Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET
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 usi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/12/3387 |
| _version_ | 1797565237940977664 |
|---|---|
| author | Hyun-Koo Kim Kook-Yeol Yoo Ho-Youl Jung |
| author_facet | Hyun-Koo Kim Kook-Yeol Yoo Ho-Youl Jung |
| author_sort | Hyun-Koo Kim |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T19:09:16Z |
| format | Article |
| id | doaj.art-89d62a777415404aaced97a5565f8d1d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T19:09:16Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-89d62a777415404aaced97a5565f8d1d2023-11-20T03:55:36ZengMDPI AGSensors1424-82202020-06-012012338710.3390/s20123387Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNETHyun-Koo Kim0Kook-Yeol Yoo1Ho-Youl Jung2Department of Information and Communication Engineering, Yeungnam University, Gyeongsan 38544, KoreaDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan 38544, KoreaDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan 38544, KoreaIn 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.https://www.mdpi.com/1424-8220/20/12/3387artificial intelligenceheterogeneous transfer methodimage generationLiDAR sensorLiDAR imaginglearning systems |
| spellingShingle | Hyun-Koo Kim Kook-Yeol Yoo Ho-Youl Jung Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET Sensors artificial intelligence heterogeneous transfer method image generation LiDAR sensor LiDAR imaging learning systems |
| title | Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET |
| title_full | Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET |
| title_fullStr | Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET |
| title_full_unstemmed | Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET |
| title_short | Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET |
| title_sort | color image generation from lidar reflection data by using selected connection unet |
| topic | artificial intelligence heterogeneous transfer method image generation LiDAR sensor LiDAR imaging learning systems |
| url | https://www.mdpi.com/1424-8220/20/12/3387 |
| work_keys_str_mv | AT hyunkookim colorimagegenerationfromlidarreflectiondatabyusingselectedconnectionunet AT kookyeolyoo colorimagegenerationfromlidarreflectiondatabyusingselectedconnectionunet AT hoyouljung colorimagegenerationfromlidarreflectiondatabyusingselectedconnectionunet |