一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號碼
標(biāo)題
留言內(nèi)容
驗證碼

基于多實例回歸模型的視覺跟蹤算法研究

張園強(qiáng) 查宇飛 庫濤 吳敏 畢篤彥

張園強(qiáng), 查宇飛, 庫濤, 吳敏, 畢篤彥. 基于多實例回歸模型的視覺跟蹤算法研究[J]. 電子與信息學(xué)報, 2018, 40(5): 1202-1209. doi: 10.11999/JEIT170717
引用本文: 張園強(qiáng), 查宇飛, 庫濤, 吳敏, 畢篤彥. 基于多實例回歸模型的視覺跟蹤算法研究[J]. 電子與信息學(xué)報, 2018, 40(5): 1202-1209. doi: 10.11999/JEIT170717
ZHANG Yuanqiang, ZHA Yufei, KU Tao, WU Min, BI Duyan. Visual Object Tracking Based on Multi-exemplar Regression Model[J]. Journal of Electronics & Information Technology, 2018, 40(5): 1202-1209. doi: 10.11999/JEIT170717
Citation: ZHANG Yuanqiang, ZHA Yufei, KU Tao, WU Min, BI Duyan. Visual Object Tracking Based on Multi-exemplar Regression Model[J]. Journal of Electronics & Information Technology, 2018, 40(5): 1202-1209. doi: 10.11999/JEIT170717

基于多實例回歸模型的視覺跟蹤算法研究

doi: 10.11999/JEIT170717
基金項目: 

國家自然科學(xué)基金(61472442, 61773397, 61701524),陜西省科技新星項目(2015KJXX-46)

Visual Object Tracking Based on Multi-exemplar Regression Model

Funds: 

The National Natural Science Foundation of China (61472442, 61773397, 61701524), The Young Star Science and Technology Program of Shaanxi Province (2015KJXX-46)

  • 摘要: 目前大部分基于檢測的跟蹤算法將跟蹤任務(wù)看作是一個類別分類的任務(wù),當(dāng)目標(biāo)發(fā)生形變或者遇到相似物體的干擾時,容易導(dǎo)致模型漂移。為此該文提出一種多實例回歸跟蹤算法。在該算法中,跟蹤任務(wù)被認(rèn)為建立在實例模型之上更為合適,為此該文利用一幀圖像建立實例模型,并在時間序列上建立多實例模型集合表征目標(biāo)的最近狀態(tài);為使跟蹤算法能夠適應(yīng)目標(biāo)的形變,利用邏輯回歸將實例模型作為隱變量,由最近若干幀建立的正負(fù)樣本集作為訓(xùn)練集,共同構(gòu)建多實例回歸跟蹤模型。由于跟蹤模型在整體上對多個實例模型建模,把它們緊密地聯(lián)系在一起,故能有效應(yīng)對目標(biāo)的形變;由于模型漂移僅會影響當(dāng)前幀的實例模型,各個實例模型之間互相獨立,故跟蹤算法能夠有效減輕模型漂移對魯棒跟蹤的影響。實驗中,OTB 2013數(shù)據(jù)庫和UAV 123數(shù)據(jù)庫被用來驗證該文算法,DeepSRDCF, Siamese-fc等算法作為對比算法,實驗結(jié)果表明,該文算法不僅充分發(fā)揮了基于多實例回歸模型進(jìn)行跟蹤的優(yōu)勢,在形變等屬性上具有很好的性能,而且在整體性能上優(yōu)于各類先進(jìn)算法3%~5%。
  • BI Duyan, KU Tao, ZHA Yufei, et al. Scale-adaptive objecttracking based on color names histogram[J]. Journal of Electronics Information Technology, 2016, 38(5): 1099-1106. doi: 10.11999/JEIT150921
    畢篤彥, 庫濤, 查宇飛, 等. 基于顏色屬性直方圖的尺度目標(biāo)跟蹤算法研究[J]. 電子與信息學(xué)報, 2016, 38(5): 1099-1106. doi: 10.11999/JEIT150921
    HARE S, SAFFARI A, TORR P H S, et al. Struck: Structured output tracking with kernels[C]. IEEE International Conference on Computer Vision, Barcelona, Spain, 2011: 263-270.
    ZHU G, PORIKLI F, and LI H. Beyond local search: Tracking objects everywhere with instance-specific proposals [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 943-951.
    DANELLJAN M, HAGER G, KHAN F S, et al. Learning spatially regularized correlation filters for visual tracking[C]. International Conference on Computer Vision, Santiago, Chile, 2015: 4310-4318.
    BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple: Complementary learners for real-time tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 1401-1409.
    GAO C, CHEN F, YU J G, et al. Robust visual tracking using exemplar-based detectors[J]. IEEE Transactions on Circuits Systems for Video Technology, 2017, 27(2): 300-312. doi: 10.1109/TCSVT.2015.2513700
    MALISIEWICZ T, GUPTA A, and ROS A A. Ensemble of exemplar-SVMs for object detection and beyond[C]. International Conference on Computer Vision, Barcelona, Spain, 2011: 89-96.
    TAO R, GAVVES E, and SMEULDER A W M. Siamese instance search for tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 1420-1429.
    BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional siamese networks for object tracking[C]. European Conference on Computer Vision, Amsterdam, Netherlands, 2016: 850-865.
    CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the devil in the details: Delving deep into convolutional nets[OL]. https://arxiv.org/abs/1405.3531, 2014.
    DENG J, DONG W, SOCHER R, et al. Imagenet: A large- scale hierarchical image database[C]. Computer Vision and Pattern Recognition, Miami, FL, USA, 2009: 248-255.
    PLATT J. Sequential minimal optimization: A fast algorithm for training support vector machines[J]. International Journal of Advanced Computer Science and Applications, 1998, 208(14): 98-112.
    NAM H, BAEK M, and HAN B. Modeling and propagating cnns in a tree structure for visual tracking[OL]. https://arxiv. org/abs/1608.07242.
    NAM H and HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 4293-4302.
    GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014: 580-587.
    FAN R E, CHANG K W, HSIEH C J, et al. LIBLINEAR: A library for large linear classification[J]. Journal of Machine Learning Research, 2008, 9(8): 1871-1874.
    WU Y, LIM J, and YANG M H. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition, Oregon, USA, 2013: 2411-2418.
    MUELLER M, SMITH N, and GHANEM B. A benchmark and simulator for uav tracking[C]. European Conference on Computer Vision, Amsterdam, Netherlands, 2016: 445-461.
    DANELLJAN M, HAGER G, KHAN F S, et al. Convolutional features for correlation filter based visual tracking[C]. International Conference on Computer Vision, Santiago, Chile, 2015: 621-629.
    ZHANG J, MA S, and SCLAROFF S. MEEM: Robust tracking via multiple experts using entropy minimization[C]. European Conference on Computer Vision, Zurich, Switzerland, 2014: 188-203.
    HONG Z, CHEN Z, WANG C, et al. Multi-store tracker (muster): A cognitive psychology inspired approach to object tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 749-758.
    DALAL N and TRIGGS B. Histograms of oriented gradients for human detection[C]. Computer Vision and Pattern Recognition, San Diego, CA, USA, 2005: 886-893.
  • 加載中
計量
  • 文章訪問數(shù):  1325
  • HTML全文瀏覽量:  178
  • PDF下載量:  258
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2017-07-19
  • 修回日期:  2017-12-11
  • 刊出日期:  2018-05-19

目錄

    /

    返回文章
    返回