轻量级红外小目标检测模型，提升复杂场景下的精准度
ISTD-YOLO: A Multi-Scale Lightweight High-Performance Infrared Small Target Detection Algorithm
- 改进YOLOv7结构，设计三尺度轻量化网络
- 用VoV-GSCSP替代ELAN-W，降低计算开销
- 引入无参注意力机制和NWD损失，增强定位精度
针对红外图像中背景复杂、信噪比低、目标尺寸小且亮度弱带来的检测难题，提出一种基于改进YOLOv7的轻量级红外小目标检测算法ISTD-YOLO。首先对YOLOv7网络结构进行轻量化重构，设计三尺度轻量化网络架构；其次将模型颈部的ELAN-W模块替换为VoV-GSCSP，以降低计算成本和网络复杂度；然后在颈部网络中引入无参注意力机制，增强局部上下文信息的相关性；最后采用归一化Wasserstein距离（NWD）优化常用的IoU指标，提升小目标的定位与检测精度。实验结果表明，相比YOLOv7及当前主流算法，ISTD-YOLO在各项指标上均有显著提升，能够实现高质量的红外小目标检测。
原文摘要 · Abstract (English)
Aiming at the detection difficulties of infrared images such as complex background, low signal-to-noise ratio, small target size and weak brightness, a lightweight infrared small target detection algorithm ISTD-YOLO based on improved YOLOv7 was proposed. Firstly, the YOLOv7 network structure was lightweight reconstructed, and a three-scale lightweight network architecture was designed. Then, the ELAN-W module of the model neck network is replaced by VoV-GSCSP to reduce the computational cost and the complexity of the network structure. Secondly, a parameter-free attention mechanism was introduced into the neck network to enhance the relevance of local con-text information. Finally, the Normalized Wasserstein Distance (NWD) was used to optimize the commonly used IoU index to enhance the localization and detection accuracy of small targets. Experimental results show that compared with YOLOv7 and the current mainstream algorithms, ISTD-YOLO can effectively improve the detection effect, and all indicators are effectively improved, which can achieve high-quality detection of infrared small targets.
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。