<br>LW-IRSTNet：轻量级红外小目标分割网络及应用部署,IEEE Transactions on Geoscience and Remote Sensing

当前位置： X-MOL 学术 › IEEE Trans. Geosci. Remote Sens. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

LW-IRSTNet：轻量级红外小目标分割网络及应用部署
IEEE Transactions on Geoscience and Remote Sensing ( IF 7.5 ) Pub Date : 2023-09-12 , DOI: 10.1109/tgrs.2023.3314586
Renke Kou ₁ , Chunping Wang ₁ , Ying Yu ₁ , Zhenming Peng ₂ , Mingbo Yang ₃ , Fuyu Huang ₁ , Qiang Fu ₁

Affiliation

从复杂的背景中高效、准确地分离红外 (IR) 小目标是一项重大挑战。文献中的大量研究提出了专门设计的各种特征融合模块，以增强红外小目标特征的提取。虽然这些设计对 IR 小目标检测的准确性提供了一些增量改进，但它们的代价是显着增加网络参数和每秒浮点运算 (FLOP)。为了力求计算效率和模型精度之间的平衡，我们决定放弃这些复杂的特征融合模块。相反，我们开发了一种新的轻量级编码和解码结构，称为轻量级红外小目标分割网络（LW-IRSTNet）。该结构集成了常规卷积、深度可分离卷积、空洞卷积和非对称卷积模块。此外，我们设计了后处理模块，包括八邻域聚类算法和在线目标特征调整策略。实验结果表明：1）LW-IRSTNet 的分割精度指标与 14 个最先进的比较基线的最佳结果相匹配； 2）LW-IRSTNet 的参数和 FLOP 分别仅为 0.16M 和 303M，与这些基线相比明显较小； 3）后处理模块增强了用户友好性和算法部署的鲁棒性。此外，LW-IRSTNet已在嵌入式平台和网站上成功实现，扩大了其应用范围。利用开放神经网络交换（ONNX）框架、神经网络处理单元（NPU）加速和CPU多线程资源分配，我们已经能够实现高性能的推理能力，以及LW-IRSTNet的在线动态阈值调整。该项目的源代码可以在 https://github.com/kourenke/LW-IRSTNet 访问。

"点击查看英文标题和摘要"

LW-IRSTNet: Lightweight Infrared Small Target Segmentation Network and Application Deployment

Efficiently and accurately separating infrared (IR) small targets from complex backgrounds presents a significant challenge. Numerous studies in the literature have proposed various feature fusion modules designed specifically to enhance the extraction of IR small target features. While these designs offer some incremental improvement to the accuracy of IR small target detection, they come at a steep cost of significantly increasing network parameters and floating-point operations per second (FLOPs). Striving for a balance between computational efficiency and model accuracy, we decided to forgo these complex feature fusion modules. Instead, we developed a new lightweight encoding and decoding structure known as the lightweight IR small target segmentation network (LW-IRSTNet). This structure integrates regular convolutions, depthwise separable convolutions, atrous convolutions, and asymmetric convolutions modules. In addition, we devised postprocessing modules, including an eight-neighborhood clustering algorithm and an online target feature adjustment strategy. Experimental results indicate that: 1) the segmentation accuracy metrics of LW-IRSTNet match the best results of 14 state-of-the-art comparative baselines; 2) the parameters and FLOPs of LW-IRSTNet at only 0.16M and 303M, respectively, are significantly smaller in comparison to these baselines; and 3) the postprocessing modules enhance both user-friendliness and the robustness of algorithm deployment. Moreover, LW-IRSTNet has been successfully implemented on both embedded platforms and websites, expanding its range of applications. Utilizing the open neural network exchange (ONNX) framework, neural network processing unit (NPU) acceleration, and CPU multithreaded resource allocation, we have been able to achieve high-performance inference capabilities, as well as online dynamic threshold adjustment with the LW-IRSTNet. The source codes for this project can be accessed at https://github.com/kourenke/LW-IRSTNet.

更新日期：2023-09-12

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南