two-stage detectors (R-CNN family, YOLO v1-v12, SSD), transformer-based architectures (DETR, ViT, Swin), and emerging LLM-driven approaches (GPT-4V, Grounding DINO, YOLO-World). We benchmark and compare these methods using key metrics-mAP, IoU, FPS-and analyze over 50 datasets across generic, autonomous driving, medical, remote sensing, and agricultural domains. Our critical synthesis identifies persistent research gaps: lightweight edge deployment, sensor fusion for real-time systems, bias and fairness in AI, and multimodal vision-language integration. By consolidating three decades of progress and outlining future challenges, this survey serves as a valuable resource for researchers and practitioners seeking to develop accurate, efficient, and reliable object detection systems.
SN - 1424-8220
ER -