Depth Prediction Improvement for Near-Field iToF Lidar in Low-Speed Motion State
Open Access
Abstract
Current deep learning-based phase unwrapping techniques for iToF Lidar sensors focus mainly on static indoor scenarios, ignoring motion blur in dynamic outdoor scenarios. Our paper proposes a two-stage semi-supervised method to unwrap ambiguous depth maps affected by motion blur in dynamic outdoor scenes. The method trains on static datasets to learn unwrapped depth map prediction and then adapts to dynamic datasets using continuous learning methods. Additionally, blind deconvolution is introduced to mitigate the blur. The combined use of these methods produces high-quality depth maps with reduced blur noise.Keywords
This publication has 36 references indexed in Scilit:
- Single-frequency and accurate phase unwrapping method using deep learningOptics and Lasers in Engineering, 2022
- Deep Image Deblurring: A SurveyInternational Journal of Computer Vision, 2022
- Learning to Prompt for Continual Learning2022
- Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency2022
- CVPR 2020 continual learning in computer vision competition: Approaches, results, current challenges and future directionsArtificial Intelligence, 2022
- Online continual learning in image classification: An empirical surveyNeurocomputing, 2022
- Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments2021
- Hyperspectral Image Classification With Pre-Activation Residual Attention NetworkIEEE Access, 2019
- Deep Residual Learning for Image Recognition2016
- Fundamentals of Digital Image Processing2010