| 基于改进样本驱动的高光谱矿物识别模型压缩方法 |
| |
| 引用本文： | 邓可望,赵慧洁,李娜,蔡辉.基于改进样本驱动的高光谱矿物识别模型压缩方法[J].红外与激光工程,2022,51(3):20210252-1-20210252-9. |
| |
| 作者姓名： | 邓可望 赵慧洁 李娜 蔡辉 |
| |
| 作者单位： | 1.北京航空航天大学 仪器科学与光电工程学院，北京 100191 |
| |
| 基金项目： | 国家重点研发计划（2016YFB0500505，2017YFC0602104）； 国家自然科学基金（61975004）；高分国土资源遥感应用示范系统（二期）（04-Y30B01-9001-18/20）；青岛创业创新领军人才计划 (18-1-2-22-zhc) |
| |
| 摘 要： | 针对机载成像高光谱遥感仪器获得的大批量高光谱数据很难实现高效快速的矿物信息提取和识别的问题，提出了一种基于改进样本驱动的高光谱矿物识别模型压缩方法，对神经网络中的冗余神经元进行剪枝，从而获取高效的矿物识别模型。首先，以验证数据集中的正确识别样本为数据驱动，计算各神经元经激活函数后的输出零值频率，并将其作为该神经元重要性判据，探讨各神经元对神经网络正确识别样本的贡献；其次，通过设置重要性阈值对冗余神经元进行剪枝，并对剪枝网络进行再训练，在保留原网络正确识别特性的基础上，提升压缩模型识别精度；最终通过多次迭代剪枝获得高效的压缩矿物识别模型。利用基于改进样本驱动的模型压缩方法对基于多层感知机的矿物识别模型进行压缩改进，并以美国内华达州Cuprite矿区的机载可见光/红外成像光谱仪的高光谱数据作为测试数据，获得了压缩比3.33、矿物识别精度94.35%的高效矿物识别模型。
|
| 关 键 词： | 神经网络 网络剪枝 高光谱 矿物识别 |
| 收稿时间： | 2021-12-10 |
Improved data-driven compressing method for hyperspectral mineral identification models |
| |
| Affiliation: | 1.School of Instrumentation Science and Opto-Electronic Engineering, Beihang University, Beijing 100191, China2.Beihang University Qingdao Research Institute, Beihang University, Qingdao 266101, China3.Unit 96901 of the People's Liberation Army of China, Beijing 300140, China |
| |
| Abstract: | It was difficult to extract mineral features efficiently and quickly from large quantities of hyperspectral data obtained by airborne imaging hyperspectral spectrometers. An improved data-driven compressing method for mineral identification models was proposed in this paper, which pruned redundant neurons in neural networks to obtain efficient mineral identification models. Firstly, the average percentage of zeros driven by correctly identified samples in the validation set (C-APoZ) of each neuron was calculated as a criterion of importance for the neuron, so as to explore the contribution of the neuron to the network for identifying samples correctly. Then, the redundant neurons were pruned by setting the importance threshold, and the pruned network was retrained to improve the identification accuracy while preserving the correct identification abilities of the original network. Finally, an efficient compressed model for mineral identification was obtained through multiple iterative pruning. In this paper, the improved data-driven compressing method was conducted on the mineral identification models based on multilayer perceptron (MLP) to promote their efficiency. The hyperspectral data of the Nevada mining area collected by Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) were applied to evaluate the proposed method. The results show that the proposed method obtained an efficient model for mineral identification with the compression rate of 3.33 and the identification accuracy of 94.35%. |
| |
| Keywords: | |
|
| 点击此处可从《红外与激光工程》浏览原始摘要信息 |
|
点击此处可从《红外与激光工程》下载全文 |
|
