Abstract | ||
---|---|---|
Single image depth estimation works fail to separate foreground elements because they can easily be confounded with the background. To alleviate this problem, we propose the use of a semantic segmentation procedure that adds information to a depth estimator, in this case, a 3D Convolutional Neural Network (CNN)-segmentation is coded as one-hot planes representing categories of objects. We explore 2D and 3D models. Particularly, we propose a hybrid 2D-3D CNN architecture capable of obtaining semantic segmentation and depth estimation at the same time. We tested our procedure on the SYNTHIA-AL dataset and obtained sigma(3)=0.95, which is an improvement of 0.14 points (compared with the state of the art of sigma(3)=0.81) by using manual segmentation, and sigma(3)=0.89 using automatic semantic segmentation, proving that depth estimation is improved when the shape and position of objects in a scene are known. |
Year | DOI | Venue |
---|---|---|
2022 | 10.3390/s22041669 | SENSORS |
Keywords | DocType | Volume |
depth estimation, hybrid convolutional neural networks, semantic segmentation, 3D CNN | Journal | 22 |
Issue | ISSN | Citations |
4 | 1424-8220 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
José E Valdez-Rodríguez | 1 | 0 | 0.34 |
Hiram Calvo | 2 | 0 | 0.68 |
Edgardo Felipe-Riverón | 3 | 0 | 0.34 |
Marco A Moreno-Armendáriz | 4 | 0 | 0.68 |