基于定量属性的单目标视觉跟踪算法评价体系研究

康文静; 刘畅; 刘功亮

doi:10.1631/FITEE.1900245

Your Location：

Home >

Browse articles >

基于定量属性的单目标视觉跟踪算法评价体系研究

常规文章 | Updated：2022-05-19

- 基于定量属性的单目标视觉跟踪算法评价体系研究
  Enhanced Publication
- A quantitative attribute-based benchmark methodology for single-target visual tracking
- 信息与电子工程前沿（英文） 2020年21卷第3期页码：405-421
- Affiliations：
  
  School of Information Science and Engineering, Harbin Institute of Technology, Weihai 264209, China
  School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
- Author bio：
  
  [ "Wen-jing KANG, E-mail: kwjqq@hit.edu.cn" ]
  [ "Chang LIU, E-mail: liuc0051@e.ntu.edu.sg" ]
  Gong-liang LIU, E-mail: liugl@hit.edu.cn
- Funds：
  
  Project supported by the National Natural Science Foundation of China (No. 61501139) and the Natural Scientific Research Innovation Foundation in Harbin Institute of Technology, Weihai (No. 2019KYCXJJYB06)
- DOI：10.1631/FITEE.1900245
  中图分类号： TP723
- 纸质出版日期：2020-03，
  
  收稿日期：2019-05-15，
  
  修回日期：2019-11-12，
- Accepted：
Scan QR Code
康文静, 刘畅, 刘功亮. 基于定量属性的单目标视觉跟踪算法评价体系研究[J]. 信息与电子工程前沿（英文）, 2020,21(3):405-421.

KANG WEN-JING, LIU CHANG, LIU GONG-LIANG. A quantitative attribute-based benchmark methodology for single-target visual tracking. [J]. Frontiers of information technology & electronic engineering, 2020, 21(3): 405-421.
康文静, 刘畅, 刘功亮. 基于定量属性的单目标视觉跟踪算法评价体系研究[J]. 信息与电子工程前沿（英文）, 2020,21(3):405-421. DOI： 10.1631/FITEE.1900245.

KANG WEN-JING, LIU CHANG, LIU GONG-LIANG. A quantitative attribute-based benchmark methodology for single-target visual tracking. [J]. Frontiers of information technology & electronic engineering, 2020, 21(3): 405-421. DOI： 10.1631/FITEE.1900245.

摘要

视觉跟踪是计算机视觉领域热门研究课题之一。近年来，很多先进跟踪算法和性能评价基准相继发布，并取得巨大成功。现有评价体系大多定位于衡量整体性能，无法通过针对性的详细论证评估跟踪器的优势和缺点，且很多常用评测指标缺乏令人信服的含义解释。本文从测试数据、测试方法、测试指标3方面深入分析跟踪评价体系的细节。首先，归纳整理了12个反映图像序列不同特性的帧间视觉属性，并首次定量给出其归一化公式。基于这些属性定义，提出两种新的测试方法，即基于相关性的测试和基于权重的测试，使评价体系能更直观、更清晰地评定跟踪器各方面性能。然后，将所提测试方法应用于著名的跟踪挑战赛，即Video Object Tracking (VOT) Challenge 2017。测试结果表明，在目标尺寸快速或剧烈变化时，跟踪器大多表现不佳，即使基于深度学习的先进跟踪器也未能很好解决这一问题。此外发现，中心位置差错（center location error，CLE）性能指标虽未考虑到目标尺度，在实际测试中仍对目标尺寸变化很敏感。

Abstract

In the past several years

various visual object tracking benchmarks have been proposed

and some of them have been used widely in numerous recently proposed trackers. However

most of the discussions focus on the overall performance

and cannot describe the strengths and weaknesses of the trackers in detail. Meanwhile

several benchmark measures that are often used in tests lack convincing interpretation. In this paper

12 frame-wise visual attributes that reflect different aspects of the characteristics of image sequences are collated

and a normalized quantitative formulaic definition has been given to each of them for the first time. Based on these definitions

we propose two novel test methodologies

a correlation-based test and a weight-based test

which can provide a more intuitive and easier demonstration of the trackers' performance for each aspect. Then these methods have been applied to the raw results from one of the most famous tracking challenges

the Video Object Tracking (VOT) Challenge 2017. From the tests

most trackers did not perform well when the size of the target changed rapidly or intensely

and even the advanced deep learning based trackers did not perfectly solve the problem. The scale of the targets was not considered in the calculation of the center location error; however

in a practical test

the center location error is still sensitive to the targets' changes in size.

