基于自適應(yīng)背景選擇和多檢測區(qū)域的相關(guān)濾波算法

蒲磊; 馮新喜; 侯志強(qiáng); 余旺盛

doi:10.11999/JEIT190931

基于自適應(yīng)背景選擇和多檢測區(qū)域的相關(guān)濾波算法

doi: 10.11999/JEIT190931

1.
空軍工程大學(xué)研究生院西安 710077
2.
空軍工程大學(xué)信息與導(dǎo)航學(xué)院西安 710077
3.
西安郵電大學(xué)計(jì)算機(jī)學(xué)院西安 710121

基金項(xiàng)目: 國家自然科學(xué)基金(61571458, 61703423)

詳細(xì)信息

作者簡介:
蒲磊：男，1991年生，博士生，研究方向?yàn)橛?jì)算機(jī)視覺、目標(biāo)跟蹤

馮新喜：男，1964年生，教授，研究方向?yàn)樾畔⑷诤?、模式識(shí)別

侯志強(qiáng)：男，1973年生，教授，研究方向?yàn)閳D像處理、計(jì)算機(jī)視覺

余旺盛：男，1985年生，講師，研究方向?yàn)閳D像處理、模式識(shí)別

通訊作者:
蒲磊　warmstoner@163.com

中圖分類號: TN911.73; TP391.4
計(jì)量
- 文章訪問數(shù): 2282
- HTML全文瀏覽量: 755
- PDF下載量: 127
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-11-20
- 修回日期: 2020-05-26
- 網(wǎng)絡(luò)出版日期: 2020-06-01
- 刊出日期: 2020-12-08

Correlation Filter Algorithm Based on Adaptive Context Selection and Multiple Detection Areas

1.
Graduate College, Air Force Engineering University, Xi’an 710077, China
2.
Institute of Information and Navigation, Air Force Engineering University, Xi’an 710077, China
3.
School of Computer Science and Technology, Xian University of Posts and Telecommunications, Xi’an 710121, China

Funds: The National Natural Science Foundation of China (61571458, 61703423)

摘要

摘要: 為了進(jìn)一步提高相關(guān)濾波算法的判別力和對快速運(yùn)動(dòng)、遮擋等復(fù)雜場景的應(yīng)對能力，該文提出一種基于自適應(yīng)背景選擇和多檢測區(qū)域的跟蹤框架。首先對檢測后的響應(yīng)圖進(jìn)行峰值分析，當(dāng)響應(yīng)為單峰的時(shí)候，提取目標(biāo)上下左右的4塊區(qū)域作為負(fù)樣本對模型進(jìn)行訓(xùn)練，當(dāng)響應(yīng)為多峰的時(shí)候，采用峰值提取技術(shù)和閾值選擇方法提取較大幾個(gè)峰值區(qū)域作為負(fù)樣本。為了進(jìn)一步提高算法對遮擋的應(yīng)對能力，該文提出了一種多檢測區(qū)域的搜索策略。將該框架和傳統(tǒng)的相關(guān)濾波算法進(jìn)行結(jié)合，實(shí)驗(yàn)結(jié)果表明，相對于基準(zhǔn)算法，該算法在精度上提高了6.9%，在成功率上提高了6.3%。
- 視覺跟蹤 /
- 相關(guān)濾波 /
- 遮擋 /
- 背景選擇
Abstract: In order to improve further the discrimination ability of the correlation filtering algorithm and the ability to deal with fast motion and occlusion, a tracking framework based on adaptive context selection and multiple detection areas is proposed. Firstly, the peak value of the detected response map is analyzed. When the response is single peak, four areas surrounding the target are extracted as negative samples to train the model. When the response is multi-peak, the peak value extraction technology and threshold selection are used to extract several larger peak areas as negative samples. In order to improve further the ability to deal with occlusion, a multi detection area search strategy is proposed. Combining the framework with the traditional correlation filter algorithm, the experimental results show that the proposed algorithm improves the accuracy by 6.9% and the success rate by 6.3%.
- Visual tracking /
- Correlation filter /
- Occlusion /
- Context selection

