基于深度特征表達(dá)與學(xué)習(xí)的視覺(jué)跟蹤算法研究

李寰宇; 畢篤彥; 楊源; 查宇飛; 覃兵; 張立朝

doi:10.11999/JEIT150031

基于深度特征表達(dá)與學(xué)習(xí)的視覺(jué)跟蹤算法研究

doi: 10.11999/JEIT150031 cstr: 32379.14.JEIT150031

1.
(空軍工程大學(xué)航空航天工程學(xué)院西安 710038)
2.
(空軍工程大學(xué)空管領(lǐng)航學(xué)院西安 710051)

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61202339, 61472443)和航空科學(xué)基金(20131996013)

計(jì)量
- 文章訪(fǎng)問(wèn)數(shù): 2249
- HTML全文瀏覽量: 222
- PDF下載量: 2034
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2015-01-06
- 修回日期: 2015-04-28
- 刊出日期: 2015-09-19

Research on Visual Tracking Algorithm Based on Deep Feature Expression and Learning

2.
(College of Aerospace Engineering, Air Force Engineering University, Xi&rsquo

摘要

摘要: 該文針對(duì)視覺(jué)跟蹤中運(yùn)動(dòng)目標(biāo)的魯棒性跟蹤問(wèn)題，將深度學(xué)習(xí)引入視覺(jué)跟蹤領(lǐng)域，提出一種基于多層卷積濾波特征的目標(biāo)跟蹤算法。該算法利用分層學(xué)習(xí)得到的主成分分析(PCA)特征向量，對(duì)原始圖像進(jìn)行多層卷積濾波，從而提取出圖像更深層次的抽象表達(dá)，然后利用巴氏距離進(jìn)行特征相似度匹配估計(jì)，進(jìn)而結(jié)合粒子濾波算法實(shí)現(xiàn)目標(biāo)跟蹤。結(jié)果表明，這種多層卷積濾波提取到的特征能夠更好地表達(dá)目標(biāo)，所提跟蹤算法對(duì)光照變化、遮擋、異面旋轉(zhuǎn)、攝像機(jī)抖動(dòng)都具有很好的不變性，對(duì)平面內(nèi)旋轉(zhuǎn)也具有一定的不變性，在具有此類(lèi)特點(diǎn)的視頻序列上表現(xiàn)出非常好的魯棒性。
- 視覺(jué)跟蹤 /
- 深度學(xué)習(xí) /
- 主成分分析 /
- 卷積神經(jīng)網(wǎng)絡(luò) /
- 粒子濾波
Abstract: For the robustness of visual object tracking, a new tracking algorithm based on multi-stage convolution filtering feature is proposed by introducing deep learning into visual tracking. The algorithm uses the Principal Component Analysis (PCA) eigenvectors obtained by stratified learning, to extract the deeper abstract expression of the original image by multi-stage convolutional filtering. Then the Bhattacharyya distance is used to evaluate the similarity among features. Finally, particle filter algorithm is combined to realize target tracking. The result shows that the feature obtained by multi-stage convolution filtering can express target better, the proposed algorithm has a better inflexibility to illumination, covering, rotation, and camera shake, and it exhibits very good robustness in video sequence with such characteristics.
- Visual tracking /
- Deep learning /
- Principal Component Analysis (PCA) /
- Convolutional neural network /
- Particle filter

HTML全文

參考文獻(xiàn)(23)

Li X, Hu W M, and Shen C H. A survey of appearance models in visual object tracking[J]. ACM Transactions on Intelligent Systems and Technology, 2013, 4(4): 5801-5848.

Hinton G E and Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.

Clement F, Camille C, Laurent N, et al.. Learning hierarchical features for scene labeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1915-1929.

Alex K, Sutskever I, and Hinton G E. ImageNet classification with deep convolutional neural networks[C]. Proceedings of Advances in Neural Information Processing Systems, Lake Tahoe, 2012: 748-764.

Zhou S S, Chen Q C, and Wang X L. Convolutional deep networks for visual data classification[J]. Neural Processing Letters, 2013, 38(11): 17-27.

Abdel-Hamid O, Mohamed A R, Jiang H, et al.. Convolutional neural networks for speech recognition[J]. ACM Transactions on Audio, Speech, and Language Processing, 2014, 22(10): 1533-1545.

Chen X Y, Xiang S M, and Li C L. Vehicle detection in satellite images by hybrid deep convolutional neural networks [J]. IEEE Transactions on Geoscience and Remote Sensing Letters, 2014, 11(10): 1797-1801.

Evgeny A S, Denis M T, and Serge N A. Comparison of regularization methods for imagenet classification with deep convolutional neural networks[J]. AASRI Procedia, 2014, 6(8): 89-94.

Baldi P and Hornik K. Neural networks and principal component analysis: learning from examples without local minima[J]. Neural Networks, 1989, 2(1): 53-58.

Ross D, Lim Jong-woo, and Lin Ruei-Sung. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(1): 125-141.

姚志均. 一種新的空間直方圖相似性度量方法及其在目標(biāo)跟蹤中的應(yīng)用[J]. 電子與信息學(xué)報(bào), 2013, 35(7): 1644-1649.

Yao Z J. A new spatiogram similarity measure method and its application to object tracking[J]. Journal of Electronics Information Technology, 2013, 35(7): 1644-1649.

Zhang K H, Zhang L, and Yang M H. Real-time compressive tracking[C]. Proceedings of Europe Conference on Computer Vision, Florence, 2012: 864-877.

Sevilla-Lara L and Learned-Miller E. Distribution fields for tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Colorado, 2011: 1910-1917.

Shaul O, Aharon B H, and Dan L. Locally orderless tracking[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, 2012: 1940-1947.

Henriques J F, Caseiro R, and Martins P. High-speed tracking with kernelized correlation filters[J]. IEEE

Transactions on Pattern Analysis and Machine Intelligence, 2015, DOI: 10.1109/TPAMI.2014.2345390.

Hare S, Saffari A, and Torr P H S. Struck：structured output tracking with kernels[C]. Proceedings of IEEE International Conference on Computer Vision, Colorado, 2011: 263-270.

Thang Ba Dinh, Nam Vo, and Medioni G. Context tracker: exploring supporters and distracters in unconstrained environments[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado, 2011: 1177-1184.

Liu Bai-yang, Huang Jun-zhou, and Yang Lin. Robust tracking using local sparse appearance model and K-selection [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado, 2011: 1313-1320.

Junseok K and Kyoung M. Tracking by sampling trackers[C]. Proceedings of IEEE International Conference on Computer Vision, Colorado, 2011: 1195-1202.

Amit Adam, Ehud Rivlin, and Ilan Shimshoni. Robust fragments-based tracking using the integral histogram[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado, 2006: 798-805.

Dorin Comaniciu, Visvanathan Ramesh, and Meer P. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪(fǎng)問(wèn)統(tǒng)計(jì)