Hough-based tracking of non-rigid objects

By Martin Godec, Peter M. Roth, Horst Bischof. Vision, 2011

395 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c6f89de36a8114787dd163f6a4d75e443ff77b74

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking (2016, methodology): “SPT [50] uses super-pixels for matching, HBT [12] uses HOG-features in a probabilistic approach, and FBT [32] uses color invariants for robustness against illumination variations.”
One-Shot Video Object Segmentation (2016, methodology): “In the latter to JOTS [52], TMFG [25] KEY [24], HVS [17] HBT [16], ST [51] and OFL [49].”
VideoMatch: Matching based Video Object Segmentation (2018, background): “, MSK [25], SFL [8], OSVOS [5], OnAVOS [53], PLM [59], MaskRNN [19], Lucid [26], SEA [1], HVS [15], JMP [13], FCP [41], BVS [34], OFL [50], CTN [24], VPN [23], SVC [54], JFS [36], LTV [37], HBT [14], AFS [51], SCF [21], RB [2] and DA [60].”
Visual Tracking: an Experimental Survey (2013, neutral): “2D binary patterns are used in TLD [1], SURF-features in FBT [62], and Labcolor features among others in HBT [63].”
Click Carving: Segmenting Objects in Video with Point Clicks (2016, methodology): “We compare with state-of-the art methods [25], [15], [10], [21], [18], [1], [24], [9], [43] and our own baselines.”
In defense of color-based model-free tracking (2015, methodology): “[7, 17]) to improve the generative model, these still suffer from missing discriminative capabilities to distinguish the object from its surrounding background.”
Incremental Learning of NCM Forests for Large-Scale Image Classification (2014, background): “The approach of [11] ﬁrst trains the trees in an extremely random fashion and subsequent updates are performed only at the leaves.”
Robust video segment proposals with painless occlusion handling (2015, background): “Many approaches focus on separating one foreground object from the background, using semi-supervised or unsupervised methods [4, 18, 28, 37, 38, 41, 45].”
Learning Video Object Segmentation from Static Images (2016, background): “Some previous works have investigated approaches that improve segmentation quality by leveraging object tracking and vice versa [10, 13, 17, 40, 53].”
Alternating Regression Forests for Object Detection and Pose Estimation (2013, background): “, object detection [9] and tracking [11], semantic segmentation [20] or object categorization [16], to name but a few.”
Robust Superpixel Tracking (2014, methodology): “The proposed superpixel-based tracking (SPT) algorithm is evaluated against several state-of-the-art tracking methods, including the IVT [3], Frag [5], MIL [7], 1 [11], PROST [18], VTD [12], TLD [13], Struck [14] and HT [32] tracking methods.”
Locally Orderless Tracking (2012, methodology): “When tracking deformable objects one often uses histogram representations [8] or discriminative methods that treat the problem as a pixel-wise binary classification problem [9, 10, 11].”
Tracking via Robust Multi-task Multi-view Joint Sparse Representation (2013, neutral): “at/research/houghtrack/ [8]”
Real-time part-based visual tracking via adaptive correlation filters (2015, methodology): “To handle the occlusion, many trackers divide the entire targets into separate parts [10, 11, 15, 18, 30, 38, 39, 41, 45, 48, 51].”
The Visual Object Tracking VOT2016 Challenge Results (2016, background): “The reader is referred to [110] for details and to http://lrs.”
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (2017, methodology): “Segtrack-v2 dataset (14 videos) Methods Flow-Th Flow-Sal FST [8] KEY [4] NLC [9] HBT [58] HVS [1] Ours-A Ours-M Ours-Joint Supervised?”
Tracking-based semi-supervised learning (2011, methodology): “Additionally, the use of an object tracker similar to the one in Godec et al. (2011) could lift the stationary camera requirement.”