关键词

视觉跟踪性能评价视觉属性计算机视觉

Keywords

Visual trackingPerformance evaluationVisual attributesComputer vision

references

B Babenko, , , MH Yang, , , S Belongie. . Robust object tracking with online multiple instance learning. . IEEE Trans Patt Anal Mach Intell, , 2011. . 33((8):):1619--1632. . DOI:10.1109/TPAMI.2010.226http://doi.org/10.1109/TPAMI.2010.226..

CL Bao, , , Y Wu, , , HB Ling, , , 等. . Real time robust L1 tracker using accelerated proximal gradient approach. . IEEE Conf on Computer Vision and Pattern Recognition, , 2012. . p.1830--1837. . DOI:10.1109/CVPR.2012.6247881http://doi.org/10.1109/CVPR.2012.6247881..

F Battistone, , , A Petrosino, , , V Santopietro. . Watch out: embedded video tracking with BST for unmanned aerial vehicles. . J Signal Process Syst, , 2018. . 90((6):):891--900. . DOI:10.1007/s11265-017-1279-xhttp://doi.org/10.1007/s11265-017-1279-x..

L Bertinetto, , , J Valmadre, , , S Golodetz, , , 等. . Staple: complementary learners for real-time tracking. . IEEE Conf on Computer Vision and Pattern Recognition, , 2016. . p.1401--1409. . DOI:10.1109/CVPR.2016.156http://doi.org/10.1109/CVPR.2016.156..

L Čehovin, , , M Kristan, , , A Leonardis. . An adaptive coupled-layer visual model for robust visual tracking. . IEEE Int Conf on Computer Vision, , 2011. . p.1363--1370. . DOI:10.1109/ICCV.2011.6126390http://doi.org/10.1109/ICCV.2011.6126390..

L Čehovin, , , A Leonardis, , , M Kristan. . Visual object tracking performance measures revisited. . IEEE Trans Image Process, , 2016a. . 25((3):):1261--1274. . DOI:10.1109/TIP.2016.2520370http://doi.org/10.1109/TIP.2016.2520370..

L Čehovin, , , A Leonardis, , , M Kristan. . Robust visual tracking using template anchors. . IEEE Winter Conf on Applications of Computer Vision, , 2016b. . p.1--8. . DOI:10.1109/WACV.2016.7477570http://doi.org/10.1109/WACV.2016.7477570..

K Chen, , , WB Tao. . Convolutional regression for visual tracking. . IEEE Trans Image Process, , 2018. . 27((7):):3611--3620. . DOI:10.1109/TIP.2018.2819362http://doi.org/10.1109/TIP.2018.2819362..

R Collins, , , XH Zhou, , , SK Teh. . An open source tracking testbed and evaluation web site. . Proc IEEE Int Workshop on Performance Evaluation of Tracking and Surveillance, , 2005. . p.17--24. . ..

N Dalal, , , B Triggs. . Histograms of oriented gradients for human detection. . IEEE Conf on Computer Vision and Pattern Recognition, , 2005. . p.886--893. . DOI:10.1109/CVPR.2005.177http://doi.org/10.1109/CVPR.2005.177..

M Danelljan, , , G Häger, , , F Khan, , , 等. . Accurate scale estimation for robust visual tracking. . Proc British Machine Vision Conf, , 2014. . p.1--11. . DOI:10.5244/C.28.65http://doi.org/10.5244/C.28.65..

M Danelljan, , , G Häger, , , FS Khan, , , 等. . Convolutional features for correlation filter based visual tracking. . Proc IEEE Int Conf on Computer Vision Workshops, , 2015a. . p.621--629. . DOI:10.1109/ICCVW.2015.84http://doi.org/10.1109/ICCVW.2015.84..

M Danelljan, , , G Häger, , , FS Khan, , , 等. . Learning spatially regularized correlation filters for visual tracking. . IEEE Int Conf on Computer Vision, , 2015b. . p.4310--4318. . DOI:10.1109/ICCV.2015.490http://doi.org/10.1109/ICCV.2015.490..

M Danelljan, , , A Robinson, , , FS Khan, , , 等. . Beyond correlation filters: learning continuous convolution operators for visual tracking. . 14th European Conf on Computer Vision, , 2016. . p.472--488. . DOI:10.1007/978-3-319-46454-1_29http://doi.org/10.1007/978-3-319-46454-1_29..

M Danelljan, , , G Bhat, , , FS Khan, , , 等. . ECO: efficient convolution operators for tracking. . IEEE Conf on Computer Vision and Pattern Recognition, , 2017. . p.6931--6939. . DOI:10.1109/CVPR.2017.733http://doi.org/10.1109/CVPR.2017.733..

