自适应尺度特征融合的异常重检跟踪算法

针对核相关滤波(KCF)跟踪算法中无法处理目标尺度变化以及单一特征的局限性问题,并避免在目标遮挡、形变等情况下跟踪器对目标的丢失,提出一种自适应尺度特征融合的异常重检(SFAR)跟踪算法。通过融合多尺度及颜色特征后的核相关滤波器,检测跟踪目标并得到多尺度图像,然后根据提取的多尺度图像去训练成多尺度目标模型,在其过程中引入峰值的异常值判定来矫正,若发生异常峰值则判定目标跟踪丢失,后进入重检机制。在公开的OTB-50数据集上测试,实验结果表明,改进算法精度为0.740,成功率为0.591,跟踪效果得到显著提升。

Anomaly Detection Method Using Feature Reconstruction Based Knowledge Distillation

In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationship between samples,resulting in poor accuracy in recognizing anomalous samples.To address this problem,a knowledge distillation anomaly detection method based on feature reconstruction was proposed in this study.Knowledge distillation was performed after inverting the structure of the teacher-student network to avoid the teacher-student network sharing the same inputs and similar structure.Representability was improved by using feature splicing to unify features at different levels,and the merged features were processed and reconstructed using an improved Transformer.The experimental results show that the proposed method achieves better performance on the MVTec dataset,verifying its effectiveness and feasibility in anomaly detection tasks.This study provides a new idea to improve the accuracy and efficiency of anomaly detection.

视频中快速运动目标的自适应模型跟踪算法

针对现有视频跟踪算法因目标运动机动性强或非对称刚体目标快速变形等情况导致的目标丢失问题,提出了一种基于相关滤波自适应模型与平均峰值相关能量(APCE)重检机制的视频跟踪算法。自适应模型跟踪算法可根据目标区域的清晰度实时调整模型,有效保证目标跟踪模型的准确性。实验结果表明,将自适应模型跟踪算法融入判别式尺度空间跟踪(DSST)模型中,可增强模型对机动性强或快速变形物体的跟踪效果,在保证跟踪速度的同时,使原始DSST模型的平均精度提高了18.3个百分点,成功率提高了15.2个百分点。此外,将自适应模型跟踪算法与APCE重检机制相结合,可保证跟踪算法的稳定性。