Gravity optimised particle filter for hand tracking

Morshidi, Malik Arman; Tjahjadi, Tardi

doi:10.1016/j.patcog.2013.06.032

Cited by 24 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Campr et al [8] used joint particle filter to calculate a combined likelihood model of hands and head. Morshidi and Tjahjadi [9] presented a hand tracking method based on gravity optimized particle filter. The literature demonstrates that particle filter is well-suited to hand tracking applications, given its capability to model non-linear probability distribution, although the perfor-mance is highly dependent on suitably chosen dynamic and observation models.…”

Section: Related Workmentioning

confidence: 99%

A four dukkha state-space model for hand tracking

Lim

Tan

2017

Neurocomputing

View full text Add to dashboard Cite

In this paper, we propose a hand tracking method which was inspired by the notion of the four dukkha: birth, aging, sickness and death (BASD) in Buddhism. Based on this philosophy, we formalize the hand tracking problem in the BASD framework, and apply it to hand track hand gestures in isolated sign language videos. The proposed BASD method is a novel nature-inspired computational intelligence method which is able to handle complex real-world tracking problem. The proposed BASD framework operates in a manner similar to a standard state-space model, but maintains multiple hypotheses and integrates hypothesis update and propagation mechanisms that resemble the effect of BASD. The survival of the hypothesis relies upon the strength, aging and sickness of existing hypotheses, and new hypotheses are birthed by the fittest pairs of parent hypotheses. These properties resolve the sample impoverishment problem of the particle filter. The estimated hand trajectories show promising results for the American sign language.

show abstract

Section: Related Workmentioning

confidence: 99%

A four dukkha state-space model for hand tracking

Lim

Tan

2017

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…In contrast to the Kalman filter, which restricts the filtering system with linear modeling and Gaussian assumptions, particle filters are often used to solve the non-linear and non-Gaussian problems. It has been proved to be an effective algorithm for object tracking [20][21][22].…”

Section: Particle Filter Reviewmentioning

confidence: 99%

Robust Object Tracking in Infrared Video via Adaptive Weighted Patches

Wang

Zhang

2016

MCA

View full text Add to dashboard Cite

With the quick development of computer and electronic techniques, infrared sensor-based object tracking has become a hot research topic in recent years. However, infrared object tracking is still a challenging task due to low resolution, lack of representing information, and occlusion. In this work, we present an adaptive weighted patch-based infrared object tracking scheme. First, the candidate local region is divided into non-overlapping sub regions, and a set of belief weights is set on these patches. After this, a particle filtering-based infrared object tracking system is realized. In the last, the belief weight of each patch is evaluated based on the linear discriminative analysis (LDA) and particle sampling scheme. Experimental results on challenging infrared sequences show that the proposed algorithm can effectively locate the tracking object.

show abstract

“…It can be seen that the two hypotheses of KF theory are quite ideal, which can hardly be met in the actual system. In the fields such image information processing [5], pattern recognition [6], underwater target tracking [7], aircraft tracking [8], space target tracking [9], and robot state estimation [10], there exists another type of non-ideal circumstances that in the process of signal transmission, there will be delay, distortion, attenuation or channel interference, the random uncertainty of system model parameters will be caused by modeling error, model simplification and random disturbance, the ranging noise of the sensor varies with the increase of the distance and appears as multiplicity noise [11]. These circumstances cannot be indicated by additive noise in classical systems.…”

Section: Introductionmentioning

confidence: 99%

A Multiplicative Noises and Additive Correlated Noises Cubature Kalman Filter and Its Application in Quadruped Robot

Liu

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The traditional Cubature Kalman Filter (CKF) and its derived algorithms cannot work without the two hypotheses of Kalman Filter (KF), one is that the system model is accurate and the other is the system is only influenced by independent white noise with known statistical characteristics. However, it is difficult to fully guarantee the above hypotheses in actual operation. The presence of multiplicative noise undermines the first hypothesis, while the additive noise correlation undermines the second hypothesis. Given invalid hypotheses, the estimated performances of CKF and its derivative algorithms are degraded drastically. To solve this issue, this paper proposes Multiplicative Noises and Additive Correlated Noises Cubature Kalman Filter (MACNCKF), which solves state estimation problems involving multiplicative noise and additive noise while maintaining CKF advantages. Moreover, this algorithm has been testified to be correct and easy to be transplanted to CKF and its derivative algorithm after strict mathematical derivation. When the system lacks multiplicative noise and additive noise, the algorithm is degraded to corresponding algorithm in a general form, which helps extend the application environment of CKF and its derivative algorithms, thus improving robustness. Numerical simulation and experiments on quadruped robot system indicate that MACNCKF can effectively solve state estimation problem involving both multiplicative noise and additive noise. Given time consumption in MACNCKF basically comparable to that in CKF, MACNCKF has improved estimation accuracy, robustness and reliability.

show abstract

Gravity optimised particle filter for hand tracking

Cited by 24 publications

References 35 publications

A four dukkha state-space model for hand tracking

A four dukkha state-space model for hand tracking

Robust Object Tracking in Infrared Video via Adaptive Weighted Patches

A Multiplicative Noises and Additive Correlated Noises Cubature Kalman Filter and Its Application in Quadruped Robot

Contact Info

Product

Resources

About