Deepanshu Vishwakarma, Rishabh Maurya, Gaurvi Shukla, Shalini Lamba & Shweta Sinha 
Department of Computer Science
National PG College(Autonomous)
Lucknow, Uttar Pradesh-India

 Abstract–This study delves into the wide-ranging applications of computer vision in the field of object detection, tracing its development from earlier techniques based on manual feature engineering to modern deep learning models like R-CNN, YOLO, SSD, and MobileNet. It underscores how these technological strides have significantly impacted various sectors such as autonomous driving, medical diagnostics, security systems, retail analytics, industrial automation, entertainment, precision farming, sports performance analysis, environmental tracking, and supply chain logistics. Through our investigation, we demonstrate that current object detection models benefit from hierarchical feature representation and end-to-end learning, resulting in notable improvements in both precision and operational speed. The paper also explores current innovations that are expected to redefine object detection in the coming years, including the rise of vision transformers, self-supervised learning frameworks, deployment on edge devices, the ethical dimensions of AI use, and convergence with augmented and virtual reality platforms. Overall, the study concludes that as these tools evolve and find broader implementation, they are set to reshape how humans and machines interact, paving the way for more intelligent and perceptive automated systems in both commercial and industrial settings.

Keywords – Computer vision, Object detection, Deep learning, Convolutional neural networks, Artificial intelligence, Machine learning.

Download:

https://npgcij.com/wp-content/uploads/2026/01/npgcij_008_A-Systematic-Study-of-Computer-Vision-in-Object-Detection.pdf