A self-adaptive edge matching method based on mean shift and its application in video tracking

Liu, Y. M.; Zhou, Shan

doi:10.1179/1743131x12y.0000000042

Cited by 5 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed time domain constraint based method, more matched features among more frames are utilised, and therefore, the matching accuracy and robustness are improved. 9 Estimation results of vehicle moving orientation …”

Section: Discussionmentioning

confidence: 99%

“…The following researches can be divided into two classes: non-linear iterative optimisation of key frames 6,7 or by filtering. 8,9 In the first group of approaches, different feature points are utilised to refine motion estimation. Based on 3D to two-dimensional projection, the non-linear optimisation techniques, such as Longuet-Higgins rule, 10 and their bundle adjustment approaches 11,12 are developed to achieve the optimal estimation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time domain optimisation for monocular visual navigation: moving horizon approach

Liao

Yang

Liu

et al. 2015

The Imaging Science Journal

View full text Add to dashboard Cite

Estimating ego motion of monocular visual system from the input image sequence is a critical problem in computer vision. This paper considers this problem from the view of time domain optimisation. At first, based on the frame to frame matches, the traditional monocular visual navigation algorithm is introduced, and this process is also seen as a two-view method. On the basis of the three-view matches, the trifocal tensor based monocular navigation algorithm is described. In addition, this paper proposes a novel moving horizon estimation (MHE) based algorithm to tackle the pose estimation problem. In this algorithm, the epipolar constraints and the closed loop constraints of position along with consecutive time steps are all involved in the global optimisation model. In accordance with this optimisation function, the MHE is introduced to achieve the tradeoff between computation costs and estimation accuracy. Because of the inherent robustness of the referred moving horizon estimator, it is becoming more popular in various applications. Based on the general epipolar constraints, trifocal tensor constraints and step crossed optimisation function during the whole moving window, the corresponding three referred pose estimation algorithms are all implemented comparatively at the end of this paper. The rotation and translation experiments are implemented to validate the improvements of the time domain optimisation methods.List of symbols C k camera optical centered coordinate system in kth step I k image coordinate system in kth step q ab rotation quaternion from a to b system r ab relative displacement vector between a and b system r abc , V abc , v abc description of r abc , V abc and v abc in c system R ab direction cosine matrix between a and b system V ab relative velocity vector between a and b system, m s 21 W world coordinate system v ab relative angular velocity between a and b system, rad s 21 P C k optical centered plane, xoy plane of C k P I k image plane, xoy plane of I k

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Time domain optimisation for monocular visual navigation: moving horizon approach

Liao

Yang

Liu

et al. 2015

The Imaging Science Journal

View full text Add to dashboard Cite

show abstract

“…In Ref. 8, by using mean-shift for edge matching, the performance of the particle filtering tracking was improved. The iterative search property of the mean-shift algorithm was used to find the local optimal solution of a probability distribution, which was then used by the particle filters.…”

Section: Introductionmentioning

confidence: 98%

A multimodal approach for individual tracking of people and their belongings

Beyan

Temizel

2015

The Imaging Science Journal

View full text Add to dashboard Cite

In this study, a fully automatic surveillance system for indoor environments which is capable of tracking multiple objects using both visible and thermal band images is proposed. These two modalities are fused to track people and the objects they carry separately using their heat signatures and the owners of the belongings are determined. Fusion of complementary information from different modalities (for example, thermal images are not affected by shadows and there is no thermal reflection or halo effect in visible images) is shown to result in better object detection performance. We use adaptive background modeling and local intensity operation for object detection and the mean-shift tracking algorithm for fully automatic tracking. Trackers are refreshed to resolve potential problems which may occur due to the changes in object's size, shape and to handle occlusion-split and to detect newly emerging objects as well as objects that leave the scene. The proposed scheme is applied to the abandoned object detection problem and the results are compared with the state of art methods. The results show that the proposed method facilitate individual tracking of objects for various applications, and provide lower false alarm rates compared to the state of art methods when applied to the abandoned object detection problem.

show abstract

Midlevel cues mean shift visual tracking algorithm based on target-background saliency confidence map

Xie

Wang

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

A self-adaptive edge matching method based on mean shift and its application in video tracking

Cited by 5 publications

References 24 publications

Time domain optimisation for monocular visual navigation: moving horizon approach

Time domain optimisation for monocular visual navigation: moving horizon approach

A multimodal approach for individual tracking of people and their belongings

Midlevel cues mean shift visual tracking algorithm based on target-background saliency confidence map

Contact Info

Product

Resources

About