Learning Spatially Regularized Correlation Filters for Visual Tracking
Citations
2,016 citations
Cites methods from "Learning Spatially Regularized Corr..."
...In this experiment, we compare our method with several representive trackers, including PTAV [11], CREST[31], SRDCF [8], SINT [33], CSR-DCF [23], Siamese-FC [4], Staple [3], CFNet [35] and DSST [9]....
[...]
...Specifically, it can surpass CSRDCF++ in the 2nd place by 14% and surpass Siamese-FC in the 3nd place by 33%....
[...]
1,613 citations
1,329 citations
1,324 citations
Cites background or methods from "Learning Spatially Regularized Corr..."
...Among the compared methods, the SRDCF and its variants SRDCFdecon and DeepSRDCF 4 Detailed results are provided in the supplementary material. provide the best results, all obtaining AUC scores above 60%....
[...]
...To detect the target, we perform a multi-scale search strategy [11,31] with 5 scales and a relative scale factor 1....
[...]
...Conventional DCF formulations [11,17,24] assume the feature channels to have the same spatial resolution, i....
[...]
...We also compare with SRDCFdecon, which integrates the adaptive decontamination of the training set [12] in SRDCF, and DeepSRDCF [10] employing activations from the first convolutional layer....
[...]
...The Fourier coefficients ŵ of the penalty function w are computed as described in [11]....
[...]
1,277 citations
Cites methods from "Learning Spatially Regularized Corr..."
...In addition, we include several of the latest trackers such as MEEM [44], MUSTER [18], DSST [8] (winner VOT2014) and SRDCF [7] (winner VOT-TIR2015 and OpenCV challenge)....
[...]
...The top performing tracker on the UAV123 dataset in terms of precision and success is SRDCF [7]....
[...]
References
37,861 citations
"Learning Spatially Regularized Corr..." refers methods in this paper
...The main difference from other techniques, such as support vector machines [6], is that the DCF formulation exploits the properties of circular correlation for efficient training and detection....
[...]
31,952 citations
"Learning Spatially Regularized Corr..." refers background in this paper
...Similar to recent DCF based trackers [8, 20, 24], we also employ HOG features, using a cell size of 4×4 pixels....
[...]
...Recent work [9, 8, 10, 20, 24] have shown a notable improvement by learning multi-channel filters on multi-dimensional features, such as HOG [7] or Color-Names [31]....
[...]
...Contrary to [14], we target the problem of multi-dimensional features, such as HOG, crucial for the overall tracking performance [10, 20]....
[...]
4,994 citations
"Learning Spatially Regularized Corr..." refers background or methods in this paper
...Similar to recent DCF based trackers [8, 20, 24], we also employ HOG features, using a cell size of 4×4 pixels....
[...]
...Among the existing methods, SAMF and MEEM provide the best results with mean OP of 64.7% Overlap threshold 0 0.2 0.4 0.6 0.8 1 O v e rl a p P re c is io n [ % ] 0 20 40 60 80 Success plot of out-of-plane rotation (39) SRDCF [60.5] MEEM [57.2] SAMF [56.0] DSST [54.1] KCF [49.9] TGPR [48.6] ASLA [46.9] ACT [46.3] Struck [45.3] SCM [42.4] Overlap threshold 0 0.2 0.4 0.6 0.8 1 O v e rl a p P re c is io n [ % ] 0 20 40 60 80 Success plot of scale variation (28) SRDCF [59.3] DSST [55.2] SAMF [52.0] MEEM [50.7] ASLA [49.7] SCM [48.1] Struck [43.1] KCF [42.8] TGPR [42.4] ACT [41.0] Overlap threshold 0 0.2 0.4 0.6 0.8 1 O v e rl a p P re c is io n [ % ] 0 20 40 60 80 Success plot of motion blur (12) SRDCF [60.8] MEEM [56.8] SAMF [52.4] KCF [50.0] Struck [47.7] ACT [46.8] DSST [45.8] TGPR [42.5] EDFT [40.5] CFLB [36.5] Overlap threshold 0 0.2 0.4 0.6 0.8 1 O v e rl a p P re c is io n [ % ] 0 20 40 60 80 Success plot of occlusion (29) SRDCF [63.4] SAMF [62.8] MEEM [57.5] DSST [53.8] KCF [51.7] TGPR [47.0] ACT [45.2] Struck [44.9] ASLA [44.7] SCM [42.1] Figure 7....
[...]
...Contrary to [14], we target the problem of multi-dimensional features, such as HOG, crucial for the overall tracking performance [10, 20]....
[...]
...We provide a comparison of our tracker with 24 state-ofthe-art methods from the literature: MIL [2], IVT [28], CT [36], TLD [22], DFT [29], EDFT [12], ASLA [21], L1APG [3], CSK [19], SCM [37], LOT [26], CPF [27], CXT [11], Frag [1], Struck [16], LSHT [17], LSST [32], ACT [10], KCF [20], CFLB [14], DSST [8], SAMF [24], TGPR [15] and MEEM [35]....
[...]
...approaches [5, 8, 10, 19, 20, 24] have successfully been applied to the tracking problem [23]....
[...]
3,828 citations
"Learning Spatially Regularized Corr..." refers methods in this paper
...Figure 5 shows the success plots for TRE and SRE on the OTB-2013 dataset with 50 videos....
[...]
...We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014....
[...]
...Attribute-based analysis of our approach on the OTB-2013 dataset with 50 videos....
[...]
...The dataset extends OTB-2013 and contains 100 videos....
[...]
...Table 1 shows the mean overlap precision (OP) for the four methods on the OTB-2013 dataset....
[...]
3,151 citations
"Learning Spatially Regularized Corr..." refers methods in this paper
...We provide a comparison of our tracker with 24 state-ofthe-art methods from the literature: MIL [2], IVT [28], CT [36], TLD [22], DFT [29], EDFT [12], ASLA [21], L1APG [3], CSK [19], SCM [37], LOT [26], CPF [27], CXT [11], Frag [1], Struck [16], LSHT [17], LSST [32], ACT [10], KCF [20], CFLB [14], DSST [8], SAMF [24], TGPR [15] and MEEM [35]....
[...]