Abstract
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.
Abstract (translated)
视频和图像监控中的目标检测是一项成熟但迅速发展的任务，受到了近期深度学习进展的强烈影响。这篇综述通过考察架构创新、生成模型集成以及利用时间信息来增强鲁棒性和准确性的方法，总结了现代技术。与早期调查不同的是，它根据核心架构、数据处理策略和特定于监控的挑战（如动态环境、遮挡、光照变化和实时需求）对方法进行分类。主要目标是评估语义目标检测当前的有效性，次要目标包括分析深度学习模型及其实际应用。综述涵盖了基于CNN的目标检测器、GAN辅助的方法以及时间融合方法，并强调生成模型如何支持重建缺失帧、减少遮挡及正常化照明等任务。此外，它还概述了预处理流水线、特征提取进展、基准数据集和比较评估。最后，指出了低延迟、高效且时空学习方法的新兴趋势，为未来的研究提供了方向。
URL
https://arxiv.org/abs/2601.14677
