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

被引:22
|
作者
Zhang, Jiaming [1 ]
Yang, Kailun [1 ]
Stiefelhagen, Rainer [1 ]
机构
[1] Karlsruhe Inst Technol, Inst Anthropomat & Robot, Karlsruhe, Germany
来源
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2021年
关键词
D O I
10.1109/IROS51168.2021.9636109
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:1132 / 1139
页数:8
相关论文
共 50 条
  • [1] Event-Based Semantic Segmentation With Posterior Attention
    Jia, Zexi
    You, Kaichao
    He, Weihua
    Tian, Yang
    Feng, Yongxiang
    Wang, Yaoyuan
    Jia, Xu
    Lou, Yihang
    Zhang, Jingyi
    Li, Guoqi
    Zhang, Ziyang
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 1829 - 1842
  • [2] Modality Translation and Fusion for event-based semantic segmentation
    Xia, Ruihao
    Zhao, Chaoqiang
    Sun, Qiyu
    Cao, Shuang
    Tang, Yang
    CONTROL ENGINEERING PRACTICE, 2023, 136
  • [3] EV-SegNet: Semantic Segmentation for Event-based Cameras
    Alonso, Inigo
    Murillo, Ana C.
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 1624 - 1633
  • [4] ESS: Learning Event-Based Semantic Segmentation from Still Images
    Sun, Zhaoning
    Messikommer, Nico
    Gehrig, Daniel
    Scaramuzza, Davide
    COMPUTER VISION, ECCV 2022, PT XXXIV, 2022, 13694 : 341 - 357
  • [5] An Event-Based Framework for the Semantic Annotation of Locations
    Anh Le
    Gertz, Michael
    Sengstock, Christian
    ADVANCES IN DATABASES AND INFORMATION SYSTEMS (ADBIS 2014), 2014, 8716 : 248 - 262
  • [6] Semantic and Event-Based Approach for Link Prediction
    Wohlfarth, Till
    Ichise, Ryutaro
    PRACTICAL ASPECTS OF KNOWLEDGE MANAGEMENT, PROCEEDINGS, 2008, 5345 : 50 - +
  • [7] Research on Event-Based Semantic Annotation of Chinese
    Zhang, Xu-jie
    Liu, Zong-tian
    Liu, Wei
    Fu, Jian-feng
    PROCEEDINGS OF 2012 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT 2012), 2012, : 1883 - 1888
  • [8] An event-based approach for semantic metadata interoperability
    Ruotsalo, Tuukka
    Hyvoenen, Eero
    SEMANTIC WEB, PROCEEDINGS, 2007, 4825 : 409 - +
  • [9] Cross-Modal Learning for Event-Based Semantic Segmentation via Attention Soft Alignment
    Xie, Chuyun
    Gao, Wei
    Guo, Ren
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (03): : 2359 - 2366
  • [10] Event-Based Motion Segmentation by Motion Compensation
    Stoffregen, Timo
    Gallego, Guillermo
    Drummond, Tom
    Kleeman, Lindsay
    Scaramuzza, Davide
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 7243 - 7252