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%。
-
關(guān)鍵詞:
- 目標(biāo)跟蹤 /
- 實例樣本 /
- 支持向量機(jī)
Abstract: Most of the tracking-by-detection algorithms treat the tracking task as a category classification task, when the target experience deformation or encounter similar objects interference, the model drift is prone to occur. In this paper, a multi-exemplar regression tracking algorithm is proposed. In this algorithm, the exemplar model is considered to be more appropriate for tracking task, the exemplar model is set up by a frame image information, and the multi-exemplar model established in the time series can represent the target current state; in order to make the tracking algorithm adapt to the target deformation, the exemplar model is considered as the hidden variable by logistic regression model, together with the training sets from several recent frames sampling, can jointly build multi-exemplar regression tracking model. As the tracker builds multi-exemplar model on the whole, linking them together closely, it can effectively deal with the target deformation. Since the model drift only affects the exemplar model at current frame, each exemplar model is independent of each other, so the tracking algorithm can effectively reduce the influence of model drift on robust tracking. In the experiment, OTB 2013 benchmark and UAV 123 benchmark are used to verify the algorithm, DeepSRDCF, Siamese-fc and other algorithms act as the contrast algorithms, the experimental results show that the proposed tracker not only gives full play to the advantages of tracking based on multi-exemplar regression model, but also has good performance in deformation and background blur scene, and achieves three to five percent more than other advanced algorithms in the metrics of success rate and precision.-
Key words:
- Target tracking /
- Object exemplar /
- Support Vector Machine (SVM)
-
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. -
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
下載:
