Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

By Zhenhua Feng, Xiaojun Wu, Josef Kittler. IEEE Transactions on Image Processing, 2018

364 citations recorded by the source corpus.

With efficient appearance learning models, discriminative correlation filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major issues, i.e., spatial boundary effect and temporal filter degradation. To mitigate these challenges, we propose a new DCF-based tracking method. The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold. More specifically, we apply structured spatial sparsity constraints to multi-channel filters. Consequently, the process of learning spatial filters can be approximated by the lasso regularization. To encourage temporal consistency, the filter model is restricted to lie around its historical value and updated locally to preserve the global structure in the manifold. Last, a unified optimization framework is proposed to jointly select temporal consistency preserving spatial features and learn discriminative filters with the augmented Lagrangian method. Qualitative and quantitative evaluations have been conducted on a number of well-known benchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour, UAV123, and VOT2018. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/bd5ecaea14eeb27c776b2c153b3e4716448bad4e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

The Seventh Visual Object Tracking VOT2019 Challenge Results (2019, methodology): “More-over, an adaptive spatial feature selection scheme [100] is employed to learn a robust deep tracking model.”
Siamese Box Adaptive Network for Visual Tracking (2020, background): “DRT [36] RCO [17] UPDT [3] SiamRPN [21] MFT [17] LADCF [45] ATOM [5] SiamRPN++ [20] DiMP [2] Ours”
Siam R-CNN: Visual Tracking by Re-Detection (2019, neutral): “LADCF ATOM SiamRPN++ THOR DiMP-50 Ours Ours [73] [16] [37] [5] [58] (short-t.”
NestFuse: An Infrared and Visible Image Fusion Architecture Based on Nest Connection and Spatial/Channel Attention Models (2020, methodology): “In this paper, we propose a novel image fusion architecture by developing a nest connection network and spatial/channel attention models.”
Ocean: Object-aware Anchor-free Tracking (2020, methodology): “CRPN ECO STRCF LADCF ATOM SRCNN SiamRPN++ DiMP Ocean Ocean [9] [5] [23] [45] [4] [39] [21] [2] offline online EAO ↑ 0.”
MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion (2018, methodology): “6 To evaluate the effect of our fusion method on RGBT tracking, we choose two trackers (LADCF [51], GFSDCF [50]) to”
Know Your Surroundings: Exploiting Scene Information for Object Tracking (2020, methodology): “We compare our approach with the recent state-of-the-art trackers: DRT [41], RCO [29], UPDT [4], DaSiamRPN [52], MFT [29], LADCF [48], ATOM [8], SiamRPN++ [31], and DiMP-50 [3].”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, methodology): “LADCF utilises adaptive spatial regularizer to train low-dimensional discriminative correlation filters [93].”