Voxel event graph neural network for event-based human gait recognition

Guangyuan Ma; Xiaolin Gong; Jiangtao Xu; Jiandong Gao; Zhaoxuan Guo

doi:10.1007/s11801-026-4204-3

Optoelectronics Letters ›› 2026, Vol. 22 ›› Issue (3) :167 -173. DOI: 10.1007/s11801-026-4204-3

Article

research-article

Voxel event graph neural network for event-based human gait recognition

Author information +

History +

PDF

Abstract

To improve the accuracy of event-based gait recognition, a method called voxel event graph neural network (VEGNN) is proposed. This method voxelizes the event stream and selects representative voxels as vertices of the graph. Then the edges are constructed based on spatio-temporal distance and temporal order constraints so that the event stream is constructed as a graph structure. Finally, a lightweight feature extraction network based on graph neural networks (GNNs) is used to efficiently capture spatio-temporal information and motion cues from the event graph. To evaluate our method, an event-based gait recognition dataset called Celex-Gait is created. Experimental results show that VEGNN achieves a gait recognition accuracy of 95.8% and 93.9% on the Celex-Gait dataset and the DVS128-Gait-Day dataset, respectively. Furthermore, compared to the state-of-the-art methods, VEGNN reduces the number of model parameters by 30%. This indicates that VEGNN achieves higher recognition accuracy with lower model complexity.

Keywords

Cite this article

Download citation ▾

Guangyuan Ma, Xiaolin Gong, Jiangtao Xu, Jiandong Gao, Zhaoxuan Guo. Voxel event graph neural network for event-based human gait recognition. Optoelectronics Letters, 2026, 22(3): 167-173 DOI:10.1007/s11801-026-4204-3

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Sepas-Moghaddam A, Etemad A. Deep gait recognition: a survey. IEEE transactions on pattern analysis and machine intelligence. 2023, 45(1): 264-284. J]

[2]	He D, Xue Y, Li Yet al. . Multi-scale spatio-temporal network for skeleton-based gait recognition. AI communications. 2023, 36(4): 297-310. J]

[3]	Liu L, Ouyang W, Wang Xet al. . Deep learning for generic object detection: a survey. International journal of computer vision. 2020, 128(2): 261-318. J]

[4]	Lichtsteiner P, Posch C, Delbruck T. A 128×128 120dB 15µs latency asynchronous temporal contrast vision sensor. IEEE journal of solid-state circuits. 2008, 43(2): 566-576. J]

[5]	Gallego G, Delbrück T, Orchard Get al. . Event-based vision: a survey. IEEE transactions on pattern analysis and machine intelligence. 2022, 44(1): 154-180. J]

[6]	Delbrück T. Neuromorophic vision sensing and processing. 46th European Solid-State Device Research Conference, September 12–15, 2016, Lausanne, Switzerland. 2016, New York, IEEE714[C]

[7]	Tulyakov S, Gehrig D, Georgoulis Set al. . Time lens: event-based video frame interpolation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20–25, 2021, Nashville, TN, USA. 2021, New York, IEEE1615016159[C]

[8]	Gehrig M, Scaramuzza D. Recurrent vision transformers for object detection with event cameras. IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 17–24, 2023, Vancouver, BC, Canada. 2023, New York, IEEE1388413893[C]

[9]	Eddine M J, Dugelay J L. GAIT3: an event-based, visible and thermal database for gait recognition. International Conference of the Biometrics Special Interest Group, September 14–16, 2022, Darmstadt, Germany. 2022, New York, IEEE15[C]

[10]	Wang Y, Du B, Shen Yet al. . EV-Gait: event-based robust gait recognition using dynamic vision sensors. IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15–20, 2019, Long Beach, CA, USA. 2019, New York, IEEE63516360[C]

[11]	Tao Y, Chang C, Saighi Set al. . GaitSpike: event-based gait recognition with spiking neural network. IEEE 6th International Conference on AI Circuits and Systems, April 22–25, 2024, Abu Dhabi, United Arab Emirates. 2024, New York, IEEE357361[C]

[12]	Wang Y, Zhang X, Shen Yet al. . Event-stream representation for human gaits identification using deep neural networks. IEEE transactions on pattern analysis and machine intelligence. 2022, 44(7): 3436-3449[J]

[13]	Fu L, Yan S. Hypergraph neural network for gait recognition based on event camera. 3rd International Conference on Advanced Algorithms and Signal Image Processing, June 30–July 2, 2023, Kuala Lumpur, Malaysia. 2023127994R[C]

[14]	Deng Y, Chen H, Liu Het al. . A voxel graph CNN for object classification with event cameras. IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18–24, 2022, New Orleans, LA, USA. 2022, New York, IEEE11621171[C]

[15]	Bi Y, Chadha A, Abbas Aet al. . Graph-based object classification for neuromorphic vision sensing. IEEE/CVF International Conference on Computer Vision, October 27–November 2, 2019, Seoul, Korea. 2019, New York, IEEE491501[C]

[16]	Bi Y, Chadha A, Abbas Aet al. . Graph-based spatio-temporal feature learning for neuromorphic vision sensing. IEEE transactions on image processing. 2020, 29: 9084-9098. J]

[17]	Schaefer S, Gehrig D, Scaramuzza D. AEGNN: asynchronous event-based graph neural networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18–24, 2022, New Orleans, LA, USA. 2022, New York, IEEE1236112371[C]

[18]	Oliveira R P D, Brites C, Ascenso Jet al. . Graph-based static 3D point clouds geometry coding. IEEE transactions on multimedia. 2019, 21(2): 284-299. J]

[19]	Fey M, Lenssen J E, Weichert Fet al. . SplineCNN: fast geometric deep learning with continuous B-spline kernels. IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18–23, 2018, Salt Lake City, UT, USA. 2018, New York, IEEE869877[C]