Object tracking based on Kalman particle filter with LSSVR

Zhou, Zhiyu; Wu, Dichong; Zhu, Zefei

doi:10.1016/j.ijleo.2015.10.038

Cited by 19 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [41] used the spatial feature and the temporal feature which are fused into the deep residual network model with the multi-scale feature vector, so that they can obtain the deep multi-scale spatiotemporal feature model. Zhou et al [45] proposed a novel object tracking method with the fusion of the extended Kalman particle filter (EKPF) and the least squares support vector regression (LSSVR) to effectively improve the accuracy. Zhang et al [42] put forward a multi-feature integration framework, including the gray features, histogram of gradient (HOG), color-naming (CN), and illumination invariant features (IIF), in order to overcome the problem of poor representation of single feature in a complex image sequence.…”

Section: Generative Trackingmentioning

confidence: 99%

Object Tracking with Multi-Classifier Fusion Based on Compressive Sensing and Multiple Instance Learning

Chen

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Object tracking is a critical research in computer vision and has attracted significant attention over the past few years. However, the traditional object tracking algorithms often suffer from the object drifting problem due to various challenging factors in complex environments such as object occlusion and background clutter. This paper proposes a robust and effective object tracking algorithm, called MCM, which combines compressive sensing and online multiple instance learning in a multi-classifier fusion framework. In this framework, we integrate the different discriminative classifiers by learning the varied and compressed feature vectors based on different random projection matrices. And then an improved online multiple instance learning mechanism SMILE is adopted, which introduces the relative similarity to select and weight the instances in the positive bag. The experiments show that the proposed algorithm can improve the performance of object tracking on the challenging video sequences.

show abstract

Section: Generative Trackingmentioning

confidence: 99%

Object Tracking with Multi-Classifier Fusion Based on Compressive Sensing and Multiple Instance Learning

Chen

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…For = 2 to "the number of image sequences"  The particles' position vectors { ( ) } =1 are updated based on the state transition model and the target center is calculated. The particles' weights are calculated according to equation (10) and are normalized using equation (6).  The number of effective samples Neff is obtained using equation (7).…”

Section: The Proposed Approaches In the Hybrid Pf Trackermentioning

confidence: 99%

“…The visual tracking process is the estimation of time variant positions of a moving object in a video sequence based on some measurement (observation) information [1][2][3][4][5][6][7][8][9]. Object tracking systems are applicable in various fields such as surveillance systems [3,4,10], humancomputer interactions [3,4], driving assistance [4] and etc. In these tracking systems, there are a lot of problems to be surmounted of which we can note partial and full occlusion [3,5,7], illumination variation [3,4,9], dynamic background [7], irregular movement [7], complex scene [7], sudden and fast motion [3], target scale change and rotational errors.…”

Section: Introduction1mentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Target Tracking Algorithm Based on Particle Filter and Genetic Algorithm

Moghadasi

Faraji

2019

IJE

View full text Add to dashboard Cite

In this paper, we propose an efficient hybrid Particle Filter (PF) algorithm for video tracking by employing a genetic algorithm to solve the sample impoverishment problem. In the presented method, the object to be tracked is selected by a rectangular window inside which a few numbers of particles are scattered. The particles' weights are calculated based on the similarity between feature vectors of the scattered particles and that of the central particle. Before the resampling stage of PF algorithm, particles with the highest weights are evolved using a genetic algorithm. The evolved particles' coordinates are transferred to the next frame by a random walk model, and the rectangle involving new particles is specified. Moreover, we utilize the idea of partitioning (selecting parts of target in the first frame with a distinct color/texture) and reducing image size to decrease the number of particles. The partitioning idea also helps our method in resolving the occlusion problem. Simulation results demonstrate the outperformance of the suggested approach comparing with other methods in terms of precision and tracking time when it encounters with the challenges such as full and partial occlusions, illumination and scale variations, fast motions, and color similarity between the object and background.

show abstract

“…Visual tracking [1][2][3] has been employed extensively in many practical applications, for example, robot navigation, video surveillance, and satellite measurement and so on, and the "tracking-by-detection" method has become the focus in the research literature of the discipline. By building the appearance of the model based on the object and background, the position of the target of interest has been evaluated.…”

Section: Introductionmentioning

confidence: 99%

Multiple instance learning tracking based on Fisher linear discriminant with incorporated priors

Zhou

Xia

et al. 2018

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

Traditional tracking-by-detection methods use online classifier to track object, and the classifier can be degenerated easily using self-learning process. The article presents a multiple instance learning (MIL) tracking method based on a semisupervised learning model with Fisher linear discriminant (MILFLD). First, the overlap rate of sampled instances and tracking object served as the prior information. Using both labeled and unlabeled data, the tracking drift problem in the learning model could be alleviated. Second, the lost function of MILFLD is built using Fisher linear discriminant model incorporated with priors. Hence the optimal classifier can be selected out directly in instance level. Last but not least, the classifiers are chosen by gradient descent method, assuring the maximum descent of lost function. Therefore, the classifiers selected at previous frames are still discriminative to future frames, which can help to constrain the error propagation. Comparison experiments show that the center location errors of online AdaBoosting , online MIL tracking, weighted MIL tracking (WMIL), compressive tracking (CT), struck tracking, and MILFLD are 78, 66, 62,74, 59, and 25 pixels, respectively, which demonstrates the tracking accuracy of our method. The experiments of robot motion tracking in realistic scenario have been complemented for comparison as well. Despite the variations in illumination, deformation, or occlusions of the objects, the proposed method can track the target accurately and has high real-time performance.

show abstract

Object tracking based on Kalman particle filter with LSSVR

Cited by 19 publications

References 15 publications

Object Tracking with Multi-Classifier Fusion Based on Compressive Sensing and Multiple Instance Learning

Object Tracking with Multi-Classifier Fusion Based on Compressive Sensing and Multiple Instance Learning

An Efficient Target Tracking Algorithm Based on Particle Filter and Genetic Algorithm

Multiple instance learning tracking based on Fisher linear discriminant with incorporated priors

Contact Info

Product

Resources

About