In defense of color-based model-free tracking

By Horst Possegger, Thomas Mauthner, Horst Bischof. 2015

367 citations recorded by the source corpus.

In this paper, we address the problem of model-free online object tracking based on color representations. According to the findings of recent benchmark evaluations, such trackers often tend to drift towards regions which exhibit a similar appearance compared to the object of interest. To overcome this limitation, we propose an efficient discriminative object model which allows us to identify potentially distracting regions in advance. Furthermore, we exploit this knowledge to adapt the object representation beforehand so that distractors are suppressed and the risk of drifting is significantly reduced. We evaluate our approach on recent online tracking benchmark datasets demonstrating state-of-the-art results. In particular, our approach performs favorably both in terms of accuracy and robustness compared to recent tracking algorithms. Moreover, the proposed approach allows for an efficient implementation to enable online object tracking in real-time.

Subfields: Computer Vision and Pattern Recognition, Global and Planetary Change

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Global and Planetary Change

Citations in the corpus

Learning feed-forward one-shot learners (2016, methodology): “An elementary tracker based on learnet compares favourably against recent tracking systems, which make use of different features and online model update strategies: DAT [17], DSST [2], MEEM [22], MUSTer [6] and SO-DLT [21].”
Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey (2016, methodology): “com/matlabcentral/fileexchange/35520-meanshift-video-tracking 4Matlab provided function 5Matlab code provided by the authors of [112]) TABLE XI”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, methodology): “We evaluate our MCPF algorithm with 29 trackers in [36] and other 22 state-of-the-art trackers using the source codes including MEEM [39], TGPR [12], KCF [16], RPT [21], MUSTer [18], DSST [9], LCT [26], CF2 [25], SCF [23], HDT [29], Staple [2], SRDCF [10], DeepSRDCF [7], SRDCFdecon [8], CNN-SVM [17]”
Staple: Complementary Learners for Real-Time Tracking (2015, methodology): “…colour histograms were used in many early approaches to object tracking [32, 31], they have only recently been demonstrated to be competitive in modern benchmarks in the Distractor-Aware Tracker (DAT) [33], which uses adaptive thresholding and explicit suppression of regions with similar colours.”
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking (2016, methodology): “We perform a comprehensive comparison with 17 recent state-of-the-art trackers: EDFT [7], LSHT [12], DFT [24], ASLA [15], TLD [16], Struck [11], CFLB [8], ACT [6], TGPR [9], KCF [13], DSST [2], SAMF [19], DAT [23], MEEM [29], LCT [22], HCF [21] and SRDCF [5].”
SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (2019, background): “Tracking researchers devote to design faster and more accurate trackers from different aspects like feature extraction [16, 17], template updating [35, 12], classifier design [40] and bounding box regression [4].”
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (2016, methodology): “We validate our Continuous Convolution Operator Tracker (C-COT) in a comprehensive comparison with 20 state-of-the-art methods: ASLA [25], TLD [26], Struck [21], LSHT [22], EDFT [14], DFT [41], CFLB [18], ACT [13], TGPR [19], KCF [24], DSST [9], SAMF [31], MEEM [47], DAT [40], LCT [36], HCF [35], St”
VITAL: VIsual Tracking via Adversarial Learning (2018, methodology): “We compare VITAL with 29 trackers from the OTB-2013 benchmark [59] and other 28 stateof-the-art trackers including DSST [10], KCF [22], TGPR [16], MEEM [63], RPT [34], LCT [37], MUSTer [25], HCFT [36], FCNT [57], SRDCF [12], CNN-SVM [24], DeepSRDCF [11], DAT [41], Staple [3], SRDCFdecon [13], CCOT [”
Distractor-aware Siamese Networks for Visual Object Tracking (2018, background): “Possegger et.al [26] propose a distractor-aware model term to suppress visually distracting regions, while the color histograms features used in their framework are less robust than the deep features.”
The Visual Object Tracking VOT2015 Challenge Results (2015, methodology): “Four complementary trackers were chosen to be used in ensemble, namely, DAT [57], DSST [11], Baseline [72] and ASMS [69].”
Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models (2017, methodology): “…based approaches: KCF (Henriques et al. 2015), DSST (Danelljan et al. 2014), SRDCF (Danelljan et al. 2015) • a color-based discriminative tracker: DAT (Possegger, Mauthner, and Bischof 2015) • a competitive particle filter based approach: HOGLR (Wang et al. 2015b) • an expert ensemble based…”
Fast Online Object Tracking and Segmentation: A Unifying Approach (2018, background): “last row of Figure 4), also known as distractors [52, 71].”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, background): “at The Tracker DAT [68] is an appearance-based tracking-by-detection approach.”
ECO: Efficient Convolution Operators for Tracking (2016, methodology): “OTB2015 Dataset: We compare our tracker with 20 stateof-the-art methods: TLD [22], Struck [19], CFLB [16], ACT [13], TGPR [17], KCF [20], DSST [7], SAMF [25], MEEM [38], DAT [33], LCT [28], HCF [27], SRDCF [9], SRDCFad [10], DeepSRDCF [8], Staple [1], MDNet [31], SiameseFC [2], TCNN [30] and C-COT [”
The Visual Object Tracking VOT2016 Challenge Results (2016, methodology): “The reader is referred to [45] for details.”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “works on correlation filters based tracking: CSK [55], KCF [56] and their variants ColorCSK [62], SAMF [58], DSST [48], Staple [45], SRDCF [51], SRDCFdecon [52], CCOT [53], BACF [69], STRCF [81], DeepSTRCF [81], ECO [47], and LDES [82] in our evaluation.”
Understanding and Diagnosing Visual Tracking Systems (2015, methodology): “Some recent methods [10, 25] demonstrated notable performance with carefully designed color features.”
Multi-cue Correlation Filters for Robust Visual Tracking (2018, methodology): “Besides, inspired by [30, 5], color information is applied to the training sample in a simple way to enhance its spatial reliability: X ′ = X C, where X represents the data matrix and C is the color mask obtained by computing the histogram-based per-pixel score map [37, 2] of ROI.”