MA Fischler, , , RC Bolles. . Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. . Commun ACM, , 1981. . 24((6):):381--395. . DOI:10.1145/358669.358692http://doi.org/10.1145/358669.358692..

B Funt, , , K Barnard, , , L Martin. . Is machine colour constancy good enough?. . 5th European Conf on Computer Vision, , 1998. . p.445--459. . DOI:10.1007/BFb0055683http://doi.org/10.1007/BFb0055683..

HK Galoogahi, , , A Fagg, , , C Huang, , , 等. . Need for speed: a benchmark for higher frame rate object tracking. . IEEE Int Conf on Computer Vision, , 2017. . p.1134--1143. . DOI:10.1109/ICCV.2017.128http://doi.org/10.1109/ICCV.2017.128..

SB Gao, , , KF Yang, , , CY Li, , , 等. . Color constancy using double-opponency. . IEEE Trans Patt Anal Mach Intell, , 2015. . 37((10):):1973--1985. . DOI:10.1109/TPAMI.2015.2396053http://doi.org/10.1109/TPAMI.2015.2396053..

E Gundogdu, , , AA Alatan. . Good features to correlate for visual tracking. . IEEE Trans Image Process, , 2018. . 27((5):):2526--2540. . DOI:10.1109/TIP.2018.2806280http://doi.org/10.1109/TIP.2018.2806280..

S Hare, , , A Saffari, , , PHS Torr. . Struck: structured output tracking with kernels. . Int Conf on Computer Vision, , 2011. . p.263--270. . DOI:10.1109/ICCV.2011.6126251http://doi.org/10.1109/ICCV.2011.6126251..

S Hare, , , S Golodetz, , , A Saffari, , , 等. . Struck: structured output tracking with kernels. . IEEE Trans Patt Anal Mach Intell, , 2016. . 38((10):):2096--2109. . DOI:10.1109/TPAMI.2015.2509974http://doi.org/10.1109/TPAMI.2015.2509974..

Z He, , , Y Fan, , , J Zhuang, , , 等. . Correlation filters with weighted convolution responses. . IEEE Int Conf on Computer Vision Workshop, , 2017. . p.1992--2000. . ..

JF Henriques, , , R Caseiro, , , P Martins, , , 等. . High-speed tracking with kernelized correlation filters. . IEEE Trans Patt Anal Mach Intell, , 2015. . 37((3):):583--596. . DOI:10.1109/TPAMI.2014.2345390http://doi.org/10.1109/TPAMI.2014.2345390..

B Karasulu, , , S Korukoglu. . A software for performance evaluation and comparison of people detection and tracking methods in video processing. . Multim Tools Appl, , 2011. . 55((3):):677--723. . DOI:10.1007/s11042-010-0591-2http://doi.org/10.1007/s11042-010-0591-2..

M Kristan, , , J Perš, , , M Perše, , , 等. . A Bayes-spectralentropy-based measure of camera focus using a discrete cosine transform. . Patt Recogn Lett, , 2006. . 27((13):):1431--1439. . DOI:10.1016/j.patrec.2006.01.016http://doi.org/10.1016/j.patrec.2006.01.016..

M Kristan, , , R Pflugfelder, , , A Leonardis, , , 等. . The Visual Object Tracking VOT2013 Challenge results. . IEEE Int Conf on Computer Vision Workshops, , 2013. . p.98--111. . DOI:10.1109/ICCVW.2013.20http://doi.org/10.1109/ICCVW.2013.20..

M Kristan, , , R Pflugfelder, , , A Leonardis, , , 等. . The Visual Object Tracking VOT2014 Challenge results. . European Conf on Computer Vision, , 2015a. . p.191--217. . DOI:10.1007/978-3-319-16181-5_14http://doi.org/10.1007/978-3-319-16181-5_14..

M Kristan, , , J Matas, , , A Leonardis, , , 等. . The Visual Object Tracking VOT2015 Challenge results. . IEEE Int Conf on Computer Vision Workshop, , 2015b. . p.564--586. . DOI:10.1109/ICCVW.2015.79http://doi.org/10.1109/ICCVW.2015.79..

M Kristan, , , J Matas, , , A Leonardis, , , 等. . A novel performance evaluation methodology for single-target trackers. . IEEE Trans Patt Anal Mach Intell, , 2016a. . 38((11):):2137--2155. . DOI:10.1109/TPAMI.2016.2516982http://doi.org/10.1109/TPAMI.2016.2516982..

