Monocular Human Depth Estimation Via Pose Estimation
We propose a novel monocular depth estimator, which improves the prediction accuracy on human regions by utilizing pose information. The proposed algorithm consists of two networks — PoseNet and DepthNet — to estimate keypoint heatmaps and a depth map, respectively. We incorpor...
Guardado en:
Autores principales: | Jinyoung Jun, Jae-Han Lee, Chul Lee, Chang-Su Kim |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/362374746b434f51bfc40a80c1a6f80d |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Self-Supervised Monocular Depth Estimation With Extensive Pretraining
por: Hyukdoo Choi
Publicado: (2021) -
Joint Soft–Hard Attention for Self-Supervised Monocular Depth Estimation
por: Chao Fan, et al.
Publicado: (2021) -
A Review of Benchmark Datasets and Training Loss Functions in Neural Depth Estimation
por: Faisal Khan, et al.
Publicado: (2021) -
Expedited Pose Estimation Algorithm Involving Perturbance Affine Term Based on Projection Vector for Space Target
por: Guiyang Zhang, et al.
Publicado: (2020) -
The Liu-Type Estimator Based on Parameter Optimization and its Application in SBAS Deformation Model Inversion
por: Min Zhai, et al.
Publicado: (2021)