CoChat

Motion-Aware Correlation Filters for Online Visual Tracking

Open access

The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.

Abstract

The discriminative correlation filters-based methods struggle deal with the problem of fast motion and heavy occlusion, the problem can severely degrade the performance of trackers, ultimately leading to tracking failures. In this paper, a novel Motion-Aware Correlation Filters (MACF) framework is proposed for online visual object tracking, where a motion-aware strategy based on joint instantaneous motion estimation Kalman filters is integrated into the Discriminative Correlation Filters (DCFs). The proposed motion-aware strategy is used to predict the possible region and scale of the target in the current frame by utilizing the previous estimated 3D motion information. Obviously, this strategy can prevent model drift caused by fast motion. On the base of the predicted region and scale, the MACF detects the position and scale of the target by using the DCFs-based method in the current frame. Furthermore, an adaptive model updating strategy is proposed to address the problem of corrupted models caused by occlusions, where the learning rate is determined by the confidence of the response map. The extensive experiments on popular Object Tracking Benchmark OTB-100, OTB-50 and unmanned aerial vehicles (UAV) video have demonstrated that the proposed MACF tracker performs better than most of the state-of-the-art trackers and achieves a high real-time performance. In addition, the proposed approach can be integrated easily and flexibly into other visual tracking algorithms.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s18113937

Cites

57 of 57 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The comparison of tracking results between our MACF tracker (in red) and the standard FDSST tracker (in green) in three sequences on OTB-100 benchmark. Our tracker performs better than FDSST in the example frames which are shown from the “Board” of fast motion (top row), “Gym1” of scale change (middle row) and “Human4.2” of heavy occlusion (bottom row) videos.
Figure 1 The comparison of tracking results between our MACF tracker (in red) and the standard FDSST tracker (in green) in three sequences on OTB-100 benchmark. Our tracker performs better than FDSST in the example frames which are shown from the “Board” of fast motion (top row), “Gym1” of scale change (middle row) and “Human4.2” of heavy occlusion (bottom row) videos.CC BY · PubMed Central
Figure 2 Illustrating of instantaneous motion estimation on the test sequence of UAV.
Figure 2 Illustrating of instantaneous motion estimation on the test sequence of UAV.CC BY · PubMed Central
Figure 3 Visualization of the separate translation and scale prediction and detection on the video sequence of UAV. The previous position and scale are indicated by red bounding box, and the predicted position and scale are denoted in green, and the detected position and scale are shown with blue bounding box.
Figure 3 Visualization of the separate translation and scale prediction and detection on the video sequence of UAV. The previous position and scale are indicated by red bounding box, and the predicted position and scale are denoted in green, and the detected position and scale are shown with blue bounding box.CC BY · PubMed Central
Figure 4 The Confidence of the Squared Response Map (CSRM) in the proposed MACF comparing with the Average Peak-to-Correlation Energy (APCE) of the response map. The example frames are from the sequence “Tiger1” on OTB-100 benchmark. The higher value of the CSMR, the more confident the response map is. The value of parameter tr determine the adaptive learning rate which compute by Equation (20). From the figure, the gap of CSMR is larger than APCE between the slightly occluded, heavily occluded and none occluded target.
Figure 4 The Confidence of the Squared Response Map (CSRM) in the proposed MACF comparing with the Average Peak-to-Correlation Energy (APCE) of the response map. The example frames are from the sequence “Tiger1” on OTB-100 benchmark. The higher value of the CSMR, the more confident the response map is. The value of parameter tr determine the adaptive learning rate which compute by Equation (20). From the figure, the gap of CSMR is larger than APCE between the slightly occluded, heavily occluded and none occluded target.CC BY · PubMed Central
Figure 5 The Precision Plots (PP) of One Pass Evaluation (OPE) on OTB-50 benchmark for the top eight trackers determined by 3 different attributes: occlusion, motion blur and fast motion. Among the top eight trackers our MACF obtains the best results on all 3 attributes.
Figure 5 The Precision Plots (PP) of One Pass Evaluation (OPE) on OTB-50 benchmark for the top eight trackers determined by 3 different attributes: occlusion, motion blur and fast motion. Among the top eight trackers our MACF obtains the best results on all 3 attributes.CC BY · PubMed Central
Figure 6 The Success Plots (SP) and Precision Plots (PP) of One Pass Evaluation (OPE), Temporal Robustness Evaluation (TRE) and Spatial Robustness Evaluation (SRE) using by Overlap Threshold (OT) and Location Error Threshold (LET) comparing MACF with the state-of-the-art trackers on OTB-50 benchmark. The ranks for the top 8 trackers are reported with the Area Under the Curve (AUC) marked in brackets.
Figure 6 The Success Plots (SP) and Precision Plots (PP) of One Pass Evaluation (OPE), Temporal Robustness Evaluation (TRE) and Spatial Robustness Evaluation (SRE) using by Overlap Threshold (OT) and Location Error Threshold (LET) comparing MACF with the state-of-the-art trackers on OTB-50 benchmark. The ranks for the top 8 trackers are reported with the Area Under the Curve (AUC) marked in brackets.CC BY · PubMed Central
Figure 7 The Success Plots (SP) and Precision Plots (PP) of One Pass Evaluation (OPE), Temporal Robustness Evaluation (TRE) and Spatial Robustness Evaluation (SRE) using by Overlap Threshold (OT) and Location Error Threshold (LET) comparing the MACF with the state-of-the-art trackers on OTB-100 benchmark. In addition, the ranks for the top 8 trackers are reported with the Area Under the Curve (AUC) marked in brackets.
Figure 7 The Success Plots (SP) and Precision Plots (PP) of One Pass Evaluation (OPE), Temporal Robustness Evaluation (TRE) and Spatial Robustness Evaluation (SRE) using by Overlap Threshold (OT) and Location Error Threshold (LET) comparing the MACF with the state-of-the-art trackers on OTB-100 benchmark. In addition, the ranks for the top 8 trackers are reported with the Area Under the Curve (AUC) marked in brackets.CC BY · PubMed Central
Figure 8 The representative frames from four videos successfully tracked by the MACF (in red) compared to the top 5 trackers including FDSST (in green), LCT (in blue), DSST (in black) and KCF (in purple). From top to bottom, the sequences are “Human6”, “Human2”, “Skater1” and “tiger1” on the OTB-100 benchmark.
Figure 8 The representative frames from four videos successfully tracked by the MACF (in red) compared to the top 5 trackers including FDSST (in green), LCT (in blue), DSST (in black) and KCF (in purple). From top to bottom, the sequences are “Human6”, “Human2”, “Skater1” and “tiger1” on the OTB-100 benchmark.CC BY · PubMed Central
Figure 9 The qualitative experiment comparing the MACF (in red) with state-of-the-art trackers ECO-HC (in blue), BACF (in cyan), STC (in white), Staple (in green), SRDCF (in black), DAT (in yellow) and FDSST (in pink) on UAV video sequence with static background.
Figure 9 The qualitative experiment comparing the MACF (in red) with state-of-the-art trackers ECO-HC (in blue), BACF (in cyan), STC (in white), Staple (in green), SRDCF (in black), DAT (in yellow) and FDSST (in pink) on UAV video sequence with static background.CC BY · PubMed Central
Figure 10 Illustration of the accuracy of the predicted position and scale of the UAV. Here, the Actual position (in blue) is the actual UAV position which is calibrated by manual in the video, the Predict position (in red) is predicted by the instantaneous motion estimation method and the Correct position (in green) is filtered position by Kalman filters. (a,b) indicate respectively in-plane predicted and actual positions. (c,d) show apart 3D predicted and actual positions where the scale represents the dept motion. (e,f) display the overall results.
Figure 10 Illustration of the accuracy of the predicted position and scale of the UAV. Here, the Actual position (in blue) is the actual UAV position which is calibrated by manual in the video, the Predict position (in red) is predicted by the instantaneous motion estimation method and the Correct position (in green) is filtered position by Kalman filters. (a,b) indicate respectively in-plane predicted and actual positions. (c,d) show apart 3D predicted and actual positions where the scale represents the dept motion. (e,f) display the overall results.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

