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
  • [41] Event-Based Sampled-Data Average Consensus
    Gong, Hang
    Wu, Fangke
    Liu, Runzhi
    Jin, Xin
    Zhou, Wei
    Chu, Xing
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020 (2020)
  • [42] An Event-Based Data Collection Engine for Serious Games
    Raghavendra, Amith Tudur
    3RD ANNUAL INTERNATIONAL CONFERENCE ON COMPUTER GAMES, MULTIMEDIA & ALLIED TECHNOLOGIES (CGAT 2010), 2010, : 113 - 116
  • [43] A DATA-FLOW APPROACH TO EVENT-BASED DEBUGGING
    OLSSON, RA
    CRAWFORD, RH
    HO, WW
    SOFTWARE-PRACTICE & EXPERIENCE, 1991, 21 (02): : 209 - 229
  • [44] Fall Detection with Event-Based Data: A Case Study
    Wang, Xueyi
    Risi, Nicoletta
    Talavera, Estefania
    Chicca, Elisabetta
    Karastoyanova, Dimka
    Azzopardi, George
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2023, PT II, 2023, 14185 : 33 - 42
  • [45] MEDEA - A model for the event-based data exchange architecture
    Sheu, RK
    Yuan, SM
    Lo, WT
    SEVENTH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS: WORKSHOPS, PROCEEDINGS, 2000, : 88 - 93
  • [46] Event-Based Motion Segmentation With Spatio-Temporal Graph Cuts
    Zhou, Yi
    Gallego, Guillermo
    Lu, Xiuyuan
    Liu, Siqi
    Shen, Shaojie
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (08) : 4868 - 4880
  • [47] Un-EVIMO: Unsupervised Event-Based Independent Motion Segmentation
    Wang, Ziyun
    Guo, Jinyuan
    Daniilidis, Kostas
    COMPUTER VISION - ECCV 2024, PT XVI, 2025, 15074 : 228 - 245
  • [48] Spike-BRGNet: Efficient and Accurate Event-Based Semantic Segmentation With Boundary Region-Guided Spiking Neural Networks
    Long, Xianlei
    Zhu, Xiaxin
    Guo, Fangming
    Chen, Chao
    Zhu, Xiangwei
    Gu, Fuqiang
    Yuan, Songyu
    Zhang, Chunlong
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 35 (03) : 2712 - 2724
  • [49] Feature Representation and Compression Methods for Event-Based Data
    Wang, Conghe
    Wang, Xia
    Yan, Changda
    Ma, Kai
    IEEE SENSORS JOURNAL, 2023, 23 (05) : 5109 - 5123
  • [50] An approach to model and query event-based temporal data
    Bertino, E
    Ferrari, E
    Guerrini, G
    FIFTH INTERNATIONAL WORKSHOP ON TEMPORAL REPRESENTATION AND REASONING - PROCEEDINGS: TIME-98, 1998, : 122 - 131