基于MobileNet的轻量化云检测模型
|
叶武剑(1987-),男,博士,讲师(硕士生导师),主要从事AI与电路模型研究。Email: yewjian@126.com。 |
Office editor: 陈庆
收稿日期: 2024-01-17
修回日期: 2024-04-24
网络出版日期: 2026-06-03
基金资助
广东省重点领域研发计划项目“嵌入式高性能数字信息处理器(DSP)关键技术研究”(2018B010115002)
“类脑智能关键技术及系统研究”(2018B030338001)
基础研究计划基础与应用基础研究项目(202201010595)
广东工业大学青年百人项目(220413548)
广东工业大学本科教学工程项目“信息论基础中编程实践与思政的融合教学设计研究”(211230164)
A MobileNet-based lightweight cloud detection model
Received date: 2024-01-17
Revised date: 2024-04-24
Online published: 2026-06-03
针对现有云检测算法计算量和模型规模庞大、在边缘设备上的部署几乎不可行的问题,提出了一种基于MobileNet网络的轻量化云检测模型。该方法在下采样阶段,使用基于注意力机制的残差模块,通过分组卷积降低模型参数量,并结合通道重排机制和挤压激励(squeeze-and-excitation,SE)注意力模块来增强通道间的信息交流。通过这种方式,既减少了参数量和计算复杂度,又保持了对重要特征的提取能力。在上采样阶段,使用了RepConv模块和改进的空洞空间金字塔池化模块(atrous spatial pyramid pooling,ASPP),以提高网络的学习能力和捕捉图像细节与空间信息的能力。实验结果证明,该文模型在参数量和模型复杂度降低的情况下,能够实现较高精度的云检测,具备实用性和可行性。
关键词: 云检测; MobileNet网络; 注意力机制; 多尺度特征; 空洞空间金字塔池化模块
叶武剑 , 谢林峰 , 刘怡俊 , 温晓卓 , 李扬 . 基于MobileNet的轻量化云检测模型[J]. 自然资源遥感, 2025 , 37(3) : 95 -103 . DOI: 10.6046/zrzyyg.2024031
The high computational complexity and large model scales of existing cloud detection algorithms render their deployment on edge devices almost infeasible. To address this challenge, this study proposed a MobileNet-based lightweight cloud detection model. In the downsampling stage, a residual module based on the attention mechanism was employed to reduce model parameters through group convolution. The channel shuffling mechanism and the squeeze-and-excitation (SE) channel attention were integrated to enhance the information exchange between channels. These approaches reduced parameters and computational complexity while maintaining the ability to extract significant features. In the upsampling stage, the RepConv module and the improved atrous spatial pyramid pooling (ASPP) module were used to enhance the network’s learning capability and its ability to capture image details and spatial information. Experimental results demonstrate that the proposed model can achieve higher cloud detection accuracy while reducing parameters and model complexity, substantiating its practicality and feasibility.
表1 MobileNetV2模型结构Tab.1 MobileNetV2 model structure |
| 输入形状 | 结构层名 | 扩展因子 | 输出通道数 | 数量 | 步距 |
|---|---|---|---|---|---|
| 2242×3 | 卷积层 | — | 32 | 1 | 2 |
| 1122×32 | IRB | 1 | 16 | 1 | 1 |
| 1122×16 | IRB | 6 | 24 | 2 | 2 |
| 562×24 | IRB | 6 | 32 | 3 | 2 |
| 282×32 | IRB | 6 | 64 | 4 | 2 |
| 142×64 | IRB | 6 | 96 | 3 | 1 |
| 142×96 | IRB | 6 | 160 | 3 | 2 |
| 72×160 | IRB | 6 | 320 | 1 | 1 |
| 72×320 | 1×1 卷积层 | — | 1 280 | 1 | 1 |
| 72×1 280 | 平均池 化7×7 | — | — | 1 | — |
| 1×1×1 280 | 线性层 | — | — | — | — |
表3 不同模型的云检测分割结果Tab.3 Cloud detection segmentation results of different models |
| 序号 | 假彩图像 | 真实值 | MobileNetV2 | ICNet | DFANet | LEDNet | 本文模型 |
|---|---|---|---|---|---|---|---|
| 1 | ![]() | ||||||
| 2 | ![]() | ||||||
| 3 | ![]() | ||||||
| 4 | ![]() | ||||||
| 5 | ![]() | ||||||
| 6 | ![]() |
表4 不同模型性能指标对比Tab.4 Comparison of performance indicators of different models(%) |
| 网络模型 | 准确率 | 召回率 | 精确率 | F1分数 | Jaccard |
|---|---|---|---|---|---|
| MobileNetV2 | 93.28 | 87.29 | 87.66 | 85.79 | 79.11 |
| ICNet | 91.35 | 92.34 | 83.91 | 85.07 | 79.12 |
| DFANet | 92.23 | 88.17 | 86.13 | 84.89 | 78.20 |
| LEDNet | 91.62 | 88.76 | 85.68 | 84.39 | 77.96 |
| 本文模型 | 93.24 | 90.82 | 87.03 | 86.27 | 80.49 |
表5 不同模型参数量和复杂度对比Tab.5 Comparison of parameter quantity and complexity of different models |
| 网络模型 | 参数量/106个 | GFLOPS |
|---|---|---|
| MobileNetV2 | 4.68 | 1.93 |
| ICNet | 26.24 | 5.70 |
| DFANet | 2.15 | 1.00 |
| LEDNet | 0.92 | 3.54 |
| 本文模型 | 1.43 | 1.04 |
表6 消融实验结果对比Tab.6 Comparison of ablation experiment results(%) |
| 网络模型 | A | B | C | 准确 率 | 召回 率 | 精确 率 | F1 分数 | Jac- card |
|---|---|---|---|---|---|---|---|---|
| MobileNetV2 | — | — | — | 93.28 | 87.29 | 87.66 | 85.79 | 79.11 |
| 模型A | √ | — | — | 92.77 | 85.51 | 89.53 | 84.95 | 78.37 |
| 模型B | √ | √ | — | 92.93 | 88.09 | 88.50 | 85.42 | 79.33 |
| 提出的模型 | √ | √ | √ | 93.24 | 90.82 | 87.03 | 86.27 | 80.49 |
| [1] |
|
| [2] |
|
| [3] |
|
| [4] |
|
| [5] |
|
| [6] |
|
| [7] |
|
| [8] |
|
| [9] |
刘小波, 刘鹏, 蔡之华, 等. 基于深度学习的光学遥感图像目标检测研究进展[J]. 自动化学报, 2021, 47(9):2078-2089.
|
| [10] |
|
| [11] |
|
| [12] |
刘广进, 王光辉, 毕卫华, 等. 基于DenseNet与注意力机制的遥感影像云检测算法[J]. 自然资源遥感, 2022, 34(2):88-96.doi:10.6046/zrzyyg.2021128.
|
| [13] |
|
| [14] |
|
| [15] |
|
| [16] |
|
| [17] |
|
| [18] |
|
| [19] |
|
| [20] |
|
| [21] |
|
| [22] |
|
/
| 〈 |
|
〉 |