2 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 57 references

Research works printed but not linked: 3

  1. Kristan, M., Pflugfelder, R., Leonardis, A., Matas, J., Porikli, F., Cehovin, L., Nebehay, G., Fernandez, G., Vojir, T., and Gatt, A. (2014, January 6–12). The Visual Object Tracking VOT2014 Challenge Results. Proceedings of the IEEE European Conference on Computer Vision Workshops (ECCVW), Zurich, Switzerland.
  2. Kristan, M., Pflugfelder, R., Leonardis, A., Matas, J., Porikli, F., Cehovin, L., Nebehay, G., Fernandez, G., Vojir, T., and Gatt, A. (2016, January 8–10). The Visual Object Tracking VOT2016 Challenge Results. Proceedings of the IEEE European Conference on Computer Vision Workshops (ECCVW), Amsterdam, The Netherlands.
  3. Zhang, 2013, Fast Tracking via Spatio-Temporal Context Learning. Computer, Science, 1, 25

Cited by

See all 20

Metadata

Authors
Zhang, Y., Yang, Y., Zhou, W., Shi, L., & Li, D.
Affiliations
Donghua University (CN)
Corresponding author
  • Zhang, Yihong
  • Yang, Yijin
Venue
Sensors
Publisher
MDPI AG
Published
2018-11-14
Volume
18
Issue
11
Pages
3937
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2901434625
Cited by
20
References
57
Citations by year
2024: 2 · 2023: 4 · 2022: 6 · 2021: 2 · 2020: 3 · 2019: 3
FWCI
1.00
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
the Fundamental Research Funds for the Central Universities of Ministry of Education of China (18D110408)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
discriminative correlation filter, fast motion, occlusion handling, model drift, adaptive model updating

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Motion-Aware Correlation Filters for Online Visual Tracking. https://app.cochat.ai/papers/10.3390/s18113937
The paper
Zhang, Y., Yang, Y., Zhou, W., Shi, L., & Li, D. (2018). Motion-Aware Correlation Filters for Online Visual Tracking. Sensors. https://doi.org/10.3390/s18113937

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.