ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data
To bring autonomous vehicles closer to real-world applications, a major task is to ensure the safety of all traffic participants. In addition to the high accuracy under controlled conditions, the assistance system is still supposed to obtain robust perception against extreme situations, especially in accident scenarios, which involve object collisions, deformations, overturns, etc. However, models trained on common datasets may suffer from a large performance degradation when applied in these challenging scenes. To tackle this issue, we present a rarely addressed task regarding semantic segmentation in accident scenarios, along with an associated large-scale dataset DADA-seg. Our dataset contains 313 sequences with 40 frames each, of which the time windows are located before and during a traffic accident. For benchmarking the segmentation performance, every 11th frame is manually annotated with reference to Cityscapes. Furthermore, we propose a novel event-based multi-modal segmentation architecture ISSAFE. Our experiments indicate that event-based data can provide complementary information to stabilize semantic segmentation under adverse conditions by preserving fine-grain motion of fast-moving foreground (crash objects) in accidents. Compared with state-of-the-art models, our approach achieves 30.0 evaluation set.
READ FULL TEXT