M Kristan, , , A Leonardis, , , J Matas, , , 等. . The Visual Object Tracking VOT2016 Challenge results. . European Conf on Computer Vision, , 2016b. . p.777--823. . DOI:10.1007/978-3-319-48881-3_54http://doi.org/10.1007/978-3-319-48881-3_54..

M Kristan, , , A Leonardis, , , J Matas, , , 等. . The Visual Object Tracking VOT2017 Challenge results. . IEEE Int Conf on Computer Vision Workshops, , 2017. . p.1949--1972. . DOI:10.1109/ICCVW.2017.230http://doi.org/10.1109/ICCVW.2017.230..

J Kwon, , , KM Lee. . Tracking of abrupt motion using Wang-Landau Monte Carlo estimation. . 10th European Conf on Computer Vision, , 2008. . p.387--400. . DOI:10.1007/978-3-540-88682-2_30http://doi.org/10.1007/978-3-540-88682-2_30..

AN Li, , , M Lin, , , Y Wu, , , 等. . NUS-PRO: a new visual tracking challenge. . IEEE Trans Patt Anal Mach Intell, , 2016. . 38((2):):335--349. . DOI:10.1109/TPAMI.2015.2417577http://doi.org/10.1109/TPAMI.2015.2417577..

B Li, , , W Wu, , , Q Wang, , , 等. . SiamRPN++: evolution of Siamese visual tracking with very deep networks. . Proc IEEE Conf on Computer Vision and Pattern Recognition, , 2019. . p.4282--4291. . ..

SY Li, , , DY Yeung. . Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models. . Proc 31st AAAI Conf on Artificial Intelligence, , 2017. . p.4140--4146. . ..

DG Lowe. . Object recognition from local scale-invariant features. . Proc 7th IEEE Int Conf on Computer Vision, , 1999. . p.150--1157. . DOI:10.1109/ICCV.1999.790410http://doi.org/10.1109/ICCV.1999.790410..

A Lukežič, , , T Vojír, , , LC Zajc, , , 等. . Discriminative correlation filter with channel and spatial reliability. . IEEE Conf on Computer Vision and Pattern Recognition, , 2017. . p.4847--4856. . DOI:10.1109/CVPR.2017.515http://doi.org/10.1109/CVPR.2017.515..

A Lukežič, , , LČ Zajc, , , M Kristan. . Deformable parts correlation filters for robust visual tracking. . IEEE Trans Cybern, , 2018. . 48((6):):1849--1861. . DOI:10.1109/TCYB.2017.2716101http://doi.org/10.1109/TCYB.2017.2716101..

R Mathew, , , SS Hiremath. . Control of velocityconstrained stepper motor-driven Hilare robot for waypoint navigation. . Engineering, , 2018. . 4((4):):491--499. . DOI:10.1016/j.eng.2018.07.013http://doi.org/10.1016/j.eng.2018.07.013..

B Mocanu, , , R Tapu, , , T Zaharia. . Single object tracking using offline trained deep regression networks. . 7th Int Conf on Image Processing Theory, Tools and Applications, , 2017. . p.1--6. . DOI:10.1109/IPTA.2017.8310091http://doi.org/10.1109/IPTA.2017.8310091..

G Nebehay, , , R Pflugfelder. . Clustering of static-adaptive correspondences for deformable object tracking. . IEEE Conf on Computer Vision and Pattern Recognition, , 2015. . p.2784--2791. . DOI:10.1109/CVPR.2015.7298895http://doi.org/10.1109/CVPR.2015.7298895..

DA Ross, , , J Lim, , , RS Lin, , , 等. . Incremental learning for robust visual tracking. . Int J Comput Vis, , 2008. . 77((1-3):):125--141. . DOI:10.1007/s11263-007-0075-7http://doi.org/10.1007/s11263-007-0075-7..

P Senna, , , IN Drummond, , , GS Bastos. . Real-time ensemble-based tracker with Kalman filter. . 30th SIBGRAPI Conf on Graphics, Patterns and Images, , 2017. . p.338--344. . DOI:10.1109/SIBGRAPI.2017.51http://doi.org/10.1109/SIBGRAPI.2017.51..

AWM Smeulders, , , DM Chu, , , R Cucchiara, , , 等. . Visual tracking: an experimental survey. . IEEE Trans Patt Anal Mach Intell, , 2014. . 36((7):):1442--1468. . DOI:10.1109/TPAMI.2013.230http://doi.org/10.1109/TPAMI.2013.230..

C Sun, , , D Wang, , , HC Lu, , , 等. . Learning spatial-aware regressions for visual tracking. . IEEE/CVF Conf on Computer Vision and Pattern Recognition, , 2018. . p.8962--8970. . DOI:10.1109/CVPR.2018.00934http://doi.org/10.1109/CVPR.2018.00934..

