光学学报, 2018, 38 (6): 0620001, 网络出版: 2018-07-09
基于离散余弦变换和深度网络的地貌图像分类 下载: 1057次
Landform Image Classification Based on Discrete Cosine Transformation and Deep Network
光计算 卷积神经网络 离散余弦变换 支持向量机 无人机着陆地貌图像 图像分类 optics in computing convolution neural network discrete cosine transform support vector machine unmanned aerial vehicle landing landform image image classification
摘要
在未知环境中,无人机(UAV)着陆地貌的自动识别和分类有着极其重要的研究意义,传统的自然场景分类利用的是中层和底层特征信息,但是无人机着陆地貌图像场景复杂、信息丰富,需要较准确的高层语义特征表达。提出了一种基于离散余弦变换(DCT)和深度网络的地貌图像分类方法。首先将离散余弦变换能量集中的优势引入到卷积神经网络(CNN)的高效特征表达中,以降低维度和计算复杂度;然后根据地貌图像特点构建了14层的特征学习网络,并改进了卷积神经网络结构;最后将得到的深层特征输入到支持向量机(SVM)中,快速准确地完成图像分类。实验结果表明,该算法降低了数据冗余,使训练时间大幅度减少,可以自动地学习高层语义特征;所提算法提取的特征具有较好的特征表达,有效地提高了图像分类准确率。
Abstract
In the unknown environment, the automatic identification and classification of unmanned aerial vehicle (UAV) landing landforms are of great significance. The traditional natural scene classification uses the information of the middle- and the low-level features, but the UAV landing landform image has complex scene and rich information, which needs high-level semantic features to express more accurate information. A landform image classification algorithm based on discrete cosine transform (DCT) and deep network is proposed. First, the advantage of DCT energy concentration is introduced into the efficient feature representation of convolutional neural network (CNN) to reduce the dimensionality and computational complexity. Then a 14-layer feature learning network is constructed based on the characteristics of landform image, and the CNN structure is improved. Finally, the deep features are input into the support vector machine (SVM) to complete the image classification quickly and accurately. Experimental results show that the algorithm reduces data redundancy and training time greatly, and can automatically learn high-level semantic features. The features extracted by the proposed algorithm have better feature expressions and effectively improve the image classification accuracy.
刘芳, 路丽霞, 黄光伟, 王洪娟, 王鑫. 基于离散余弦变换和深度网络的地貌图像分类[J]. 光学学报, 2018, 38(6): 0620001. Fang Liu, Lixia Lu, Guangwei Huang, Hongjuan Wang, Xin Wang. Landform Image Classification Based on Discrete Cosine Transformation and Deep Network[J]. Acta Optica Sinica, 2018, 38(6): 0620001.