Xiaokai Song

Xiaokai Song

Auto-generated profile, based on publicly available information

Xiaokai Song

College of Aerospace Science and Engineering and Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation, National University of Defense Technology, Changsha, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Xiangcheng ChenXiangcheng Chen
Xiangcheng Chen
XSXiaokai Song
Xiaokai Song
LCLei Cheng
Lei Cheng
RZRan Zipeng
Ran Zipeng
YWYajun WANG
Yajun WANG
Yuwei WangYuwei Wang
Yuwei Wang
The calibration of camera systems employing zoom lenses raises several challenges, as changes in lens control settings introduce various imaging conditions, especially different degrees of defocus. This article presents a Fourier-based defocus calibration method to calibrate a camera attached with an electronically focus-tunable lens (ETL). Different from the traditional method which requires changing the scale of the calibration object for sharp images, the proposed method is more concerned with the frequency characteristics of the captured images than the gray distributions. According to the invariance of the fundamental frequencies before and after defocusing the images, coordinates of feature points can be extracted accurately, even in different degrees of defocus. Therefore, one normal size target can also be qualified for zoom system calibration. Then polynomial approximation is used to account for the variation of the intrinsic and distortion parameters across the zoom range. Extensive simulations and experiments were implemented to demonstrate the proposed idea's robustness against defocus, flexibility, and accuracy.

5 February 2026
Verified
Preprint
Open access
XSXiaokai Song
Xiaokai Song
ZLZhang Li
Zhang Li
BGBanglei Guan
Banglei Guan
KWKun Wang
Kun Wang
YYYibin Ye
Yibin Ye
QYQifeng Yu
Qifeng Yu
Frame-based visual-inertial odometry (VIO) can be significantly enhanced by integrating event cameras, particularly in high-speed motion and high-dynamic-range (HDR) scenarios. However, existing VIO frameworks often process event and frame-based data simultaneously, introducing unnecessary computational overhead. Additionally, tracking handcrafted features on event streams typically requires extensive parameter tuning and lacks robustness against noise. To address these limitations, we propose Hybrid-EVIO, a method that effectively fuses event data, standard frames, and inertial measurement unit (IMU) measurements. Hybrid-EVIO consists of a hybrid visual front-end and a sliding-window-based back-end. The front-end combines traditional and learning-based techniques in a scene-adaptive manner: features are tracked using either conventional methods on frames or a learned sparse optical flow network on asynchronous events, depending on the imaging quality. IMU measurements are further utilized to construct epipolar constraints, prefiltering extreme outliers before Random Sample Consensus and thereby improving pose estimation accuracy. Finally, a tightly coupled, graph-based optimization framework integrates three sensor modalities for high-precision state estimation. We evaluate the proposed method on multiple representative and challenging public datasets. Our approach outperforms state-of-the-art methods, reducing trajectory errors by up to 34\% in the best case. Our trajectories and evaluation code are publicly available at https://github.com/sssxxxkkkk/hybrid_EVIO .

8 May 2026 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
XSXiaokai Song
Xiaokai Song
ZLZhang Li
Zhang Li
BGBanglei Guan
Banglei Guan
KWKun Wang
Kun Wang
YYYibin Ye
Yibin Ye
QYQifeng Yu
Qifeng Yu
Frame-based visual-inertial odometry (VIO) can be significantly enhanced by integrating event cameras, particularly in high-speed motion and high-dynamic-range (HDR) scenarios. However, existing VIO frameworks often process event and frame-based data simultaneously, introducing unnecessary computational overhead. Additionally, tracking handcrafted features on event streams typically requires extensive parameter tuning and lacks robustness against noise. To address these limitations, we propose Hybrid-EVIO, a method that effectively fuses event data, standard frames, and inertial measurement unit (IMU) measurements. Hybrid-EVIO consists of a hybrid visual front-end and a sliding-window-based back-end. The front-end combines traditional and learning-based techniques in a scene-adaptive manner: features are tracked using either conventional methods on frames or a learned sparse optical flow network on asynchronous events, depending on the imaging quality. IMU measurements are further utilized to construct epipolar constraints, prefiltering extreme outliers before Random Sample Consensus and thereby improving pose estimation accuracy. Finally, a tightly coupled, graph-based optimization framework integrates three sensor modalities for high-precision state estimation. We evaluate the proposed method on multiple representative and challenging public datasets. Our approach outperforms state-of-the-art methods, reducing trajectory errors by up to 34% in the best case. Our trajectories and evaluation code are publicly available at https://github.com/sssxxxkkkk/hybrid EVIO.