1 / 12

JEG-Hybrid: Automotive Image Quality

JEG-Hybrid: Automotive Image Quality. Anthony Winterlich Vladimir Zlokolica Edward Jones Martin Glavin Connaught Automotive Research Group Electrical & Electronic Engineering National University of Ireland, Galway. Current Applications. Junction View. Current Applications.

pink
Download Presentation

JEG-Hybrid: Automotive Image Quality

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. JEG-Hybrid: Automotive Image Quality Anthony Winterlich Vladimir Zlokolica Edward Jones Martin Glavin Connaught Automotive Research Group Electrical & Electronic Engineering National University of Ireland, Galway

  2. Current Applications Junction View

  3. Current Applications Park Assist

  4. Subjective testing challenges • Fish-eye distortion • Sharpness • Visual Saliency • Colour balance and contrast (HDR scenes) • Noise in high & low light conditions

  5. LOWER SPATIAL RESOLUTION AT THE EDGE OF AN IMAGE RESULTS IN A LOSS OF PERCEPTUAL QUALITY

  6. LOWER SPATIAL RESOLUTION AT THE EDGE OF AN IMAGE RESULTS IN A LOSS OF PERCEPTUAL QUALITY

  7. FEATURE VECTORS ARE EXTRACTED TO DETERMINE SALIENCY

  8. HDR and contrast

  9. Quality in low light conditions

  10. Existing subjective testing standards • ITU-R Recommendation BT.500-11, “Methodology for the subjective assessment of the quality of television pictures,” • General viewing conditions for subjective assessments in laboratory environment • Not appropriate for automotive vision systems! • The absence of defects in the reference part of the presentation pair is crucial to obtain stable results. • Fish-eye images are not free of defects!

  11. Thank You! SSIM : 0.7134

More Related