Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (8): 239-246.DOI: 10.3778/j.issn.1002-8331.2112-0360

• Graphics and Image Processing • Previous Articles     Next Articles

Dehazing Object Tracking Algorithm Using Dark Channel Prior

CHANG Jiashun, SUN Lifan, YANG Zhe, ZHANG Jinjin, FU Zhumu   

  1. School of Information Engineering, Henan University of Science and Technology, Luoyang, Henan 471023, China
  • Online:2023-04-15 Published:2023-04-15

融合暗通道先验的去雾目标跟踪算法

常家顺,孙力帆,杨哲,张金锦,付主木   

  1. 河南科技大学 信息工程学院,河南 洛阳 471023

Abstract: For tracking drift problem caused by the degradation of image quality and fuzzy background information in the haze scene, in the framework of siamese networks, combined with dark channel prior, this paper proposes a new dehazing object tracking algorithm. This algorithm dehazes the template image and the search image and extracts its features by using convolutional neural network. Lastly, according to the matching degree of its feature similarity, it estimates the target location. In addition, for the problem of insufficient data sets in haze scenes, this paper synthesizes artificially haze data sets (OTB-H, OTB-M, OTB-L) on the basis of the existing test data set OTB100. Finally, the proposed algorithm is compared with existing algorithms on each data set. The experimental results demonstrate that the proposed algorithm has better tracking performance in haze scenarios. The tracking accuracy is 0.713 under OTB-H data set and the tracking success rate is 0.519. Compared to SiamFC, tracking accuracy is improved by 35.6% and success rate is improved by 33.4%, and it meets the real-time requirements.

Key words: object tracking, image dehazing, siamese network, atmospheric scattering model, dark channel prior

摘要: 针对雾霾场景下,拍摄图像出现质量下降和背景信息模糊导致的跟踪漂移问题。在孪生网络框架下,融合暗通道先验提出一种新的去雾目标跟踪算法。通过对输入的模板图像和搜索区域图像去雾,继而利用卷积神经网络对其进行特征提取,根据其特征相似度匹配程度估计目标位置。此外,针对有雾场景数据集不足问题,在已有测试数据集OTB100的基础上人工合成有雾数据集(OTB-H、OTB-M、OTB-L),最后在各数据集上与现有算法进行对比实验。实验结果表明该算法在雾霾场景下有着更出色的跟踪性能,在数据集OTB-H下跟踪精确度为0.713,跟踪成功率为0.519,相比于SiamFC跟踪精确度提升了35.6%,成功率提升了33.4%,且满足实时性的要求。

关键词: 目标跟踪, 图像去雾, 孪生网络, 大气散射模型, 暗通道先验