Patent
Deep Learning based Automotive Video Processing Method
Choi Min Seok,Kwon Young Su +1 more
- 11 Jun 2019
1
TL;DR: In this article, a vehicle image processing method based on deep learning was proposed, where a distortion in an image obtained from an existing CMOS image sensor is corrected by applying a deep learning algorithm through a deep neural network.
read more
Abstract: Disclosed is a vehicle image processing method based on deep learning. According to the present invention, since a distortion in an image obtained from an existing CMOS image sensor is corrected by applying a deep learning algorithm through a deep neural network, the recognition performance of an image-based vehicle object recognition system can become stable in spite of using the existing CMOS image sensor.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Joint rolling shutter correction and image deblurring
Quoc-Huy Tran,Bingbing Zhuang,Pan Ji,Manmohan Chandraker +3 more
- 27 May 2021
TL;DR: In this article, a method for jointly removing rolling shutter distortions and blur artifacts in a single input RS and blurred image is presented, which includes generating a plurality of RS blurred images from a camera, synthesizing RS blurred image from a set of GS sharp images, corresponding GS sharp depth maps, and synthesized RS camera motions by employing a structure-and-motion-aware RS distortion and blur rendering module.