基于局部差別性分析的目標跟蹤算法

田鵬; 呂江花; 馬世龍; 汪溁鶴

doi:10.11999/JEIT170045

基于局部差別性分析的目標跟蹤算法

doi: 10.11999/JEIT170045

基金項目:

國家自然科學基金(61300007)

計量
- 文章訪問數(shù): 1252
- HTML全文瀏覽量: 111
- PDF下載量: 305
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-01-02
- 修回日期: 2017-07-20
- 刊出日期: 2017-11-19

Robust Object Tracking Based on Local Discriminative Analysis

Funds:

The National Natural Science Foundation of China (61300007)

摘要

摘要: 在復雜場景下，為了更好地提升跟蹤的魯棒性，基于局部的相似度測量得到了廣泛應(yīng)用。然而，局部遮擋，形變和光照變化等場景的復雜性，基于傳統(tǒng)局部相似度測量的目標跟蹤存在很大缺點，例如，在跟蹤過程中，僅僅依靠目標和模板的匹配度容易造成跟蹤的偏移現(xiàn)象。鑒于此，該文提出一種基于局部差別性相似度測量的目標跟蹤算法。首先，以目標-背景的差異性，形成相似性和差異性相結(jié)合的局部判別性相似度測量；其次，基于子塊在視頻序列中的差異性，對子塊進行差異性學習，以提高跟蹤的準確性。最后，在粒子濾波框架下，基于差別性局部區(qū)域測量構(gòu)建了一種有效的目標跟蹤算法。實驗結(jié)果表明，在復雜圖像序列中，該算法實現(xiàn)了目標的準確跟蹤，并在光照變化、旋轉(zhuǎn)、縮放和遮擋等方面具有較好的效果。
- 目標跟蹤 /
- 局部稀疏表示 /
- 相似度測量 /
- 判別性分析 /
- 差異性權(quán)重
Abstract: The local similarity measurements are usually used for improving the tracking robustness under the complex scene. However, this method have drawbacks in cases of partial occlusion, deformation and rotation. For example, the method only considers traditional similarity measurements of targets and templates, results in the matching errors to lead to tracking failure. In this paper, a target tracking algorithm is proposed based on measurements of the local difference similarities. The presented method has the following advantages: firstly, both similarities and differences are considered for measurement; secondly, the differential weight learning of the local region is carried out to improve the accuracy of sub-block difference measurement; at last, an effective and efficient tracker is designed based on the difference analysis and a simple update manner within the particle filter framework. Experimental results show that the proposed algorithm achieves better performance than traditional competing methods in various factors, such as illumination changes, part occlusion, scale changes and so on.
- Object tracking /
- Local sparse representation /
- Similarity measurement /
- Discriminative analyses /
- Difference weight

HTML全文

參考文獻(25)

劉紅亮, 周生華, 劉宏偉, 等. 一種航跡恒虛警的目標檢測跟蹤一體化算法[J]. 電子與信息學報, 2016, 38(5): 1072-1078. doi: 10.11999/JEIT150638.

LIU Hongliang, ZHOU Shenghua, LIU Hongwei, et al. An integrated target detection and tracking algorithm with constant track false alarm rate[J]. Journal of Electronics Information Technology, 2016, 38(5): 1072-1078. doi: 10.11999/JEIT150638.

MARKUS Z, THOMAS N, and ANDREAS K. Tracking human locomotion by relative positional feet tracking[C]. 2015 IEEE Virtual Reality (VR), Arles, France, 2015: 317-318.

EVANGELO S, HATICE G, and ANDREA C. Automatic analysis of facial affect: A survey of registration, representation, and recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(6): 1113-1133.

SAI Y, BO X, Li P Y, et al. Robust scene matching method based on sparse representation and iterative correction[J]. Image and Vision Computing, 2017, 60(4): 115-123.

PENG P L, ERIK B, and HAI B L. Encoding color information for visual tracking: algorithms and benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5630-5644. doi: 10.1109/TIP.2015.2482905.

