重建高光谱图像的酿酒高粱品种识别方法研究

目的基于重建高光谱图像技术实现对酿酒高粱品种的实时快速识别。方法对分层回归网络(hierarchical regression network,HRNet)进行改进,得到残差注意力分层回归网络(residual attention-hierarchical regression network,RA-HRNet)。利用该网络进行重建高光谱图像,并在此基础上建立双向长短期记忆网络结合注意力机制(bi-directional long short-term memory-attention,BiLSTM-Attention)的酿酒高粱品种识别模型。以原始RGB数据作为重建高光谱图像网络的输入,将输出重建的光谱图像作为酿酒高粱品种识别模型的输入,以完成酿酒高粱品种识别。结果RA-HRNet相比HRNet,模型参数量[Params(M)]降低80.5%,模型计算量[floating point operations per second,FLOPS(G)]降低80.2%,峰值信噪比(peak signal-to-noise ratio,PSNR)提升16.9%,平均相对绝对误差值(mean relative absolute error,MRAE)降低31.8%,均方根误差值(root mean squared error,RMSE)降低19.1%;相比高光谱检测,重建高光谱检测效率提升95.8%;酿酒高粱品种识别模型的识别准确率最高可达95.1%。结论基于RA-HRNet重建高光谱图像网络结合BiLSTM-Attention模型可以实时快速识别酿酒高粱品种。

一种用于预测航空遥感影像光谱信息的深度学习方法

为从航空RGB遥感影像中预测高光谱影像中有用的地物属性信息,提高航空RGB遥感影像光谱的分辨率,提出一种轻量型的深度学习网络模型。所提模型组合了密集卷积神经网络架构和自适应注意力机制的优点,构建了一种新型密集注意力卷积神经网络模型(dense attention convolutional neural network model,DACNN model)。在真实的多模态AeroRIT场景影像和同源的雄安航空遥感影像上的多种定量对比实验结果表明,所提出的网络架构可以生成与原始高光谱遥感影像相似的空间特征和光谱特征,并且所需参数量显著降低,具有较好的性能和适用性,且所提模型架构方法具有一定的通用性。

Parallel Spectral-Domain Optical Coherence Tomography for Non-Scattering Object Imaging

The parallel spectral-domain optical coherence tomography（PSDOCT） is described for highspeed optical coherence tomography（OCT） without lateral scanning. In this setup, the self-elimination of auto-correlation（AC） interference algorithm was used for eradicating the AC interference and ghost images. However, when performed in free space OCT, this algorithm still generated a weak DC component. The algorithm was improved by adding the background intensity part to compensate for the mutual interference between object and reference arms. The results demonstrate that the DC component can be eradicated. Compared with conventional QCT and complex Fourier-domain optical coherence to- mography, the advantages of PSDOCT with the improved algorithm in free space are that it has no moving parts to generate consecutive phase shift, the structure of the object can be reconstructed immediately and automatically, and the speed is approximately 16 times faster than those of the other two in the same case.