HTML全文

圖 1 基于響應(yīng)圖峰值提取的自適應(yīng)背景選擇策略

下載: 全尺寸圖片幻燈片

圖 2 多檢測區(qū)域搜索策略

下載: 全尺寸圖片幻燈片

圖 3 OTB100測試結(jié)果的精度曲線和成功率曲線

下載: 全尺寸圖片幻燈片

圖 4 定性分析

下載: 全尺寸圖片幻燈片

表 1 基于自適應(yīng)背景選擇和多檢測區(qū)域的相關(guān)濾波算法

　輸入：圖像序列I₁, I₂, ···, I_n，目標(biāo)初始位置p₀=(x₀, y₀)。

　輸出：每幀圖像的跟蹤結(jié)果p_t=(x_t, y_t)。

　對于t=1, 2, ···, n, do：

　　(1) 定位目標(biāo)中心位置

　　(a) 利用前一幀目標(biāo)位置p_t_-1確定第t幀ROI區(qū)域，并提取
　　　 HOG特征；

　　(b) 利用式(3)在多個(gè)檢測區(qū)域進(jìn)行計(jì)算，獲得多個(gè)響應(yīng)圖；

　　(2) 模型更新

　　(a) 對得到的響應(yīng)圖計(jì)算峰值個(gè)數(shù)；

　　(b) 當(dāng)為單峰時(shí)，提取上下左右4個(gè)背景塊進(jìn)行模型更新；

　　(d) 采用式(7)對模型進(jìn)行更新。

　結(jié)束

下載: 導(dǎo)出CSV

表 2 算法跟蹤速度對比

	本文算法	DCF_CA	DCF	DSST	TLD	MOSSE_CA
成功率	0.586	0.566	0.523	0.552	0.448	0.488
跟蹤精度	0.808	0.776	0.739	0.731	0.633	0.642
跟蹤速度(FPS)	53.5	82.3	333.0	28.3	33.4	115.0

下載: 導(dǎo)出CSV

參考文獻(xiàn)(28)

SMEULDERS A W M, CHU D M, CUCCHIARA R, et al. Visual tracking: An experimental survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1442–1468. doi: 10.1109/TPAMI.2013.230

HE Anfeng, LUO Chong, TIAN Xinmei, et al. A twofold Siamese network for real-time object tracking[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 4834–4843. doi: 10.1109/CVPR.2018.00508.

LI Bo, YAN Junjie, WU Wei, et al. . High performance visual tracking with Siamese region proposal network[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 8971–8980. doi: 10.1109/CVPR.2018.00935.

LI Peixia, CHEN Boyu, OUYANG Wanli, et al. GradNet: Gradient-guided network for visual object tracking[C]. 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea, 2019: 6162–6171. doi: 10.1109/ICCV.2019.00626.

BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 2544–2550. doi: 10.1109/CVPR.2010.5539960.

HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]. 12th European Conference on Computer Vision on Computer Vision, Florence, Italy, 2012: 702–715. doi: 10.1007/978-3-642-33765-9_50.

HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583–596. doi: 10.1109/tpami.2014.2345390

DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive color attributes for real-time visual tracking[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 1090–1097. doi: 10.1109/CVPR.2014.143.

DANELLJAN M, H?GER G, KHAN F S, et al. Convolutional features for correlation filter based visual tracking[C]. 2015 IEEE International Conference on Computer Vision Workshop, Santiago, Chile, 2015: 58–66. doi: 10.1109/ICCVW.2015.84.

QI Yuankai, ZHANG Shengping, QIN Lei, et al. Hedged deep tracking[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 4303–4311. doi: 10.1109/CVPR.2016.466.

MA Chao, HUANG Jiabin, YANG Xiaokang, et al. Hierarchical convolutional features for visual tracking[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3074–3082. doi: 10.1109/ICCV.2015.352.

WANG Haijun, ZHANG Shengyan, GE Hongjuan, et al. Robust visual tracking via semiadaptive weighted convolutional features[J]. IEEE Signal Processing Letters, 2018, 25(5): 670–674. doi: 10.1109/LSP.2018.2819622

QI Yuankai, ZHANG Shengping, QIN Lei, et al. Hedging deep features for visual tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(5): 1116–1130. doi: 10.1109/TPAMI.2018.2828817

ZHANG Tianzhu, XU Changsheng, and YANG M H. Learning multi-task correlation particle filters for visual tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(2): 365–378. doi: 10.1109/TPAMI.2018.2797062

DANELLJAN M, H?GER G, KHAN F S, et al. Learning spatially regularized correlation filters for visual tracking[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 4310–4318. doi: 10.1109/ICCV.2015.490.

蒲磊, 馮新喜, 侯志強(qiáng), 等. 基于空間可靠性約束的魯棒視覺跟蹤算法[J]. 電子與信息學(xué)報(bào), 2019, 41(7): 1650–1657. doi: 10.11999/JEIT180780

PU Lei, FENG Xinxi, HOU Zhiqiang, et al. Robust visual tracking based on spatial reliability constraint[J]. Journal of Electronics &Information Technology, 2019, 41(7): 1650–1657. doi: 10.11999/JEIT180780

GALOOGAHI H K, SIM T, LUCEY S. Correlation filters with limited boundaries[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 4630–4638. doi: 10.1109/CVPR.2015.7299094.

PU Lei, FENG Xinxi, and HOU Zhiqiang. Learning temporal regularized correlation filter tracker with spatial reliable constraint[J]. IEEE Access, 2019, 7: 81441–81450. doi: 10.1109/ACCESS.2019.2922416

LI Feng, TIAN Cheng, ZUO Wangmeng, et al. Learning spatial-temporal regularized correlation filters for visual tracking[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 4904–4913. doi: 10.1109/CVPR.2018.00515.

侯志強(qiáng), 王帥, 廖秀峰, 等. 基于樣本質(zhì)量估計(jì)的空間正則化自適應(yīng)相關(guān)濾波視覺跟蹤[J]. 電子與信息學(xué)報(bào), 2019, 41(8): 1983–1991. doi: 10.11999/JEIT180921

HOU Zhiqiang, WANG Shuai, LIAO Xiufeng, et al. Adaptive regularized correlation filters for visual tracking based on sample quality estimation[J]. Journal of Electronics &Information Technology, 2019, 41(8): 1983–1991. doi: 10.11999/JEIT180921

MUELLER M, SMITH N, GHANEM B, et al. Context-aware correlation filter tracking[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 1396–1404. doi: 10.1109/CVPR.2017.152.

WANG Mengmeng, LIU Yong, HUANG Zeyi, et al. Large margin object tracking with circulant feature maps[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 4021–4029. doi: 10.1109/CVPR.2017.510.

WU Yi, LIM J, and YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834–1848. doi: 10.1109/TPAMI.2014.2388226

DANELLJAN M, H?GER G, KHAN F S, et al. Accurate scale estimation for robust visual tracking[C]. British Machine Vision Conference 2014, Nottingham, UK, 2014: 65.1–65.11. doi: 10.5244/C.28.65.

HARE S, GOLODETZ S, SAFFARI A, et al. Struck: Structured output tracking with kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10): 2096–2109. doi: 10.1109/TPAMI.2015.2509974

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

ZHANG Tianzhu, GHANEM B, LIU Si, et al. Robust visual tracking via multi-task sparse learning[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 2042–2049. doi: 10.1109/CVPR.2012.6247908.

BABENKO B, YANG M H, and BELONGIE S. Visual tracking with online multiple instance learning[C]. 2019 IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 983–990. doi: 10.1109/CVPR.2009.5206737.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)