Segmentation-based tracking by support fusion

Heber, Markus; Godec, Martin; Rüther, Matthias; Roth, Peter M.; Bischof, Horst

doi:10.1016/j.cviu.2013.02.001

Cited by 15 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assume that the occluded foreground has been segmented from the traffic background without visual artefacts. Many methods can judge the beginning and the ending of occlusions, for example, the bounding box distance method [22] and the connected component method [23]. We use a bidirectional reasoning model proposed in [5] to detect occlusions.…”

Section: Methods Descriptionmentioning

confidence: 99%

Multilevel framework to handle object occlusions for real‐time tracking

Cai

Wang

Chen

et al. 2016

IET Image Processing

View full text Add to dashboard Cite

Section: Methods Descriptionmentioning

confidence: 99%

Multilevel framework to handle object occlusions for real‐time tracking

Cai

Wang

Chen

et al. 2016

IET Image Processing

View full text Add to dashboard Cite

“…W HILE several tracking methods have been developed over the past decade [1], [2], [3], [4], [5], [6], [7] and have been proven to be successful in many applications, such as robotics or video surveillance, tracking small objects in videos still remains a challenging problem, in particular when the complex scenarios and real time constraints are to be considered. In this paper, small objects mean that the targets in images have sizes of less than 1% of the whole image.…”

Section: Introductionmentioning

confidence: 99%

Aggregation Signature for Small Object Tracking

Liu

Ding

Yang

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://github.com/bczhangbczhang/.

show abstract

“…A perfect parsing can contribute to a variety of applications including unmanned vehicles, environmental reconstruction, and visual SLAM. Many other fundamental computer vision problems can benefit from the parsing of an image, such as medical image analysis, tracking, and object detection [1,2,3].…”

Section: Introductionmentioning

confidence: 99%

MoE-SPNet: A mixture-of-experts scene parsing network

Gong

Wang

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

Scene parsing is an indispensable component in understanding the semantics within a scene. Traditional methods rely on handcrafted local features and probabilistic graphical models to incorporate local and global cues. Recently, methods based on fully convolutional neural networks have achieved new records on scene parsing. An im-2012 and SceneParse150 based on two kinds of baseline models FCN-8s and DeepLab-ASPP.

show abstract

Segmentation-based tracking by support fusion

Cited by 15 publications

References 42 publications

Multilevel framework to handle object occlusions for real‐time tracking

Multilevel framework to handle object occlusions for real‐time tracking

Aggregation Signature for Small Object Tracking

MoE-SPNet: A mixture-of-experts scene parsing network

Contact Info

Product

Resources

About