激光与光电子学进展, 2018, 55 (12): 121004, 网络出版: 2019-08-01
基于改进卷积神经网络的稠密视差图提取方法 下载: 1003次
Dense Disparity Map Extraction Method Based on Improved Convolutional Neural Network
图像处理 视差获取 深度学习 卷积神经网络 立体匹配 image processing disparity acquisition deep learning convolutional neural network stereo matching
摘要
针对现有的卷积神经网络方法所生成的视差图中细节损失严重的问题,提出了在结构上改进的新方法。将原有网络中特征提取部分的4层卷积结构提升到7层,最大化提高了精度;在网络中引入了双金字塔结构,将多尺度降采样信息和特征信息进行了融合,保持了输入图像中的原始细节信息。实验结果表明,改进后网络的错误率从3.029%降到了2.795%,生成的视差图具有更好的连通性。
Abstract
According to the problem of the severe detail loss of the disparity map generated by the current convolutional neural network methods, a structural improvement method is proposed. The 4 layers convolutional structure of the feature extraction part from original network is added to 7 layers to maximize the accuracy. And, the proposed dual pyramid structure is introduced to the network to combine the multi-scale down-sampling information with the feature information, which keeps the details of the original input images. Experimental results show that the error rate of the improved network reduces from 3.029% to 2.795%, and the generated disparity maps have better connectivity.
黄东振, 赵沁, 刘华巍, 李宝清, 袁晓兵. 基于改进卷积神经网络的稠密视差图提取方法[J]. 激光与光电子学进展, 2018, 55(12): 121004. Dongzhen Huang, Qin Zhao, Huawei Liu, Baoqing Li, Xiaobing Yuan. Dense Disparity Map Extraction Method Based on Improved Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121004.