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...
Enregistré dans:
Auteurs principaux: | Jinyoung Jun, Jae-Han Lee, Chul Lee, Chang-Su Kim |
---|---|
Format: | article |
Langue: | EN |
Publié: |
IEEE
2021
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/362374746b434f51bfc40a80c1a6f80d |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Self-Supervised Monocular Depth Estimation With Extensive Pretraining
par: Hyukdoo Choi
Publié: (2021) -
Joint Soft–Hard Attention for Self-Supervised Monocular Depth Estimation
par: Chao Fan, et autres
Publié: (2021) -
A Review of Benchmark Datasets and Training Loss Functions in Neural Depth Estimation
par: Faisal Khan, et autres
Publié: (2021) -
Expedited Pose Estimation Algorithm Involving Perturbance Affine Term Based on Projection Vector for Space Target
par: Guiyang Zhang, et autres
Publié: (2020) -
The Liu-Type Estimator Based on Parameter Optimization and its Application in SBAS Deformation Model Inversion
par: Min Zhai, et autres
Publié: (2021)