Regression‐based convolutional 3D pose estimation from single image
| Autor: | Sara Ershadi-Nasab, Shohreh Kasaei, Esmaeil Sanaei |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science business.industry 020207 software engineering Pattern recognition 02 engineering and technology Image plane 3D pose estimation Convolutional neural network Measure (mathematics) Regression 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Electrical and Electronic Engineering Projection (set theory) business Pose |
| Zdroj: | Electronics Letters. 54:292-293 |
| ISSN: | 1350-911X 0013-5194 |
| DOI: | 10.1049/el.2017.4052 |
| Popis: | Estimation of 3D human pose from a single image is a challenging task because of ambiguities in projection from 3D space to the 2D image plane. A new two-stage deep convolutional neural network-based method is proposed for regressing the distance and angular difference matrices among body joints. Using the angular difference between body joints in addition to the distance between them in articulated objects such as human body can better model the structure of the shapes and increases the modelling capability of the learning method. Experimental results on HumanEva I and Human3.6M datasets show that the proposed method has substantial improvement in the mean per joint position error measure over the state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text