Visual Tracking Algorithm Based on Global Context and Feature Dimensionality Reduction
-
摘要: 相关滤波算法容易受到形变、运动模糊、相似背景等因素的干扰，导致跟踪任务失败。为了克服以上问题，该文提出一种基于全局背景与特征降维的视觉跟踪算法。该算法首先提取紧邻目标的图像区域作为负样本供分类器学习，以抑制相似背景的干扰；然后提出一种基于主成分分析的更新策略，构建降维矩阵压缩HOG特征的维度，在更新分类器的同时减少其冗余度；最后加入颜色特征表征运动目标，并根据特征对系统状态的响应强度进行自适应融合。在标准数据集上将该文提出的算法与Staple, KCF等其他算法进行了仿真对比，结果表明该文算法具有更强的鲁棒性，在形变因素的影响下，所提出的算法与Staple和KCF算法相比距离精度分别提升8.3%和13.1%。Abstract: Tracking effects of algorithms using correlation filter are easily interfered by deformation, motion blur and background clustering, which can result in tracking failure. To solve these problems, a visual tracking algorithm based on global context and feature dimensionality reduction is proposed. Firstly, the image patches uniformly around the target are extracted as negative sample, and thus the similar background patches around the target are suppressed. Then, an update strategy based on principal component analysis is proposed, constructing the matrix to reduce the dimensionality of HOG feature, which can reduce the redundancy of feature when it updates. Finally, the color features are added to represent the motion target and the response of the system states are adaptively fused according to the features. Experiments are performed on recent online tracking benchmark. The results show that the proposed method performs favorably both in terms of accuracy and robustness compared to the state-of-the-art trackers such as Staple or KCF. When deformation occur, the proposed method is shown to outperform the Staple tracker and KCF algorithm by 8.3% and 13.1% respectively in median distance precision.
-
表 1 基于全局背景与特征降维的视觉跟踪算法
输入：图像 ${I_1}$, ${I_1}$, ···, ${I_T\,}$，目标的初始位置 ${x_1}$。 输出：每帧图像中目标的位置 ${x_t}$。 (1)For t=1, 2, ···,T–1 do； (2)根据输入图像 ${I_t}$和目标位置 ${x_t}$进行全局背景提取，利用HOG特征表征目标以及背景，获得基于HOG特征的训练样本；同时采集图像块
并提取颜色特征；(3)构建降维矩阵压缩HOG特征，并利用式(11)对分类器模型进行参数更新； (4)利用颜色特征表征的样本训练更新直方图分类器； (5)根据输入图像 ${I_{t + 1}}$采集检测样本，并分别提取HOG和颜色特征；然后根据式(10)构建降维矩阵，以压缩32维HOG特征至17维，得到降
维后的检测样本；(6)将HOG和颜色特征表征的检测样本送入相应的分类器，由式(12)计算得到基于HOG特征的响应图 ${f_t}$；利用直方图滤波器进行检测，获
得基于颜色特征的响应图 ${f_h}$；(7)根据式(13)计算特征权重 ${\gamma _i}$；然后利用式(14)将 ${f_t}$和 ${f_h}$自适应融合，得到最终响应图 $f$；最后查找响应图 $f$的峰值来确定目标位置 ${x_{t{\rm{ + }}1}}$。 (8)End for 
下载: 导出CSV
表 2 视频序列及其描述
序列 帧数 场景特征 Skiing 81 形变、快速运动、复杂背景 Football 81 运动模糊、背景干扰、形变 Freeman 297 背景干扰、形变 Singer 351 背景干扰、光照变化、尺度变化 Jumping 313 运动模糊、快速运动 Deer 71 快速运动、运动模糊
下载: 导出CSV
-
齐苑辰, 吴成东, 陈东岳, 等. 基于稀疏表达的超像素跟踪算 法[J]. 电子与信息学报, 2015, 37(3): 529–535 doi: 10.11999/JEIT140374QI Yuanchen, WU Chengdong, CHEN Dongyue, et al. Superpixel tracking based on sparse representation[J]. Journal of Electronics&Information Technology, 2015, 37(3): 529–535 doi: 10.11999/JEIT140374 JI Hui, LING Haibin, WU Yi, et al. Real time robust L1 tracker using accelerated proximal gradient approach[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 1830–1837. KWON J and LEE K M. Tracking by sampling trackers[C]. International Conference on Computer Vision, Barcelona, Spain, 2011: 1195–1202. LIU Baiyang, HUANG Junzhou, KULIKOWAKI C, et al. Robust visual tracking using local sparse appearance model and k-selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2968–2981 doi: 10.1109/tpami.2012.215 