计算机应用 ›› 2021, Vol. 41 ›› Issue (4): 1100-1105.DOI: 10.11772/j.issn.1001-9081.2020060869

所属专题: 人工智能

• 人工智能 • 上一篇    下一篇

基于距离加权重叠度估计与椭圆拟合优化的精确目标跟踪算法

王宁1, 宋慧慧2, 张开华1   

  1. 1. 江苏省大数据分析技术重点实验室(南京信息工程大学), 南京 210044;
    2. 江苏省大气环境与装备技术协同创新中心(南京信息工程大学), 南京 210044
  • 收稿日期:2020-06-23 修回日期:2020-11-27 出版日期:2021-04-10 发布日期:2020-12-30
  • 通讯作者: 宋慧慧
  • 作者简介:王宁(1995—),男,河北邢台人,硕士研究生,主要研究方向:视觉目标跟踪;宋慧慧(1986—),女,山东聊城人,教授,博士,主要研究方向:遥感图像处理;张开华(1983—),男,山东日照人,教授,博士,CCF会员,主要研究方向:图像分割、目标跟踪。
  • 基金资助:
    国家新一代人工智能重大项目(2018AAA0100400);国家自然科学基金资助项目(61872189,61876088);江苏省自然科学基金资助项目(BK20191397)。

Accurate object tracking algorithm based on distance weighting overlap prediction and ellipse fitting optimization

WANG Ning1, SONG Huihui2, ZHANG Kaihua1   

  1. 1. Jiangsu Key Laboratory of Big Data Analysis Technology;(Nanjing University of Information Science and Technology), Nanjing Jiangsu 210044, China;
    2. Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology;(Nanjing University of Information Science and Technology), Nanjing Jiangsu 210044, China
  • Received:2020-06-23 Revised:2020-11-27 Online:2021-04-10 Published:2020-12-30
  • Supported by:
    This work is partially supported by the National New Generation Artificial Intelligence Major Project of China (2018AAA0100400), the National Natural Science Foundation of China (61872189, 61876088), the Natural Science Foundation of Jiangsu Province (BK20191397).

摘要: 为解决判别式相关滤波(DCF)跟踪算法在跟踪目标旋转或非刚性形变时的模型漂移、尺度粗糙、跟踪失败问题,提出一种基于距离加权重叠度估计与椭圆拟合优化的精确目标跟踪算法(DWOP-EFO)。首先,同时采用矩形框之间的重叠度和中心距离作为动态锚框质量评价的依据,能够缩小预测结果与目标区域之间的空间距离,缓解模型漂移问题;其次,为了进一步提高跟踪精度,采用轻量化的目标分割网络将目标从背景中分割出来,再利用椭圆拟合算法对分割轮廓进行优化并输出稳定的旋转矩形框,实现对目标尺度的精确估计;最后,通过尺度置信度优化策略对置信度高的尺度结果实现门控输出。所提算法能缓解模型漂移问题,同时有利于增强跟踪器的鲁棒性和提升跟踪精度。在两个最为流行的评测数据集VOT2018和OTB100上进行了实验,结果表明:在VOT2018数据集上,所提算法的期望平均重叠率(EAO)指标比基于重叠度最大化准确跟踪算法(ATOM)提高2.2个百分点,相较于基于可学习的判别模型跟踪器(DiMP)提高1.9个百分点;同时,所提算法在OTB100评测数据集上的成功率指标比ATOM高出1.3个百分点,特别是在非刚性形变属性上效果显著。所提算法在评测数据集上的平均运行速率均超过25 frame/s实现了实时跟踪。

关键词: 判别式相关滤波, 视觉跟踪, 目标分割, 距离加权, 椭圆拟合

Abstract: In order to solve the problems of Discriminative Correlation Filter(DCF) tracking algorithm such as model drift, rough scale and tracking failure when the tracking object suffers from rotation or non-rigid deformation, an accurate object tracking algorithm based on Distance Weighting Overlap Prediction and Ellipse Fitting Optimization(DWOP-EFO) was proposed. Firstly, the overlap and center-distance between bounding-boxes were both used as the basis for the evaluation of dynamic anchor boxes, which can narrow the spatial distance between the prediction result and the object region,easing the model drift problem. Secondly,in order to further improve the tracking accuracy,a lightweight object segmentation network was applied to segment the object from background, and the ellipse fitting algorithm was applied to optimize the segmentation contour result and output stable rotated bounding box, achieving accurate estimation of the object scale. Finally, a scale-confidence optimization strategy was used to realize gating output of the scale result with high confidence. The proposed algorithm can alleviate the problem of model drift, enhance the robustness of the tracker, and improve the accuracy of the tracker. Experiments were conducted on two widely used evaluation datasets Visual Object Tracking challenge(VOT2018) and Object Tracking Benchmark(OTB100). Experimental results demonstrate that the proposed algorithm improves Expected-Average-Overlap(EAO) index by 2.2 percentage points compared with Accurate Tracking by Overlap Maximization(ATOM) and by 1.9 percentage points compared with Learning Discriminative Model Prediction for tracking(DiMP). Meanwhile, on evaluation dataset OTB100, the proposed algorithm outperforms ATOM by 1.3 percentage on success rate index and shows significant performance especially on attribute of non-rigid deformation. the proposed algorithm runs over 25 frame/s averagely on evaluation datasets which realizes real-time tracking.

Key words: discriminative correlation filtering, visual tracking, object segmentation, distance weighting, ellipse fitting

中图分类号: