Real-time visual tracking via online weighted multiple instance learning

Zhang, Kaihua; Song, Hwangjun

doi:10.1016/j.patcog.2012.07.013

Cited by 258 publications

(228 citation statements)

References 24 publications

Supporting

Mentioning

228

Contrasting

Order By: Relevance

“…In this section, we implement our method on 7 challenging sequences, compared with the latest three algorithms (CT [7], WMIL [20], and FCT [14]). All the video clips are publicly available (all of the sequences can be download on visual tracking benchmark).…”

Section: Methodsmentioning

confidence: 99%

Adaptive Scale Compressive Tracking with Feature Integration

2017

View full text Add to dashboard Cite

Abstract. Compressive tracking (CT) is utilized to cope with real-time tracking, which use a very sparse measurement matrix to compressive samples of targets and background, then a classifier is trained to distinguish foreground and background. However, this algorithm suffers from the drifting problem, and used the fixed size tracking box to detect, recognize, and update the samples and classifier. In order to solve these problems, we adopt a different way to extracted positive samples, and employ powerful features to exploit the advantages of feature fusion to describe target, a scale pyramid is used to realize adaptive scale tracking. Experimental results on various benchmark video sequences demonstrate the superior performance of our algorithm.

show abstract

Section: Methodsmentioning

confidence: 99%

Adaptive Scale Compressive Tracking with Feature Integration

2017

View full text Add to dashboard Cite

show abstract

“…Other approaches such as [13,14,15] also use tracking to improve the object detector then used for extracting positive and negative examples from the current frame. Babenko et al [13] use multiple instance learning (MIL), Zhang et al [14] use sparse representation, and Lu et al [15] use weighted multiple instance learning (WMIL).…”

Section: Related Workmentioning

confidence: 99%

“…Babenko et al [13] use multiple instance learning (MIL), Zhang et al [14] use sparse representation, and Lu et al [15] use weighted multiple instance learning (WMIL). However, these tracking-by-detection approaches are trained with the aim of tracking a single object given an initial bounding box, while in our case, foreground detectors are trained to detect at the same time multiple and different object categories in an unsupervised way and without any specific initialization.…”

Section: Related Workmentioning

confidence: 99%

Combining where and what in change detection for unsupervised foreground learning in surveillance

Huerta

Pedersoli

Gonzàlez³

et al. 2015

Pattern Recognition

View full text Add to dashboard Cite

Change detection is the most important task for video surveillance analytics such as foreground and anomaly detection. Current foreground detectors learn models from annotated images since the goal is to generate a robust foreground model able to detect changes in all possible scenarios. Unfortunately, manual labelling is very expensive. Most advanced supervised learning techniques based on generic object detection datasets currently exhibit very poor performance when applied to surveillance datasets because of the unconstrained nature of such environments in terms of types and appearances of objects. In this paper, we take advantage of change detection for training multiple foreground detectors in an unsupervised manner. We use statistical learning techniques which exploit the use of latent parameters for selecting the best foreground model parameters for a given scenario. In essence, the main novelty of our proposed approach is to combine the where (motion segmentation) and what (learning procedure) in change detection in Preprint submitted to Pattern Recognition November 3, 2014 an unsupervised way for improving the specificity and generalization power of foreground detectors at the same time. We propose a framework based on latent Support Vector Machines that, given a noisy initialization based on motion cues, learns the correct position, aspect ratio, and appearance of all moving objects in a particular scene. Specificity is achieved by learning the particular change detections of a given scenario, and generalization is guaranteed since our method can be applied to any possible scene and foreground object, as demonstrated in the experimental results outperforming the state-of-the-art.

show abstract

“…Fortunately, Zhang et al [21] proposed an online multiple instance learning (MIL) tracker by putting the positive samples and the negative ones into several positive and negative bags, after which a classifier is trained online, according to the bag likelihood function. Furthermore, a weighted multiple instance learning (WMIL) tracker was developed by integrating the sample importance into the learning procedure [22].…”

Section: Introductionmentioning

confidence: 99%

Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Wan

Qian

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Infrared moving target tracking plays a fundamental role in many burgeoning research areas of Smart City. Challenges in developing a suitable tracker for infrared images are particularly caused by pose variation, occlusion, and noise. In order to overcome these adverse interferences, a total variation regularization term-based low-rank and sparse matrix representation (TV-LRSMR) model is designed in order to exploit a robust infrared moving target tracker in this paper. First of all, the observation matrix that is derived from the infrared sequence is decomposed into a low-rank target matrix and a sparse occlusion matrix. For the purpose of preventing the noise pixel from being separated into the occlusion term, a total variation regularization term is proposed to further constrain the occlusion matrix. Then an alternating algorithm combing principal component analysis and accelerated proximal gradient methods is employed to separately optimize the two matrices. For long-term tracking, the presented algorithm is implemented using a Bayesien state inference under the particle filtering framework along with a dynamic model update mechanism. Both qualitative and quantitative experiments that were examined on real infrared video sequences verify that our algorithm outperforms other state-of-the-art methods in terms of precision rate and success rate.

show abstract

Real-time visual tracking via online weighted multiple instance learning

Cited by 258 publications

References 24 publications

Adaptive Scale Compressive Tracking with Feature Integration

Adaptive Scale Compressive Tracking with Feature Integration

Combining where and what in change detection for unsupervised foreground learning in surveillance

Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Contact Info

Product

Resources

About