A Tran, , , A Manzanera. . Mixing Hough and color histogram models for accurate real-time object tracking. . 17th Int Conf on Computer Analysis of Images and Patterns, , 2017. . p.43--54. . DOI:10.1007/978-3-319-64689-3_4http://doi.org/10.1007/978-3-319-64689-3_4..

J Valmadre, , , L Bertinetto, , , J Henriques, , , 等. . End-to-end representation learning for correlation filter based tracking. . IEEE Conf on Computer Vision and Pattern Recognition, , 2017. . p.5000--5008. . DOI:10.1109/CVPR.2017.531http://doi.org/10.1109/CVPR.2017.531..

T Vojíř, , , J Matas. . The enhanced flock of trackers. . In: Cipolla R, Battiato S, Farinella GM (Eds.), Registration and Recognition in Images and Videos. Springer, Berlin, , 2014. . p.113--136. . DOI:10.1007/978-3-642-44907-9_6http://doi.org/10.1007/978-3-642-44907-9_6..

T Vojíř, , , J Noskova, , , J Matas. . Robust scale-adaptive mean-shift for tracking. . Patt Recogn Lett, , 2014. . 49250--258. . DOI:10.1016/j.patrec.2014.03.025http://doi.org/10.1016/j.patrec.2014.03.025..

Y Wu, , , J Lim, , , MH Yang. . Online object tracking: a benchmark. . IEEE Conf on Computer Vision and Pattern Recognition, , 2013. . p.2411--2418. . DOI:10.1109/CVPR.2013.312http://doi.org/10.1109/CVPR.2013.312..

Y Wu, , , J Lim, , , MH Yang. . Object tracking benchmark. . IEEE Trans Patt Anal Mach Intell, , 2015. . 37((9):):1834--1848. . DOI:10.1109/TPAMI.2014.2388226http://doi.org/10.1109/TPAMI.2014.2388226..

LX Yang, , , RS Liu, , , D Zhang, , , 等. . Deep locationspecific tracking. . Proc 25th ACM Int Conf on Multimedia, , 2017. . p.1309--1317. . DOI:10.1145/3123266.3123381http://doi.org/10.1145/3123266.3123381..

A Yilmaz, , , O Javed, , , M Shah. . Object tracking: a survey. . ACM Comput Surv, , 2006. . 38((4):):13DOI:10.1145/1177352.1177355http://doi.org/10.1145/1177352.1177355..

DP Young, , , JM Ferryman. . PETS metrics: on-line performance evaluation service. . IEEE Int Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, , 2005. . p.317--324. . DOI:10.1109/VSPETS.2005.1570931http://doi.org/10.1109/VSPETS.2005.1570931..

JC Zhang, , , YX Peng. . Object-aware aggregation with bidirectional temporal graph for video captioning. . Proc IEEE Conf on Computer Vision and Pattern Recognition, , 2019. . p.8327--8336. . ..

JM Zhang, , , SG Ma, , , S Sclaroff. . MEEM: robust tracking via multiple experts using entropy minimization. . 13th European Conf on Computer Vision, , 2014. . p.188--203. . DOI:10.1007/978-3-319-10599-4_13http://doi.org/10.1007/978-3-319-10599-4_13..

RF Zhang, , , T Deng, , , GH Wang, , , 等. . A robust object tracking framework based on a reliable point assignment algorithm. . Front Inform Technol Electron Eng, , 2017. . 18((4):):545--558. . DOI:10.1631/FITEE.1601464http://doi.org/10.1631/FITEE.1601464..

TZ Zhang, , , S Liu, , , CS Xu, , , 等. . Correlation particle filter for visual tracking. . IEEE Trans Image Process, , 2018. . 27((6):):2676--2687. . DOI:10.1109/TIP.2017.2781304http://doi.org/10.1109/TIP.2017.2781304..

WM Zuo, , , XH Wu, , , L Lin, , , 等. . Learning support correlation filters for visual tracking. . IEEE Trans Patt Anal Mach Intell, , 2019. . 41((5):):1158--1172. . DOI:10.1109/TPAMI.2018.2829180http://doi.org/10.1109/TPAMI.2018.2829180..

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Light field imaging for computer vision: a survey

Auxiliary diagnostic system for ADHD in children based on AI technology

Exploiting a depth context model in visual tracking with correlation filter

Performance analysis of visual markers for indoor navigation systems#

Inertial measurement unit-camera calibration based on incomplete inertial sensor information