Proposal-Based Visual Tracking Using Spatial Cascaded Transformed Region Proposal Network
1
Faculty of Space, Xi’an Institute of Optics and Precision Mechanics of CAS, Xi’an 710119, China
2
School of Astronautics, Northwestern Polytechnical Universty, Xi’an 710072, China
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(17), 4810; https://doi.org/10.3390/s20174810
Received: 20 July 2020
/
Revised: 13 August 2020
/
Accepted: 14 August 2020
/
Published: 26 August 2020
(This article belongs to the Section Sensor Networks)
Region proposal network (RPN) based trackers employ the classification and regression block to generate the proposals, the proposal that contains the highest similarity score is formulated to be the groundtruth candidate of next frame. However, region proposal network based trackers cannot make the best of the features from different convolutional layers, and the original loss function cannot alleviate the data imbalance issue of the training procedure. We propose the Spatial Cascaded Transformed RPN to combine the RPN and STN (spatial transformer network) together, in order to successfully obtain the proposals of high quality, which can simultaneously improves the robustness. The STN can transfer the spatial transformed features though different stages, which extends the spatial representation capability of such networks handling complex scenarios such as scale variation and affine transformation. We break the restriction though an easy samples penalization loss (shrinkage loss) instead of smooth L1 function. Moreover, we perform the multi-cue proposals re-ranking to guarantee the accuracy of the proposed tracker. We extensively prove the effectiveness of our proposed method on the ablation studies of the tracking datasets, which include OTB-2015 (Object Tracking Benchmark 2015), VOT-2018 (Visual Object Tracking 2018), LaSOT (Large Scale Single Object Tracking), TrackingNet (A Large-Scale Dataset and Benchmark for Object Tracking in the Wild) and UAV123 (UAV Tracking Dataset).
View Full-Text
Keywords:
visual tracking; spatial cascaded networks; shrinkage loss; multi-cue proposals re-ranking; region proposals networks
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Zhang, X.; Luo, S.; Fan, X. Proposal-Based Visual Tracking Using Spatial Cascaded Transformed Region Proposal Network. Sensors 2020, 20, 4810. https://doi.org/10.3390/s20174810
AMA Style
Zhang X, Luo S, Fan X. Proposal-Based Visual Tracking Using Spatial Cascaded Transformed Region Proposal Network. Sensors. 2020; 20(17):4810. https://doi.org/10.3390/s20174810
Chicago/Turabian StyleZhang, Ximing, Shujuan Luo, and Xuewu Fan. 2020. "Proposal-Based Visual Tracking Using Spatial Cascaded Transformed Region Proposal Network" Sensors 20, no. 17: 4810. https://doi.org/10.3390/s20174810
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
