A Comparative Study of Different CNN Encoders for Monocular Depth Prediction
| Autor: | Samir A. Rawashdeh, Mohamed Aladem, Zaid El-Shair, Sumanth Chennupati |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Monocular
Stereo cameras business.industry Computer science Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Robotics 02 engineering and technology 010501 environmental sciences 01 natural sciences Convolutional neural network 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Augmented reality Artificial intelligence business Encoder 0105 earth and related environmental sciences Structured light |
| Zdroj: | 2019 IEEE National Aerospace and Electronics Conference (NAECON). |
| DOI: | 10.1109/naecon46414.2019.9057857 |
| Popis: | Depth estimation of an observed scene is an important task for many domains such as mobile robotics, autonomous driving, and augmented reality. Traditionally, specialized sensors such as stereo cameras and structured light (RGB-D) ones are used to obtain depth along with color information of the environment. However, extending typical monocular cameras with the ability to infer depth information is an attractive solution. In this paper, we will demonstrate a Convolutional Neural Network (CNN) in an encoder-decoder architecture to perform monocular depth prediction. Additionally, we will evaluate and compare different CNN encoders’ performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|