Zhang Yinhuan, Xiao Qinkun, Liu Xing, Wei Yongquan, Xue Jingyun
School of Mechatronic Engineering, Xi'an Technological University, Xi'an, 710021, China.
Civil & Architectural Engineering, Weinan Vocational & Technical College, Weinan, 714000, China.
Sci Rep. 2025 Mar 11;15(1):8334. doi: 10.1038/s41598-025-92957-y.
This paper addresses the challenge of reconstructing the motion process of the safety and arming (S&A) mechanism in fuze by transforming the problem into a target detection and tracking problem. A novel tracking method, which fuses an improved Kalman filter with a temporal scale-adaptive KCF (AKF-CF), is proposed. The methodology introduces key innovations: (1) Extraction of grayscale images and directional gradient histogram (HOG) features of the target, followed by the use of an Adaptive Wave PCA-Autoencoder (AWPA) method to accurately capture multi-modal and multi-scale features of the target; (2) Application of bilinear interpolation and hybrid filtering techniques to generate a spatial and temporal scale-adaptive bounding box for the filtered target, enabling dynamic adjustment of the tracking box size; (3) Integration of an occlusion-aware mechanism using average peak correlation energy (APCE) to trigger Kalman-based position prediction when the target is occluded, thus mitigating tracking drift. Finally, the tracking curve of the target is plotted, facilitating the reconstruction of the S&A mechanism's motion trajectory. Experimental results from five datasets indicate the effectiveness of the proposed method. Compared to the ACSRCF algorithm on the OTB50 dataset, the proposed method achieves accuracy and success rate improvements of 0.8 and 0.6%, respectively. On the OTB100 dataset, it attains 92.50% accuracy and 68.10% success rate, outperforming other related filtering algorithms. These results highlight significant improvements in tracking accuracy and success rate, demonstrating the algorithm's robustness in handling challenging tracking scenarios. Additionally, the reconstructed motion curves effectively replicate mechanical trajectories, showcasing strong performance in complex occlusion environments.
本文通过将引信中安全与解除保险（S&A）机构的运动过程重建问题转化为目标检测与跟踪问题，来应对这一挑战。提出了一种将改进的卡尔曼滤波器与时间尺度自适应核相关滤波器（AKF-CF）相融合的新型跟踪方法。该方法引入了关键创新点：（1）提取目标的灰度图像和方向梯度直方图（HOG）特征，随后使用自适应波主成分分析自动编码器（AWPA）方法准确捕捉目标的多模态和多尺度特征；（2）应用双线性插值和混合滤波技术为滤波后的目标生成空间和时间尺度自适应的边界框，实现跟踪框大小的动态调整；（3）集成一种基于平均峰值相关能量（APCE）的遮挡感知机制，在目标被遮挡时触发基于卡尔曼的位置预测，从而减轻跟踪漂移。最后，绘制目标的跟踪曲线，便于重建S&A机构的运动轨迹。来自五个数据集的实验结果表明了所提方法的有效性。在OTB50数据集上，与ACSRCF算法相比，所提方法的准确率和成功率分别提高了0.8%和0.6%。在OTB100数据集上，其准确率达到92.50%，成功率达到68.10%，优于其他相关滤波算法。这些结果突出了跟踪准确率和成功率的显著提高，证明了该算法在处理具有挑战性的跟踪场景时的鲁棒性。此外，重建的运动曲线有效地复制了机械轨迹，在复杂遮挡环境中表现出强大性能。