BABENKO B, YANG M H, and BELONG S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632. doi: 10.1109/TPAMI.2010.226.

ZHANG K, ZHANG L, and YANG M H. Real-time object tracking via online discriminative feature selection[J]. IEEE Transactions on Image Processing, 2013, 22(12): 4664-4677. doi: 10.1109/TIP.2013.2277800.

LAURA S L and ERIK L M. Distribution fields for tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 1910-1917.

BAO C, WU Y, LING H, et al. Real time robust L1 tracker using accelerated proximal gradient approach[C]. IEEE Conference Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 2012: 1830-1837.

MEI X, LING H, and WU Y. Efficient minimum error bounded particle resampling LI tracker with occlusion detection[J]. IEEE Transactions on Image Processing, 2013, 22(7): 2661-2675.

KWON J and LEE K M. Highly non-rigid object tracking via patch-based dynamic appearance modeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(10): 2427-2441.

LIU B, HUANG J, YANG L, et al. Robust tracking using local sparse appearance model and k-selection[C]. IEEE Conference on Computer Vision and Pattern Recognition. Colorado, CO, USA, 2011, 201: 1313-1320.

JIA X, LU H, and YANG M H. Visual tracking via adaptive structural local sparse appearance model[C]. IEEE Conference Computer Vision and Pattern Recognition (CVPR), USA, 2012: 1822-1829.

ADAM A, RIVLINi E, and SHIMSHONI I. Robust fragment- based tracking using the integral histogram[C]. IEEE Conference Computer Vision and Pattern Recognition (CVPR), USA, 2006: 798-805.

HE S, YANG Q, and Yang M H. Visual tracking via locality sensitive histograms[C]. IEEE Conference Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA, 2013: 2427-2434.

JIA Y M, HUA B, JI Z, et al. Robust feature matching for remote sensing image registration via locally linear transforming[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(12): 6469-6481. doi: 10.1109/ TGRS.2015.2441954.

WANG D, LU H C, and BO C J. Visual tracking via weighted local cosine similarity[J]. IEEE Transactions on Cybernetics, 2015, 45(9): 1838-1850. doi: 10.1109/TCYB. 2014.2360924.

LIU H C, LI S T, and FANG L Y. Robust object tracking based on principal component analysis and local parse representation[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64(11): 2863-2875. doi: 10.1109/TIM. 2015.2437636.

ZHUANG B H, LU H C, XIAN Z Y, et al. Visual tracking via discriminative sparse similarity map[J]. IEEE Transactions on Image Processing, 2014, 23(4): 1872-1881. doi: 10.1109/ TIP.2014.2308414.

畢篤彥, 庫濤, 查宇飛, 等. 基于顏色屬性直方圖的尺度目標跟蹤算法研究[J]. 電子與信息學報, 2016, 38(5): 1009-1106. doi: 10.11999/JEIT150921.

BI Duyan, KU Tao, ZHA Yufei, et al. Scale-adaptive object tracking based on color names histogram[J]. Journal of Electronics Information Technology, 2016, 38(5): 1009-1106. doi: 10.11999/JEIT150921.

占榮輝, 劉盛啟, 歐建平, 等. 基于序貫蒙特卡羅概率假設(shè)密度濾波的多目標檢測前跟蹤改進算法[J]. 電子與信息學報, 2014, 36(11): 2593-2599. doi: 10.3724/SP.J.1146.2013.02029.

ZHAN Ronghui, LIU Shengqi, OU Jianping , et al. Improved multi target track before detect algorithm using the sequential monte carlo probability hypothesis density filter[J]. Journal of Electronics Information Technology, 2014, 36(11): 2593-2599. doi: 10.3724/SP.J.1146.2013.02029.

ORONR S and AHARON B H. Locally orderless tracking[J]. International Journal of Computer Vision, 2015, 111(2): 213-228. doi: 10.1109/CVPR.2012.6247895.

相關(guān)文章

施引文獻

資源附件(0)

訪問統(tǒng)計