ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data

20 Aug 2020  ·  Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen ·

Ensuring the safety of all traffic participants is a prerequisite for bringing intelligent vehicles closer to practical applications. The assistance system should not only achieve high accuracy under normal conditions, but obtain robust perception against extreme situations. However, traffic accidents that involve object collisions, deformations, overturns, etc., yet unseen in most training sets, will largely harm the performance of existing semantic segmentation models. To tackle this issue, we present a rarely addressed task regarding semantic segmentation in accidental scenarios, along with an accident dataset DADA-seg. It contains 313 various accident sequences with 40 frames each, of which the time windows are located before and during a traffic accident. Every 11th frame is manually annotated for benchmarking the segmentation performance. 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. Our approach achieves +8.2% mIoU performance gain on the proposed evaluation set, exceeding more than 10 state-of-the-art segmentation methods. The proposed ISSAFE architecture is demonstrated to be consistently effective for models learned on multiple source databases including Cityscapes, KITTI-360, BDD and ApolloScape.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation DADA-seg ISSAFE mIoU 29.97 # 6
Semantic Segmentation DensePASS SwiftNet (Merge3) mIoU 32.04% # 23
Semantic Segmentation EventScape ISSAFE mIoU 43.61 # 10
Semantic Segmentation KITTI-360 ISSAFE (ResNet50) mIoU 56.64 # 6
Semantic Segmentation KITTI-360 ISSAFE (ResNet18) mIoU 53.95 # 10

Methods


No methods listed for this paper. Add relevant methods here