Kim Hyun-Koo, Yoo Kook-Yeol, Jung Ho-Youl
Department of Information and Communication Engineering, Yeungnam University, Gyeongsan 38544, Korea.
Sensors (Basel). 2020 Jun 15;20(12):3387. doi: 10.3390/s20123387.
In this paper, a modified encoder-decoder structured fully convolutional network (ED-FCN) is proposed to generate the camera-like color image from the light detection and ranging (LiDAR) reflection image. Previously, we showed the possibility to generate a color image from a heterogeneous source using the asymmetric ED-FCN. In addition, modified ED-FCNs, i.e., UNET and selected connection UNET (SC-UNET), have been successfully applied to the biomedical image segmentation and concealed-object detection for military purposes, respectively. In this paper, we apply the SC-UNET to generate a color image from a heterogeneous image. Various connections between encoder and decoder are analyzed. The LiDAR reflection image has only 5.28% valid values, i.e., its data are extremely sparse. The severe sparseness of the reflection image limits the generation performance when the UNET is applied directly to this heterogeneous image generation. In this paper, we present a methodology of network connection in SC-UNET that considers the sparseness of each level in the encoder network and the similarity between the same levels of encoder and decoder networks. The simulation results show that the proposed SC-UNET with the connection between encoder and decoder at two lowest levels yields improvements of 3.87 dB and 0.17 in peak signal-to-noise ratio and structural similarity, respectively, over the conventional asymmetric ED-FCN. The methodology presented in this paper would be a powerful tool for generating data from heterogeneous sources.
本文提出了一种改进的编码器-解码器结构的全卷积网络（ED-FCN），用于从光探测与测距（LiDAR）反射图像生成类似相机的彩色图像。此前，我们展示了使用非对称ED-FCN从异构源生成彩色图像的可能性。此外，改进的ED-FCN，即UNET和选择性连接UNET（SC-UNET），已分别成功应用于生物医学图像分割和军事用途的隐藏目标检测。在本文中，我们应用SC-UNET从异构图像生成彩色图像。分析了编码器和解码器之间的各种连接。LiDAR反射图像只有5.28%的有效值，即其数据极其稀疏。当直接将UNET应用于这种异构图像生成时，反射图像的严重稀疏性限制了生成性能。在本文中，我们提出了一种SC-UNET中的网络连接方法，该方法考虑了编码器网络中每个层级的稀疏性以及编码器和解码器网络相同层级之间的相似性。仿真结果表明，所提出的在最低两个层级具有编码器-解码器连接的SC-UNET，相比于传统的非对称ED-FCN，在峰值信噪比和结构相似性方面分别提高了3.87 dB和0.17。本文提出的方法将成为从异构源生成数据的有力工具。
