EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LiquidSpike: A Continuous–Discrete Spiking Framework for Resource-Constrained Automotive Event-Based Object Detection

Mingfeng Yin, Xiaolin Yu, Yi Sheng, Xin Wen, Yujie Chen, Yu Wang

Information · 19.11.2026 · 17 (11) · 1178

DOI: 10.3390/info17111178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 19.11.2026. Verfasst von Mingfeng Yin und 5 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Research Project of Jiangsu Higher Education Institutions, Changzhou Applied Basic Research Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Resource-constrained automotive perception requires accurate and low-latency detection under limited onboard computing and energy budgets. Event cameras and spiking neural networks offer a promising solution through temporally sparse sensing and event-driven computation. However, strictly discrete spiking processing may limit adaptation to time-varying event activity and weaken the spatial information required for accurate localization. This study proposes LiquidSpike, a continuous–discrete hybrid framework that selectively introduces continuous computation at information-critical stages while retaining discrete transmission through most backbone and neck stages. LTC-IPLIF provides input-conditioned temporal integration, LiquidSSM performs localized long-range spatial state propagation followed by discrete re-encoding, and response-aware multi-scale processing improves cross-scale fusion and spatial refinement. On the Gen1 automotive event-camera dataset, LiquidSpike achieves 69.4% mAP@50 and 41.8% mAP@50:95 with 18.9 million parameters under the 4 × 2 configuration. Compared with SpikeYOLO under the same configuration, it improves the two metrics by 2.2 and 1.4 percentage points, respectively, while reducing the parameter count by 18.2%. Results on MS COCO 2017 provide supplementary evidence of applicability to temporally encoded frame-based inputs. These results demonstrate a competitive trade-off among detection accuracy, model size, and theoretical operation-level energy.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Research Project of Jiangsu Higher Education Institutions
  • Changzhou Applied Basic Research Program
  • Jiangsu University of Technology

Zitieren

APA

Yin, M., Yu, X., Sheng, Y., Wen, X., Chen, Y., & Wang, Y. (2026). LiquidSpike: A Continuous–Discrete Spiking Framework for Resource-Constrained Automotive Event-Based Object Detection. Information, 17(11), 1178. https://doi.org/10.3390/info17111178

Vancouver

Yin M, Yu X, Sheng Y, Wen X, Chen Y, Wang Y. LiquidSpike: A Continuous–Discrete Spiking Framework for Resource-Constrained Automotive Event-Based Object Detection. Information. 2026;17(11):1178. doi:10.3390/info17111178

BibTeX
@article{Yin2026,
  author = {Yin, Mingfeng and Yu, Xiaolin and Sheng, Yi and Wen, Xin and Chen, Yujie and Wang, Yu},
  title = {LiquidSpike: A Continuous–Discrete Spiking Framework for Resource-Constrained Automotive Event-Based Object Detection},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {11},
  pages = {1178},
  doi = {10.3390/info17111178}
}
Kostenlos starten →