Visual target tracking in occlusion condition: A GM-PHD-based approach

Yazdian-Dehkordi, Mahdi; Rojhani, Omid Reza; Azimifar, Zohreh

doi:10.1109/aisp.2012.6313805

Cited by 6 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous papers aim to overcome the limitations of the PHD filter. An approach is to introduce state dependent detection probabilities as reported in [23], [24], [25], [26]. In [27] state-dependent survival probability is considered in a scenario with low detectability.…”

Section: A Related Workmentioning

confidence: 99%

GM-PHD Filter Based Sensor Data Fusion for Automotive Frontal Perception System

Lindenmaier

Aradi

Bécsi

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Advanced driver assistance systems and highly automated driving functions require an enhanced frontal perception system. The requirements of a frontal environment perception system cannot be satisfied by either of the existing automotive sensors. A commonly used sensor cluster for these functions consists of a mono-vision smart camera and automotive radar. The sensor fusion is intended to combine the data of these sensors to perform a robust environment perception. Multi-object tracking algorithms have a suitable software architecture for sensor data fusion. Several multi-object tracking algorithms, such as JPDAF or MHT, have good tracking performance; however, the computational requirements of these algorithms are significant according to their combinatorial complexity. The GM-PHD filter is a straightforward algorithm with favorable runtime characteristics that can track an unknown and time-varying number of objects. However, the conventional GM-PHD filter has a poor performance in object cardinality estimation. This paper proposes a method that extends the GM-PHD filter with an object birth model that relies on the sensor detections and a robust object extraction module, including Bayesian estimation of objects' existence probability to compensate for drawbacks of the conventional algorithm.

show abstract

Section: A Related Workmentioning

confidence: 99%

GM-PHD Filter Based Sensor Data Fusion for Automotive Frontal Perception System

Lindenmaier

Aradi

Bécsi

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…In [9], a dynamic detection probability method is introduced into the GM-PHD filter, which is used to compute the detection probability of individual targets. However, the size of each target must be known as prior, and the size of all targets must be same.…”

Section: Introductionmentioning

confidence: 99%

Improved Gaussian Mixture Probability Hypothesis Density for Tracking Closely Spaced Targets

Zhang

Yang

2017

International Journal of Electronics and Telecommunications

View full text Add to dashboard Cite

Abstract-Probability hypothesis density (PHD) filter is a suboptimal Bayesian multi-target filter based on random finite set. The Gaussian mixture PHD filter is an analytic solution to the PHD filter for linear Gaussian multi-target models. However, when targets move near each other, the GM-PHD filter cannot correctly estimate the number of targets and their states. To solve the problem, a novel reweighting scheme for closely spaced targets is proposed under the framework of the GM-PHD filter, which can be able to correctly redistribute the weights of closely spaced targets, and effectively improve the multiple target state estimation precision. Simulation results demonstrate that the proposed algorithm can accurately estimate the number of targets and their states, and effectively improve the performance of multi-target tracking algorithm.

show abstract

“…In recent years, the GM‐PHD filter has been widely applied to various fields such as tracking visual targets [13–15], Doppler‐only targets [16, 17], radar targets [18, 19] and extended targets [20, 21]. Tracking of multi‐sensor multi‐target based on the GM‐PHD filter is also studied in [22] and tracking of manoeuvring targets using this filter is considered in [23, 24].…”

Section: Introductionmentioning

confidence: 99%

Novel N ‐scan GM‐PHD‐based approach for multi‐target tracking

Yazdian-Dehkordi

Azimifar

2016

IET signal process.

View full text Add to dashboard Cite

The GM-PHD-based filter has been proposed as an alternative of the PHD filter to estimate the first-order moment of the multi-target posterior density. The GM-PHD filter utilises a weighted summation of Gaussian components to estimate the target states. This filter and its recent variants perform state extraction of the targets based on the target weights. However, due to different uncertainties such as noisy observation, miss-detection, clutter or occlusion, the weight of a target is decreased and the estimation of the target is lost in some steps. In this study, the authors develop a simple and effective N-scan approach which employs the weight history of targets to improve the performance of the GM-PHD-based methods. They propose to assign a label, a weight history and a binary confidence indicator to each Gaussian component and propagate them in time. Then, they explain a novel N-scan state extraction algorithm to estimate the target states based on their histories in the N last steps. To study the efficiency of the proposed N-scan approach, it is applied on the GM-PHD filter as well as its several recent variants. The experimental results provided for various uncertainties show the effectiveness of the method.

show abstract

Visual target tracking in occlusion condition: A GM-PHD-based approach

Cited by 6 publications

References 8 publications

GM-PHD Filter Based Sensor Data Fusion for Automotive Frontal Perception System

GM-PHD Filter Based Sensor Data Fusion for Automotive Frontal Perception System

Improved Gaussian Mixture Probability Hypothesis Density for Tracking Closely Spaced Targets

Novel N ‐scan GM‐PHD‐based approach for multi‐target tracking

Contact Info

Product

Resources

About