What question did this study set out to answer?

The aim is to assess how environmental contamination impacts the performance of object detection neural networks.

April 19, 2026ComputersOpen Access

Performance Degradation of Object Detection Neural Networks Under Natural Visual Contamination in Autonomous Driving

View Full Paper

Ask AI

Bookmark

The aim is to assess how environmental contamination impacts the performance of object detection neural networks.
Conducted a literature review to identify factors affecting sensor performance.
Created a synthetic dataset with clean images and contaminated variants of urban traffic scenes.
Evaluated detection efficiency using state-of-the-art neural network-based object detectors.
Contamination leads to a measurable reduction in detection performance across all models tested.
Smaller model variants are more sensitive to performance degradation.
Medium-complexity models show a balance between robustness and computational cost.
Performance differences highlight the importance of model design and size.
Spatial distribution of contamination, especially near the image center, significantly impacts detection performance.

No takes yet. Share an insight, caveat, or question.

Literature review examines how environmental contamination affects detection efficiency in autonomous vehicles, suggesting design improvements.

Csikor et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Literature review examines how environmental contamination affects detection efficiency in autonomous vehicles, suggesting design improvements.