提升YOLOv11n在低质监控视频中儿童检测的准确性，适配真实场景
Enhancing YOLOv11n for Reliable Child Detection in Noisy Surveillance Footage
- 设计特定领域增强策略，模拟遮挡、模糊等真实干扰
- 在Roboflow Daycare数据集上实现[email protected]: 0.967，[email protected]:0.95: 0.783
- 轻量级部署，支持边缘设备实时运行，适合低成本监控系统
本文提出一种实用且轻量的解决方案，用于提升低质量监控视频中的儿童检测性能，是真实世界走失儿童预警与托育机构监控系统的关键组件。基于高效的 YOLOv11n 架构，我们构建了一个可部署的处理流程，显著改善了在遮挡、小目标、低分辨率、运动模糊和光照不良等常见于现有CCTV基础设施下的挑战性条件下的检测效果。方法引入领域特定的数据增强策略，通过空间扰动（如部分可见、截断、重叠）与光度退化（如光照变化、噪声）合成逼真的儿童位置。为提高小目标及部分遮挡实例的召回率，在推理阶段集成 Slicing Aided Hyper Inference (SAHI)。所有组件均在过滤后的仅含儿童子集的 Roboflow Daycare 数据集上训练与评估。相较于基线 YOLOv11n，增强系统在 [email protected] 达到 0.967，[email protected]:0.95 达到 0.783，绝对提升分别为 0.7% 和 2.3%，且无需修改网络结构。整个流程保持对低功耗边缘设备的兼容性，并支持实时性能，特别适用于低成本或资源受限的工业监控部署。示例增强数据集与生成代码已公开于：https://github.com/html-ptit/Data-Augmentation-YOLOv11n-child-detection
原文摘要 · Abstract (English)
This paper presents a practical and lightweight solution for enhancing child detection in low-quality surveillance footage, a critical component in real-world missing child alert and daycare monitoring systems. Building upon the efficient YOLOv11n architecture, we propose a deployment-ready pipeline that improves detection under challenging conditions including occlusion, small object size, low resolution, motion blur, and poor lighting commonly found in existing CCTV infrastructures. Our approach introduces a domain-specific augmentation strategy that synthesizes realistic child placements using spatial perturbations such as partial visibility, truncation, and overlaps, combined with photometric degradations including lighting variation and noise. To improve recall of small and partially occluded instances, we integrate Slicing Aided Hyper Inference (SAHI) at inference time. All components are trained and evaluated on a filtered, child-only subset of the Roboflow Daycare dataset. Compared to the baseline YOLOv11n, our enhanced system achieves a mean Average Precision at 0.5 IoU ([email protected]) of 0.967 and a mean Average Precision averaged over IoU thresholds from 0.5 to 0.95 ([email protected]:0.95) of 0.783, yielding absolute improvements of 0.7 percent and 2.3 percent, respectively, without architectural changes. Importantly, the entire pipeline maintains compatibility with low-power edge devices and supports real-time performance, making it particularly well suited for low-cost or resource-constrained industrial surveillance deployments. The example augmented dataset and the source code used to generate it are available at: https://github.com/html-ptit/Data-Augmentation-YOLOv11n-child-detection
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。