A comprehensive overview of deep learning models for object detection from videos/images
It provides a comprehensive overview for researchers and practitioners in surveillance, but it is incremental as it synthesizes existing methods without introducing novel findings.
This review paper tackles the problem of object detection in video and image surveillance by summarizing modern deep learning techniques, including architectural innovations and generative model integration, to enhance robustness and accuracy, though it does not present new experimental results or concrete numbers.
Object detection in video and image surveillance is a well-established yet rapidly evolving task, strongly influenced by recent deep learning advancements. This review summarises modern techniques by examining architectural innovations, generative model integration, and the use of temporal information to enhance robustness and accuracy. Unlike earlier surveys, it classifies methods based on core architectures, data processing strategies, and surveillance specific challenges such as dynamic environments, occlusions, lighting variations, and real-time requirements. The primary goal is to evaluate the current effectiveness of semantic object detection, while secondary aims include analysing deep learning models and their practical applications. The review covers CNN-based detectors, GAN-assisted approaches, and temporal fusion methods, highlighting how generative models support tasks such as reconstructing missing frames, reducing occlusions, and normalising illumination. It also outlines preprocessing pipelines, feature extraction progress, benchmarking datasets, and comparative evaluations. Finally, emerging trends in low-latency, efficient, and spatiotemporal learning approaches are identified for future research.