| 引用本文: | 黄鹤,张科,陈永安,王会峰,茹锋,王珺.一种无人机航拍目标的长期跟踪算法[J].哈尔滨工业大学学报,2022,54(5):104.DOI:10.11918/202105112 |
| HUANG He,ZHANG Ke,CHEN Yongan,WANG Huifeng,RU Feng,WANG Jun.A long-term tracking algorithm for UAV aerial photography[J].Journal of Harbin Institute of Technology,2022,54(5):104.DOI:10.11918/202105112 |
|
| |
|
|
| 本文已被：浏览 1182次 下载 755次 |
码上扫一扫！ |
|
|
| 一种无人机航拍目标的长期跟踪算法 |
|
黄鹤1,2,张科1,陈永安1,王会峰1,茹锋1,2,王珺2
|
|
(1.长安大学 电子与控制工程学院,西安 710064; 2.西安市智慧高速公路信息融合与控制重点实验室(长安大学),西安 710064)
|
|
| 摘要: |
| 针对无人机在航拍目标跟踪的复杂场景过程中,运动目标可能会被遮挡或不确定跟踪,导致视觉模型出现逐渐损坏、漂移和不可逆转失败等问题,提出了一种无人机航拍目标的长期跟踪算法。首先,进行互补分类器多特征自适应融合设计,在贝叶斯分类器中采用颜色直方图特征,在相关滤波器中采用方向梯度直方图、灰度以及颜色名特征；结合多种特征的优点,构建目标鲁棒性的外观以适应复杂场景。然后,在相关滤波器中加入自适应时空正则化项。在空间正则化参数中引入局部变化,实现学习时限制像素可信度较低的滤波器；而在时间正则化中,根据全局响应自适应地调整滤波器的学习,并用初始滤波器约束更新范围,这样在缓解边界效应的同时,有效防止滤波器退化。最后,在上述基础上,加入重检测模块,使得跟踪过程更加准确。实验结果表明,本文算法可以适应无人机航拍的复杂场景,缓解边界效应和防止滤波器退化。与同类主流算法相比,在目标经历严重遮挡、移出视野等情况后,仍然满足实时性需要,获得了较好的跟踪效果。 |
| 关键词: 长期跟踪 相关滤波 边界效应 滤波器退化 目标重检测 |
| DOI：10.11918/202105112 |
| 分类号:TP391.4 |
| 文献标识码:A |
| 基金项目:国家自然科学基金面上项目(52172324)；国家重点研发计划(2018YFB1600600)；陕西省重点研发计划(2021GY-5,1SF-483)；陕西省自然科学基础研究计划(2021JM-184)；西安市智慧高速公路信息融合与控制重点实验室(长安大学)开放基金(300102321502) |
|
| A long-term tracking algorithm for UAV aerial photography |
|
HUANG He1,2,ZHANG Ke1,CHEN Yongan1,WANG Huifeng1,RU Feng1,2,WANG Jun2
|
|
(1.School of Electronics and Control Engineering, Chang’an University, Xi’an 710064, China; 2.Xi’an Key Laboratory of Intelligent Expressway Information Fusion and Control (Chang’an University), Xi’an 710064, China)
|
| Abstract: |
| In view of the problem that the moving target may be occluded or tracked under uncertain conditions during the aerial target tracking of UAV in complex scenes, resulting in the gradual damage, drift, and irreversible failure of the visual model, a long-term tracking algorithm for UAV was proposed. Firstly, the complementary classifier was designed for multi-feature adaptive fusion. The color histogram feature was used in Bayesian classifier, and the directional gradient histogram, grayscale, and color name features were used in the correlation filter. In combination with the advantages of multiple features, the robust appearance of the target was built to adapt to the complex scenes. Secondly, an adaptive spatial-temporal regularization term was added to the correlation filter. Local changes were introduced into the spatial regularization parameters for the implementation of the filter with low pixel credibility during learning. In temporal regularization, the learning of the filter was adaptively adjusted according to the global response, and the initial filter was used to constrain the update range, which effectively prevented filter degradation while mitigating boundary effects. Finally, a re-detection module was added to make sure the accuracy of the tracking process. Experimental results show that the proposed algorithm could adapt to the complex scenes of UAV aerial photography, alleviate boundary effects, and prevent filter degradation. In comparison with similar mainstream algorithms, the proposed algorithm could still meet the real-time requirements and achieve better tracking effect even when the target experienced serious occlusion or moved out of view. |
| Key words: long-term tracking correlation filtering boundary effects filter degradation target re-detection |
|
|
|
|
