局部感知下的稀疏優(yōu)化目標(biāo)跟蹤方法
doi: 10.11999/JEIT170473
-
1.
(遼寧工程技術(shù)大學(xué)電子與信息工程學(xué)院 葫蘆島 125105)
-
2.
(遼寧工程技術(shù)大學(xué)軟件學(xué)院 葫蘆島 125105)
-
3.
(遼寧工程技術(shù)大學(xué)工商管理學(xué)院 葫蘆島 125105)
國家自然科學(xué)基金(61172144),遼寧省科技攻關(guān)計(jì)劃項(xiàng)目(2012216026)
Object Tracking Method Based on Sparse Optimization of Local Sensing
-
1.
(School of Electronic and Information Engineering, Liaoning Technical University, Huludao 125105, China)
-
2.
(School of Software, Liaoning Technical University, Huludao 125105,China)
-
3.
(School of Business and Management, Liaoning Technical University, Huludao 125105, China)
The National Natural Science Foundation of China (61172144), The Science and Technology Foundation of Liaoning Province (2012216026)
-
摘要: 針對傳統(tǒng)稀疏表示跟蹤算法在復(fù)雜背景中易出現(xiàn)跟蹤漂移問題,該文提出一種局部感知下的稀疏優(yōu)化目標(biāo)跟蹤方法。首先,將首幀確定的目標(biāo)區(qū)域進(jìn)行非重疊均勻分割,并利用目標(biāo)的全局特征和局部特征聯(lián)合建模。然后,提出一種局部感知校驗(yàn)方法約束稀疏優(yōu)化匹配過程,從而確定最優(yōu)匹配樣本。最后,在模板更新中提出一種決策方法對遮擋進(jìn)行檢測,并針對不同遮擋情況采取相應(yīng)的更新策略,使得更新后的模板集更加完善。實(shí)驗(yàn)在10個(gè)標(biāo)準(zhǔn)庫視頻序列中測試,并與目前較流行的目標(biāo)跟蹤算法在跟蹤效果、成功率等方面進(jìn)行比較,實(shí)驗(yàn)結(jié)果表明,提出的跟蹤方法在局部遮擋、目標(biāo)形變、復(fù)雜背景等條件下跟蹤準(zhǔn)確、適應(yīng)性強(qiáng)。
-
關(guān)鍵詞:
- 目標(biāo)跟蹤 /
- 局部感知 /
- 稀疏優(yōu)化 /
- 遮擋決策
Abstract: The problem of tracking drift is produced easily by traditional sparse representation tracking methods in complex scene. To solve this problem, a novel tracking approach based on sparse optimization of local sensing is proposed. Firstly, the object area of the first frame is divided into non-overlapping uniform segmentation, and building the template set using global features and local features. Then, a local sensing correction method for constraining sparse optimization matching process is utilized to determine the optimal matching samples. Finally, a new method of occlusion decision is used to detect occlusion, and updating strategies are adopted according to different occlusion conditions, which makes the template sets more complete in the process of template update. The experiments compare with state-of-the-art tracking algorithms on 10 tracking test sequences of benchmark library. Experiment results indicate that the proposed method possesses characteristics of accurate tracking and strong adaptability in the conditions of partial occlusion, deformation, and complex background.-
Key words:
- Object tracking /
- Local sensing /
- Sparse optimization /
- Occlusion decision
-
QI 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. 齊苑辰, 吳成東, 陳東岳, 等. 基于稀疏表達(dá)的超像素跟蹤算法[J]. 電子與信息學(xué)報(bào), 2015, 37(3): 529-535. doi: 10.11999/ JEIT140374. 李文娟,顧 紅,蘇衛(wèi)民. 基于多伯努利概率假設(shè)密度的擴(kuò)展目標(biāo)跟蹤方法[J]. 電子與信息學(xué)報(bào), 2016, 38(12): 3114-3121.doi: 10.11999/JEIT160372. LI Wenjuan, GU Hong, and SU Weimin. Extended target tracking method based on multi-bernoulli probability hypothesis density[J]. Journal of Electronics Information Technology, 2016, 38(12): 3114-3121. doi: 10.11999/JEIT 160372. 楊峰, 張婉瑩. 一種多模型貝努利粒子濾波機(jī)動(dòng)目標(biāo)跟蹤算法[J]. 