综述视频图像目标检测的深度学习方法，涵盖架构、时序信息与生成模型应用。
A comprehensive overview of deep learning models for object detection from videos/images
- 按核心架构与数据处理策略分类，梳理主流检测方法
- 指出生成模型可修复缺失帧、缓解遮挡与光照变化问题
- 适合关注目标检测在复杂监控场景中应用的研究者
视频与图像监控中的目标检测是一项成熟但快速发展的任务，受深度学习进展显著推动。本文综述现代技术，重点分析架构创新、生成模型融合及时间信息利用对鲁棒性与精度的提升。不同于以往综述，本工作基于核心架构、数据处理策略及监控特有挑战（如动态环境、遮挡、光照变化、实时性要求）进行分类。主要目标是评估语义目标检测当前有效性，次要目标包括分析深度学习模型及其实际应用。涵盖基于CNN的检测器、GAN辅助方法与时序融合策略，强调生成模型在重建缺失帧、减轻遮挡、归一化光照等方面的作用。同时介绍预处理流程、特征提取进展、基准数据集与对比评估结果。最后识别低延迟、高效及时空学习等未来研究趋势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。