EUVIMEDEUVIMED entdecken
Crossref

SpikeTOD: A Biologically Interpretable Spike-Driven Object Detection in Challenging Traffic Scenarios

Junfan Wang, Yi Chen, Xiaoyue Ji, Zhekang Dong, Mingyu Gao, Zhiwei He

IEEE Transactions on Intelligent Transportation Systems · 2024-12 · 25 (12) · 21297-21314

DOI: 10.1109/tits.2024.3468038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-12. Verfasst von Junfan Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Zhejiang Provincial Major Research and Development Project of China, Central Guiding Local Science and Technology Development Fund Project of China, Zhejiang Provincial Key Laboratory of Equipment Electronics.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial neural networks (ANN) have shown remarkable performance in intelligent transportation systems (ITS), especially for the traffic object detection. However, as the ITS is applied to a wider range of traffic scenarios, the increasing demand for the trade-off between detection performance and power resources has become inevitable. A biologically interpretable spike-driven traffic object detector for challenging scenarios is proposed in this paper, named SpikeTOD, achieving the trade-off between the accuracy and power consumption. Firstly, the spike neural network (SNN) is employed to realize energy-efficient object detection in traffic scenarios. And a local modulation-based integrate-and-fire (IF) neuron is designed, which provides an efficient way to convert the traffic detection model from ANN to SNN. Secondly, a biology-inspired detail-guided context-aware network (DCNet) is proposed to improve the detection performance. The integration of detail coherence and global priors is leveraged to selectively emphasize object features and improve the detection capabilities within challenging conditions. As far as we know, this is the first application of SNN in traffic object detection tasks. SpikeTOD achieved a mAP@50 of 46.11% on the BDD100K dataset with a power consumption of 4.73E-03J, demonstrating a more efficient trade-off in detection accuracy and power consumption. Notably, SpikeTOD maintained an average missed detection rate of 44.56%, further contributing to its overall efficacy in traffic object detection. Further, we conducted on road test by deploying SpikeTOD on Jetson Xavier NX and Loihi to demonstrate that model achieves a better balance between accuracy and power consumption.

Förderung

  • Zhejiang Provincial Major Research and Development Project of China
  • Central Guiding Local Science and Technology Development Fund Project of China
  • Zhejiang Provincial Key Laboratory of Equipment Electronics

Zitieren

APA

Wang, J., Chen, Y., Ji, X., Dong, Z., Gao, M., & He, Z. (2024). SpikeTOD: A Biologically Interpretable Spike-Driven Object Detection in Challenging Traffic Scenarios. IEEE Transactions on Intelligent Transportation Systems, 25(12), 21297-21314. https://doi.org/10.1109/tits.2024.3468038

Vancouver

Wang J, Chen Y, Ji X, Dong Z, Gao M, He Z. SpikeTOD: A Biologically Interpretable Spike-Driven Object Detection in Challenging Traffic Scenarios. IEEE Transactions on Intelligent Transportation Systems. 2024;25(12):21297-21314. doi:10.1109/tits.2024.3468038

BibTeX
@article{Wang2024,
  author = {Wang, Junfan and Chen, Yi and Ji, Xiaoyue and Dong, Zhekang and Gao, Mingyu and He, Zhiwei},
  title = {SpikeTOD: A Biologically Interpretable Spike-Driven Object Detection in Challenging Traffic Scenarios},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2024},
  volume = {25},
  number = {12},
  pages = {21297--21314},
  doi = {10.1109/tits.2024.3468038}
}
Kostenlos starten →