電子與信息學(xué)報(bào), 2017 39(3): 634-639. doi: 10.11999 /JEIT160467. YANG Feng and ZHANG Wanying. Multiple model Bernoulli particle filter for maneuvering target tracking[J]. Journal of Electronics Information Technology, 2017, 39(3): 634-639. doi: 10.11999/JEIT160467. MEI Xue and LING Haibin. Robust visual tracking using L1 minimization[C]. IEEE 12th International Conference on Computer Vision, Florence, Italy, 2009: 1436-1443. doi: 10.1109/ICCV.2009.5459292. BAO Chenglong, WU Yi, LING Haibin, et al. Real time robust L1 tracker using accelerated proximal gradient approach[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 1830-1837. doi: 10.1109/CVPR.2012.6247881. ZHANG Tianzhu, Ghanem B, LIU Si, et al. Robust visual tracking via multi-task sparse learning[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 2042-2049. doi: 10. 1109/CVPR.2012.6247908. 張旭東, 陳仲海, 胡良梅, 等. 基于聯(lián)合模板稀疏表示的目標(biāo)跟蹤方法[J]. 控制與決策, 2015, 30(9): 1696-1700. doi: 10.13195/j.kzyjc.2014.1175. ZHANG Xudong, CHEN Zhonghai, HU Liangmei, et al. Object tracking method based on sparse representation of joint template[J]. Control and Decision, 2015, 30(9): 1696-1700. doi: 10.13195/j.kzyjc.2014.1175. ZHANG Shengping, ZHOU Huiyu, JIANG Feng, et al. Robust visual tracking using structurally random projection and weighted least squares[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2015, 25(11): 1749-1760. doi: 10.1109/TCSVT.2015.2406194. 胡秀華, 郭雷, 李暉暉, 等. 一種結(jié)合空間信息和稀疏字典優(yōu)化的目標(biāo)跟蹤算法[J]. 控制與決策, 2016, 31(12): 2170-2176. doi: 10.13195/j.kzyjc.2015.1489. HU Xiuhua, GUO Lei, LI Huihui, et al. An object tracking algorithm combining spatial information and sparse dictionary optimization[J]. Control and Decision, 2016, 31(12): 2170-2176. doi: 10.13195/j.kzyjc.2015.1489. MEI X, LING Haibin, WU Yi, et al. Efficient minimum error bounded particle resampling L1 tracker with occlusion detection[J]. IEEE Transactions on Image Processing, 2013, 22(7): 2661-2675. doi: 10.1109/TIP.2013.2255301. WU Yi, LIM Jongwoo, and YANG Minghsuan. Online object tracking: A benchmark[C]. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 2411-2418. doi: 10.1109/ CVPR.2013.312. KALAL Z, MIKOLAJCZYK K, and MATAS J. Tracking- learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422. doi: 10.1109/TPAMI.2011.239. ORON S, HILLEL A, and LEVI D. Locally orderless tracking [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 1940-1947. doi: 10.1109/CVPR.2012.6247895. KWON J and LEE K M. Visual tracking decomposition [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010: 1269-1276. doi: 10.1109/CVPR.2010.5539821. ZHONG Wei, LU Huchuan, and YANG Minghsuan. Robust object tracking via sparsity-based collaborative model[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA, 2012: 1838-1845. doi: 10.1109/CVPR.2012.6247882. ADAM A, RIVLIN E, and SHIMSHONI I. Robust fragments-based tracking using the integral histogram[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, NY, USA, 2006: 798-805. doi: 10.1109/CVPR.2006.256. -
計(jì)量
- 文章訪問數(shù): 1461
- HTML全文瀏覽量: 131
- PDF下載量: 280
- 被引次數(shù): 0