Spatial Recall Index for the performance of machine-learning algorithms for automotive applications
We simulate a realistic objective lens based on a Cooke-triplet that exhibits typical optical aberrations like astigmatism and chromatic aberration, all variable over field. We use a special pixel-based convolution to degrade a subset of images from the BDD100k dataset, and quantify the changes in the performance of the pre-trained Hybrid Task Cascade (HTC) and Mask R-CNN algorithm. We present the SRI, which spatially resolves where in the image these changes occur, on a pixel-by-pixel basis. Our examples demonstrate the spatial dependence of the performance from the optical quality over field, highlighting the need to take the spatial dimension into account when training ML-based algorithms, especially when looking forward to autonomous driving applications.
An AutoSensPLUS subscription is required to watch this video on demand.
Presentations, panel discussions, interviews and more from all AutoSens events, with brand new content streamed both live and on demand.
Want to watch this FREE session?
You must be logged in to watch this session.
Please either login or create an account below.
Already a subscriber? Please Log in
Prof. Dr. Alexander Braun
Professor of Physics
University of Applied Science, Duesseldorf
More on the topic
More from the partners