Robust visual tracking via online multiple instance learning with Fisher information

Xu, Chao; Tao, Wenyuan; Meng, Zhaopeng; Feng, Zhiyong

doi:10.1016/j.patcog.2015.06.004

Cited by 36 publications

(16 citation statements)

References 41 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most trackers use statistical learning techniques to take charge of constructing robust object descriptors and building effective mathematical models for target identification. [16][17][18][19][20][21][22][23] As estimated object position is converted into labeled samples, it is hard to give the accurate estimation of the object position. Wang et al used an inverse sparse representation formulation and a locally weighted distance metric to propose a sparsity-based tracking algorithm.…”

Section: Related Workmentioning

confidence: 99%

Visual tracking via improving motion model and model updater

Xue

Feng

et al. 2018

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

Motion model and model updater are two necessary components for online visual tracking. On the one hand, an effective motion model needs to strike the right balance between target processing, to account for the target appearance and scene analysis, and to describe stable background information. Most conventional trackers focus on one aspect out of the two and hence are not able to achieve the correct balance. On the other hand, the admirable model update needs to consider both the tracking speed and the model drift. Most tracking models are updated on every frame or fixed frames, so it cannot achieve the best performance. In this article, we solve the motion model problem by collaboratively using salient region detection and image segmentation. Particularly, the two methods are for different purposes. In the absence of prior knowledge, the former considers image attributes like color, gradient, edges, and boundaries then forms a robust object; the latter aggregates individual pixels into meaningful atomic regions by using the prior knowledge of target and background in the video sequence. Taking advantage of their complementary roles, we construct a more reasonable confidence map. For model update problems, we dynamically update the model by analyzing scene with image similarity, which not only reduces the update frequency of the model but also suppresses the model drift. Finally, we use these improved building blocks not only to do comparative tests but also to give a basic tracker, and extensive experimental results on OTB50 show that the proposed methods perform favorably against the state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Visual tracking via improving motion model and model updater

Xue

Feng

et al. 2018

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Viola et al [12] proposed an algorithm, known as Fretcit k-NN based on minimum Hausdorff dissimilarity measure, and determined the class label of unseen bag by utilizing both references and citers. MIL approaches also have significant contribution to visual tracking [15,17,58] and real time video event detection areas [59].…”

Section: Overview Of Multiple Instance Learning Approaches and Their mentioning

confidence: 99%

Twin Support Vector Machine for Multiple Instance Learning Based on Bag Dissimilarities

Tomar

Agarwal

2016

Advances in Artificial Intelligence

View full text Add to dashboard Cite

In multiple instance learning (MIL) framework, an object is represented by a set of instances referred to as bag. A positive class label is assigned to a bag if it contains at least one positive instance; otherwise a bag is labeled with negative class label. Therefore, the task of MIL is to learn a classifier at bag level rather than at instance level. Traditional supervised learning approaches cannot be applied directly in such kind of situation. In this study, we represent each bag by a vector of its dissimilarities to the other existing bags in the training dataset and propose a multiple instance learning based Twin Support Vector Machine (MIL-TWSVM) classifier. We have used different ways to represent the dissimilarity between two bags and performed a comparative analysis of them. The experimental results on ten benchmark MIL datasets demonstrate that the proposed MIL-TWSVM classifier is computationally inexpensive and competitive with state-of-the-art approaches. The significance of the experimental results has been tested by using Friedman statistic and Nemenyi post hoc tests.

show abstract

“…However, only one positive sample (the tracking result) is used for classifier updating. Once the tracking result drifts away from the ground truth, the positive sample is inaccurately cropped [ 14 ]. Therefore, the interference from background will be introduced into the classifier, which leads to tracking failure.…”

Section: Introducementioning

confidence: 99%

Patch Based Multiple Instance Learning Algorithm for Object Tracking

Wang¹,

Wang²,

Zhang

2017

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To deal with the problems of illumination changes or pose variations and serious partial occlusion, patch based multiple instance learning (P-MIL) algorithm is proposed. The algorithm divides an object into many blocks. Then, the online MIL algorithm is applied on each block for obtaining strong classifier. The algorithm takes account of both the average classification score and classification scores of all the blocks for detecting the object. In particular, compared with the whole object based MIL algorithm, the P-MIL algorithm detects the object according to the unoccluded patches when partial occlusion occurs. After detecting the object, the learning rates for updating weak classifiers' parameters are adaptively tuned. The classifier updating strategy avoids overupdating and underupdating the parameters. Finally, the proposed method is compared with other state-of-the-art algorithms on several classical videos. The experiment results illustrate that the proposed method performs well especially in case of illumination changes or pose variations and partial occlusion. Moreover, the algorithm realizes real-time object tracking.

show abstract

Robust visual tracking via online multiple instance learning with Fisher information

Cited by 36 publications

References 41 publications

Visual tracking via improving motion model and model updater

Visual tracking via improving motion model and model updater

Twin Support Vector Machine for Multiple Instance Learning Based on Bag Dissimilarities

Patch Based Multiple Instance Learning Algorithm for Object Tracking

Contact Info

Product

Resources

About