HARE S, SAFFARI A, and TORR P H S. Struck: Structured output tracking with kernels[C]. International Conference on Computer Vision, Barcelona, Spain, 2011: 263–270. KALAL Z, MATAS J, and MIKOLAJCZYK K. P-N learning: Bootstrapping binary classifiers by structural constraints[C]. IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 49–56. BABENKO B, YANG Minghsuang, and BELONGIE S. Visual tracking with online multiple instance learning[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 983–990. 孙航, 李晶, 杜博, 等. 基于多阶段学习的相关滤波目标跟踪[J]. 电子学报, 2017, 45(10): 2337–2342 doi: 10.3969/j.issn.0372-2112.2017.10.004SUN Hang, LI Jing, DU Bo, et al. Correlation filtering target tracking based on online multi-lifespan learning[J]. Acta Electronica Sinca, 2017, 45(10): 2337–2342 doi: 10.3969/j.issn.0372-2112.2017.10.004 BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]. IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 2544–2550. HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]. Proceedings of European Conference on Computer Vision, Florence, Italy, 2012: 702–715. HENRIQUES J F, RUI C, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2015, 37(3): 583–596 doi: 10.1109/tpami.2014.2345390 DANELLJAN M, HÄGER G, KHAN F, et al. Accurate scale estimation for robust visual tracking[C]. Proceedings of British Machine Vision Conference, Nottingham, UK, 2014: 65.1–65.11. MUELLER M, SMITH N, and GHANEM B. Context-aware correlation filter tracking[C]. IEEE International Conference on Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 1387–1395. BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple: Complementary learners for real-time tracking[C]. IEEE International Conference on Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1401–1409. 邬战军, 牛敏, 许冰, 等. 基于谱回归特征降维与后向传播神经网络的识别方法研究[J]. 电子与信息学报, 2016, 38(4): 978–984 doi: 10.11999/JEIT150781WU Zhanjun, NIU Min, XU Bing, et al. Research on recognition method based on spectral regression and back propagation neural network[J]. Journal of Electronics&Information Technology, 2016, 38(4): 978–984 doi: 10.11999/JEIT150781 侯志强, 张浪, 余旺盛, 等. 基于快速傅里叶变换的局部分块视觉跟踪算法[J]. 电子与信息学报, 2015, 37(10): 2397–2404 doi: 10.11999/JEIT150183HOU Zhiqiang, ZHANG Lang, YU Wangsheng, et al. Local patch tracking algorithm based on fast fourier transform[J]. Journal of Electronics&Information Technology, 2015, 37(10): 2397–2404 doi: 10.11999/JEIT150183 DANELLJAN M, HAGER G, KHAN F S, et al. Discriminative scale space tracking[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2017, 39(8): 1561–1575 doi: 10.1109/tpami.2016.2609928 熊昌镇, 赵璐璐, 郭芬红. 自适应特征融合的核相关滤波跟踪 算法[J]. 计算机辅助设计与图形学学报, 2017, 29(6): 1068–1074 doi: 10.3969/j.issn.1003-9775.2017.06.012XIONG Changzhen, ZHAO Lulu, and GUO Fenhong. Kernelized correlation filters tracking based on adaptive feature fusion[J]. Journal of Computer-Aided Design&Computer Graphics, 2017, 29(6): 1068–1074 doi: 10.3969/j.issn.1003-9775.2017.06.012 WU Yi, LIM J, and YANG Minghsuan. Online object tracking: a benchmark[C]. Proceedings of the Computer Vision and Pattern Recognition, Portland, USA, 2013: 2411–2418. -
图(3) / 表(2)
计量
- 文章访问数: 1631
- HTML全文浏览量: 447
- PDF下载量: 64
- 被引次数: 0
下载:
