Correlation-based self-correcting tracking

Biresaw, Tewodros A.; Cavallaro, Andrea; Regazzoni, Carlo S.

doi:10.1016/j.neucom.2014.10.057

Cited by 11 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All results were achieved for the same set of parameters in the localization pipeline as discussed in Sec. 4 of 0% (complete failure) for the archery, tennis court, and squash sequences, to 100% (complete success) for the frisbee sequences. The sequences with the best results contain objects with prominent FMO characteristics, i.e.…”

Section: Discussionmentioning

confidence: 99%

“…Tracking is a key problem in video processing. A range of methods has been proposed based on diverse principles, such as correlation [4,9,8], feature point tracking [24], mean-shift [6,25], and tracking-by-detection [29,12]. The literature sometimes refer to fast moving objects, but only the case with no significant blur is considered, e.g.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The World of Fast Moving Objects

Rozumnyi

Kotera

Šroubek

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

The notion of a Fast Moving Object (FMO), i.e. an object that moves over a distance exceeding its size within the exposure time, is introduced. FMOs may, and typically do, rotate with high angular speed. FMOs are very common in sports videos, but are not rare elsewhere. In a single frame, such objects are often barely visible and appear as semitransparent streaks.A method for the detection and tracking of FMOs is proposed. The method consists of three distinct algorithms, which form an efficient localization pipeline that operates successfully in a broad range of conditions. We show that it is possible to recover the appearance of the object and its axis of rotation, despite its blurred appearance. The proposed method is evaluated on a new annotated dataset. The results show that existing trackers are inadequate for the problem of FMO localization and a new approach is required. Two applications of localization, temporal superresolution and highlighting, are presented.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

The World of Fast Moving Objects

Rozumnyi

Kotera

Šroubek

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Object tracking methods are based on diverse principles, such as correlation [4,8,9,22,33], feature point tracking [35], mean-shift [6,36], and trackingby-detection [40,12]. In addition, several surveys of object tracking have been compiled [1,2,11].…”

Section: Related Workmentioning

confidence: 99%

“…In addition, several surveys of object tracking have been compiled [1,2,11]. Excellent performance in visual object tracking has been shown by discriminative correlation filters [4,8,9,22], yet all the methods fail when the tracked object is blurred as demonstrated in [28].…”

Section: Related Workmentioning

confidence: 99%

Intra-Frame Object Tracking by Deblatting

Kotera¹,

Rozumnyi²,

Šroubek³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Objects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects elapse non-negligible distance during exposure time of a single frame and therefore their position in the frame is not well defined. They appear as semitransparent streaks due to the motion blur and cannot be reliably tracked by standard trackers.We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. The trajectory is then estimated by fitting a piecewise quadratic curve, which models physically justifiable trajectories. As a result, tracked objects are precisely localized with higher temporal resolution than by conventional trackers.The proposed TbD tracker was evaluated on a newly created dataset of videos with ground truth obtained by a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms baseline both in recall and trajectory accuracy.

show abstract

“…As a result, computational complexity of the method becomes high. Some works on human pose tracking based on 3D data [16] [21], [4], [42], [40], [59], [7] are also available in the literature. We propose that we would estimate the human pose in the first frame of the video and then onward track the pose throughout the video.…”

Section: Related Workmentioning

confidence: 99%

A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial Structure

Samanta,

Chanda

2016

Preprint

View full text Add to dashboard Cite

In this paper, we present a data-driven approach for human pose tracking in video data. We formulate the human pose tracking problem as a discrete optimization problem based on spatio-temporal pictorial structure model and solve this problem in a greedy framework very efficiently. We propose the model to track the human pose by combining the human pose estimation from single image and traditional object tracking in a video. Our pose tracking objective function consists of the following terms: likeliness of appearance of a part within a frame, temporal displacement of the part from previous frame to the current frame, and the spatial dependency of a part with its parent in the graph structure. Experimental evaluation on benchmark datasets (VideoPose2, Poses in the Wild and Outdoor Pose) as well as on our newly build ICDPose dataset shows the usefulness of our proposed method.

show abstract

Correlation-based self-correcting tracking

Cited by 11 publications

References 47 publications

The World of Fast Moving Objects

The World of Fast Moving Objects

Intra-Frame Object Tracking by Deblatting

A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial Structure

Contact Info

Product

Resources

About