Presentation + Paper
12 April 2021 Analyzing the impact of vibration on YOLO algorithm performance
Author Affiliations +
Abstract
In this paper we will analyze the effect of vibration on the performance of the YOLO (You Only Look Once) algorithm on object classification. The YOLO algorithm will initially be trained using static imagery of common objects. Image processing techniques will then be used to create video clips with varying levels of blur due to vibration. These videos will then be used to evaluate the performance of the algorithm on object classification. Results of the classification will be presented. An initial summary of the classification results will be discussed in relation to the amount of vibration added to the imagery.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jonathan G. Hixson, Brian P. Teaney, Bryan Vogel, Mark Jeiran, and George Nehmetallah "Analyzing the impact of vibration on YOLO algorithm performance", Proc. SPIE 11740, Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXXII, 117400H (12 April 2021); https://doi.org/10.1117/12.2586953
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Image processing

Optical sensors

Video processing

RELATED CONTENT

Image processing in a maritime environment
Proceedings of SPIE (May 23 2015)
Image-based wind measurement
Proceedings of SPIE (January 01 1900)
Aesthetic color templates for enhancing casual videos
Proceedings of SPIE (September 17 2018)
Digital Scene Matching Area Correlator (DSMAC)
Proceedings of SPIE (December 23 1980)

Back to Top