Pedestrian Detector Domain Shift Robustness Evaluation, And Domain Shift Error Mitigation Proposal
MetadataShow full item record
This paper evaluates daytime to nighttime traffic image domain shift on Faster R-CNNand SSD based pedestrian and cyclist detectors. Daytime image trained detectors are applied on anewly compiled nighttime image dataset and their performance is evaluated against detectors trainedon both daytime and nighttime images. Faster R-CNN based detectors proved relatively robust, butstill clearly inferior to the models trained on nighttime images, the SSD based model proved noncompetitive.Approaches to the domain shift deterioration mitigation were proposed and future workoutlined.
KeywordsObject detection, Pedestrian detection, Cyclist detection, ADAS, AV, Faster R-CNN,SSD, Domain shift, Domain adaptation, Data augmentation
Document typePeer reviewed
Document versionFinal PDF
SourceProceedings II of the 27st Conference STUDENT EEICT 2021: Selected Papers. s. 181-187. ISBN 978-80-214-5943-4