Hierarchical search strategy in particle filter framework to track infrared target

Shi, Zhen; Wei, Chang'an; Li, Junbao; Fu, Ping; Jiang, Shouda

doi:10.1007/s00521-016-2460-z

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in these methods, many particles are needed to cover the states of the real target. In [15,35,36], the result of the saliency extraction is utilized as a prior knowledge of the transition probability model to limit the particle sampling process, which can improve the efficiency of particle sampling significantly. In [37], an improved particle filter framework is proposed to enhance the mean state estimation and resampling procedures, in which the number of high-weighted particles are determined adaptively by applying the k-means clustering over all particles' weights.…”

Section: Particle Filter For Trackingmentioning

confidence: 99%

Mask Sparse Representation Based on Semantic Features for Thermal Infrared Target Tracking

Peng

Chen

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Thermal infrared (TIR) target tracking is a challenging task as it entails learning an effective model to identify the target in the situation of poor target visibility and clutter background. The sparse representation, as a typical appearance modeling approach, has been successfully exploited in the TIR target tracking. However, the discriminative information of the target and its surrounding background is usually neglected in the sparse coding process. To address this issue, we propose a mask sparse representation (MaskSR) model, which combines sparse coding together with high-level semantic features for TIR target tracking. We first obtain the pixel-wise labeling results of the target and its surrounding background in the last frame, and then use such results to train target-specific deep networks using a supervised manner. According to the output features of the deep networks, the high-level pixel-wise discriminative map of the target area is obtained. We introduce the binarized discriminative map as a mask template to the sparse representation and develop a novel algorithm to collaboratively represent the reliable target part and unreliable target part partitioned with the mask template, which explicitly indicates different discriminant capabilities by label 1 and 0. The proposed MaskSR model controls the superiority of the reliable target part in the reconstruction process via a weighted scheme. We solve this multi-parameter constrained problem by a customized alternating direction method of multipliers (ADMM) method. This model is applied to achieve TIR target tracking in the particle filter framework. To improve the sampling effectiveness and decrease the computation cost at the same time, a discriminative particle selection strategy based on kernelized correlation filter is proposed to replace the previous random sampling for searching useful candidates. Our proposed tracking method was tested on the VOT-TIR2016 benchmark. The experiment results show that the proposed method has a significant superiority compared with various state-of-the-art methods in TIR target tracking.

show abstract

Section: Particle Filter For Trackingmentioning

confidence: 99%

Mask Sparse Representation Based on Semantic Features for Thermal Infrared Target Tracking

Peng

Chen

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Some studies applied particle filtering, but with heavy computational burden. [20][21][22] In this paper, the characteristics of SBIRC measurements are analyzed theoretically. Using the mid-riser quantizer in digital signal processing to describe the discrete image plane, the measurement noise model of a SBIRC is given.…”

Section: Introductionmentioning

confidence: 99%

Target Tracking in Boost Stage with Quantized Measurements of Space-based Infrared Cameras

Wang

Cui

2020

Trans. Japan Soc. Aero. S Sci.

View full text Add to dashboard Cite

A novel state estimation method is proposed for target tracking in the boost stage using space-based infrared cameras (SBIRC) whose measurements are essentially corrupted by both Gaussian noise and quantization noise. As the quantization noise has non-Gaussian properties, conventional extended Kalman filtering (EKF) suffers from poor performance. The quantization noise of SBIRC is modelled using the mid-riser quantizer, which is usually adopted in the digital signal processing field. A novel minimum square error (MMSE) state estimation algorithm with quantized measurements, named the quantized extended Kalman filtering (QEKF), is then proposed. The time update is given based on first-order linearization of the nonlinearities, and the measurement update is derived based on the conditional mean estimate given the quantized measurements. As the multidimensional integrals in the measurement update derived doesn't have analytical solutions, a numerical integration method is proposed by combining Genz's transformation and quasi-Monte Carlo (QMC) method, which can avoid the curse of dimensionality. To further improve the tracking accuracy, quantized high-degree cubature Kalman filtering (QHCKF) is developed by integrating the fifth-degree cubature rule into the framework of the QEKF. Numerical simulation results illustrate the superiority of the proposed QEKF and QHCKF methods.

show abstract

Intelligent visual object tracking with particle filter based on Modified Grey Wolf Optimizer

Narayana¹,

Nenavath²,

Chavan³

et al. 2019

Optik

View full text Add to dashboard Cite

Hierarchical search strategy in particle filter framework to track infrared target

Cited by 3 publications

References 22 publications

Mask Sparse Representation Based on Semantic Features for Thermal Infrared Target Tracking

Mask Sparse Representation Based on Semantic Features for Thermal Infrared Target Tracking

Target Tracking in Boost Stage with Quantized Measurements of Space-based Infrared Cameras

Intelligent visual object tracking with particle filter based on Modified Grey Wolf Optimizer

Contact Info

Product

Resources

About