A local-motion-based probabilistic model for visual tracking

Kristan, Matej; Perš, Janez; Kovačič, Stanislav; Leonardis, Aleš

doi:10.1016/j.patcog.2009.01.002

Cited by 35 publications

(13 citation statements)

References 26 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Parameters: The search radius R of the tracker is set in the interval [20], [50], the search scale c is set to 2 and the balance parameter κ b in Equ. (2) [10,20].…”

Section: B Evaluation Of Target Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Robust Online Learned Spatio-Temporal Context Model for Visual Tracking

Wen

Cai

Lei

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Visual tracking is an important but challenging problem in the computer vision field. In the real world, the appearances of the target and its surroundings change continuously over space and time, which provides effective information to track the target robustly. However, enough attention has not been paid to the spatio-temporal appearance information in previous works. In this paper, a robust spatio-temporal context model based tracker is presented to complete the tracking task in unconstrained environments. The tracker is constructed with temporal and spatial appearance context models. The temporal appearance context model captures the historical appearance of the target to prevent the tracker from drifting to the background in a long-term tracking. The spatial appearance context model integrates contributors to build a supporting field. The contributors are the patches with the same size of the target at the key-points automatically discovered around the target. The constructed supporting field provides much more information than the appearance of the target itself, and thus, ensures the robustness of the tracker in complex environments. Extensive experiments on various challenging databases validate the superiority of our tracker over other state-of-the-art trackers.

show abstract

“…2) Parameters: The search radius R of the tracker is set in the interval [20], [50], the search scale c is set to 2 and the balance parameter κ b in Equ. (2) [10,20].…”

Section: B Evaluation Of Target Trackingmentioning

confidence: 99%

“…Some work has also been done on the search strategy [22], [43]. In real applications, the motion of target is hard to define, especially when the video is captured by a moving camera, therefore just a few works pay attention to the motion model [20], [28].…”

mentioning

confidence: 99%

Robust Online Learned Spatio-Temporal Context Model for Visual Tracking

Wen

Cai

Lei

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Lucena et al [4] enhance the observation model of a particle filter by incorporating the Lucas-Kanade flow. Kristan et al [5] obtain Lucas-Kanade estimates to locally adapt the observation model for each tracked object.…”

Section: Research Funded By a Phd Grant Of The Institute For The Prommentioning

confidence: 99%

Sparse optical flow regularization for real-time visual tracking

Spruyt

Ledda

Philips

2013

2013 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Optical flow can greatly improve the robustness of visual tracking algorithms. While dense optical flow algorithms have various applications, they can not be used for real-time solutions without resorting to GPU calculations. Furthermore, most optical flow algorithms fail in challenging lighting environments due to the violation of the brightness constraint. We propose a simple but effective iterative regularisation scheme for real-time, sparse optical flow algorithms, that is shown to be robust to sudden illumination changes and can handle large displacements. The algorithm proves to outperform well known techniques in real life video sequences, while being much faster to calculate. Our solution increases the robustness of a real-time particle filter based tracking application, consuming only a fraction of the available CPU power. Furthermore, a new and realistic optical flow dataset with annotated ground truth is created and made freely available for research purposes.

show abstract

“…For example, Kristan et al [16] use a measurement model combining color and optical flow to resolve color-only ambiguities. They use a mixed dynamic model combining constant velocity for position and Brownian evolution for size.Čehovin et al [31] built on that approach with a constellation of local visual parts, which get resampled spatially based on consistency with an object's higher-level appearance.…”

Section: Related Workmentioning

confidence: 99%

Motion Models that Only Work Sometimes

Cifuentes¹,

Sturzel²,

Jurie³

et al. 2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

It is too often that tracking algorithms lose track of interest points in image sequences. This persistent problem is difficult because the pixels around an interest point change in appearance or move in unpredictable ways. In this paper we explore how classifying videos into categories of camera motion improves the tracking of interest points, by selecting the right specialist motion model for each video. As a proof of concept, we enumerate a small set of simple categories of camera motion and implement their corresponding specialized motion models. We evaluate the strategy of predicting the most appropriate motion model for each test sequence. Within the framework of a standard Bayesian tracking formulation, we compare this strategy to two standard motion models. Our tests on challenging real-world sequences show a significant improvement in tracking robustness, achieved with different kinds of supervision at training time.frame 0 frame 10 frame 20 Figure 1: Example sequence with overlaid box showing the output of our specialized "forward" motion model, where the velocity and scale of objects approaching the camera tend to increase. Neither Brownian nor constant-velocity motion models are as successful at tracking interest points here.

show abstract

A local-motion-based probabilistic model for visual tracking

Cited by 35 publications

References 26 publications

Robust Online Learned Spatio-Temporal Context Model for Visual Tracking

Robust Online Learned Spatio-Temporal Context Model for Visual Tracking

Sparse optical flow regularization for real-time visual tracking

Motion Models that Only Work Sometimes

Contact Info

Product

Resources

About