融合暗通道先验的去雾目标跟踪算法

doi:10.3778/j.issn.1002-8331.2112-0360

摘要/Abstract

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

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

常家顺, 孙力帆, 杨哲, 张金锦, 付主木. 融合暗通道先验的去雾目标跟踪算法[J]. 计算机工程与应用, 2023, 59(8): 239-246.

CHANG Jiashun, SUN Lifan, YANG Zhe, ZHANG Jinjin, FU Zhumu. Dehazing Object Tracking Algorithm Using Dark Channel Prior[J]. Computer Engineering and Applications, 2023, 59(8): 239-246.

参考文献

[1] 王道累，张天宇.图像去雾算法的综述及分析[J].图学学报，2020，41（6）：861-870.
WANG D L，ZHANG T Y.Review and analysis of image defogging algorithm[J].Journal of Graphics，2020，41（6）：861-870.
[2] 王德俊，王建立，阴玉梅，等.基于FPGA的实时图像改进直方图均衡化算法[J].微电子学与计算机，2010（5）：87-89.
WANG D J，WANG J L，YIN Y M，et al.Algorithm of improved histogram equalization for real-time image based on FPGA[J].Microelectronics & Computer，2010（5）：87-89.
[3] FEBIN I P，JIDESH P，BINI A A.A retinex based variational model for enhancement and restoration of low contrast remote sensed images corrupted by shot noise[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，13：941-949.
[4] HE K，JIAN S，FELLOW，et al.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2011，33（12）：2341-2353.
[5] WANG C，DING M，ZHANG Y，et al.A single image enhancement technique using dark channel prior[J].Applied Sciences，2021，11（6）：2712.
[6] PAN Y，CHEN Z，LI X，et al.Single-image dehazing via dark channel prior and adaptive threshold[J].International Journal of Image and Graphics，2021：2150053.
[7] 李一菲，杨燕，张国强.基于补偿暗通道和透射率融合的图像去雾算法[J].计算机工程与应用，2019，55（3）：196-201.
LI Y F，YANG Y，ZHANG G Q.Image haze removal algorithm based on compensation of dark channel and transmission fusion[J].Computer Engineering and Applications，2019，55（3）：196-201.
[8] HENRIQUES J F，CASEIRO R，MARTINS P，et al.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2015，37（3）：583-596.
[9] MCLEOD D R，GRIFFITHS R R.An automated version of the digit symbol substitution test （DSST）[J].Behavior Research Methods & Instrumentation，1982，14（5）：463-466.
[10] YANG L，ZHU J.A scale adaptive kernel correlation filter tracker with feature integration[C]//European Conference on Computer Vision.Cham：Springer，2014.
[11] ZHANG Z，XIE Y，XING F，et al.MDNet：a semantically and visually interpretable medical image diagnosis network[C]//IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：3549-3557.
[12] LMEZ E，AKDOAN V，KORKMAZ M，et al.Automatic segmentation of meniscus in multispectral MRI using regions with convolutional neural network（R-CNN）[J].Journal of Digital Imaging，2020，33（4）：916-929.
[13] BERTINETTO L，VALMADRE J，HENRIQUES J F，et al.Fully-convolutional siamese networks for object tracking[M].Cham：Springer，2016.
[14] LI B，YAN J，WU W，et al.High performance visual tracking with siamese region proposal network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2018.
[15] NARASIMHAN S G，NAYAR S K.Chromatic framework vision in bad weather[C]//IEEE Conference on Computer Vision and Pattern Recognition，2002：598-605.
[16] NARASIMHAN S G，NAYAR S K.Vision and the atmosphere[J].International Journal of Computer Vision，2002，48（3）：233-254.
[17] 解宇虹，谢源，陈亮，等.真实有雾场景下的目标检测[J].计算机辅助设计与图形学学报，2021，33（5）：733-745.
XIE Y H，XIE Y，CHEN L，et al.Object detection in real-world hazy scene[J].Journal of Computer-Aided Design & Computer Graphics，2021，33（5）：733-745.
[18] 李益红，周晓谊.一种多分辨多尺度的Retinex彩色图像增强算法[J].计算机工程与应用，2017，53（16）：193-198.
LI Y H，ZHOU X Y.Multi-resolution and multi-scale retinex for color image enhancement[J].Computer Engineering and Applications，2017，53（16）：193-198.
[19] JOBSON D J，RAHMAN Z，WOODELL G A.A multiscale retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Transactions on Image Processing，2002，6（7）：965-976.
[20] WANG J，LU K，XUE J，et al.Single image dehazing based on the physical model and MSRCR algorithm[J].IEEE Transactions on Circuits and Systems for Video Technology，2018，28（9）：2190-2199.
[21] DANELLJAN M，H?GER G，KHAN F S，et al.Discrimi-
native scale space tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（8）：1561-1575.
[22] DANELLJAN M，HAGER G，KHAN F S，et al.Learning spatially regularized correlation filters for visual tracking[C]//2015 IEEE International Conference on Computer Vision（ICCV），2015.
[23] BERTINETTO L，VALMADRE J，GOLODETZ S，et al.Staple：complementary learners for real-time tracking[C]//Computer Vision & Pattern Recognition，2016.