Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEnvironment Modeling Based on Generic Infrastructure Sensor Interfaces Using a Centralized Labeled-Multi-Bernoulli Filter
56
0
0.0
(
0
)
Added by
Martin Herrmann
Publication date
2019
fields
Electronic Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Urban intersections put high demands on fully automated vehicles, in particular, if occlusion occurs. In order to resolve such and support vehicles in unclear situations, a popular approach is the utilization of additional information from infrastructure-based sensing systems. However, a widespread use of such systems is circumvented by their complexity and thus, high costs. Within this paper, a generic interface is proposed, which enables a huge variety of sensors to be connected. The sensors are only required to measure very few features of the objects, if multiple distributed sensors with different viewing directions are available. Furthermore, a Labeled Multi-Bernoulli (LMB) filter is presented, which can not only handle such measurements, but also infers missing object information about the objects extents. The approach is evaluated on simulations and demonstrated on a real-world infrastructure setup.
rate research
Read More
A multiple maneuvering target system can be viewed as a Jump Markov System (JMS) in the sense that the target movement can be modeled using different motion models where the transition between the motion models by a particular target follows a Markov chain probability rule. This paper describes a Generalized Labelled Multi-Bernoulli (GLMB) filter for tracking maneuvering targets whose movement can be modeled via such a JMS. The proposed filter is validated with two linear and nonlinear maneuvering target tracking examples.
This paper provides a scalable, multi-sensor measurement adaptive track initiation technique for labeled random finite set filters. A naive construction of the multi-sensor measurement adaptive birth set leads to an exponential number of newborn components in the number of sensors. A truncation criterion is established for a multi-sensor measurement-generated labeled multi-Bernoulli random finite set that provably minimizes the L1-truncation error in the generalized labeled multi-Bernoulli posterior distribution. This criterion is used to construct a Gibbs sampler that produces a truncated measurement-generated labeled multi-Bernoulli birth distribution with quadratic complexity in the number of sensors. A closed form solution of the conditional sampling distribution assuming linear (or linearized) Gaussian likelihoods is provided, alongside an approximate solution using Monte Carlo importance sampling. Multiple simulation results are provided to verify the efficacy of the truncation criterion, as well as the reduction in complexity.
Natural disasters such as floods and earthquakes immensely impact the telecommunication network infrastructure, leading to the malfunctioning and interruption of wireless services. Consequently, the user devices under the disaster zone are unable to access the cellular base stations. Wireless coverage on an unmanned aerial vehicle (UAV) is considered for providing coverage service to ground user devices in disaster events. This work evaluated the efficient performance of wireless coverage services of UAVs to provide the internet to fly things to help recover the communications link in a natural disaster in multi environments. The results demonstrate the line of sight, nonline of sight, path loss, and coverage probability for the radio propagation environment scenario. Therefore, the path loss and coverage probability are affected by the user devices elevation angle and distance in the multi-environment system. The user positions optimum user device distance and elevation angle are also investigated to improve the coverage probability, which could be especially useful for the UAV deployment design.
We propose a scalable track-before-detect (TBD) tracking method based on a Poisson/multi-Bernoulli model. To limit computational complexity, we approximate the exact multi-Bernoulli mixture posterior probability density function (pdf) by a multi-Bernoulli pdf. Data association based on the sum-product algorithm and recycling of Bernoulli components enable the detection and tracking of low-observable objects with limited computational resources. Our simulation results demonstrate a significantly improved tracking performance compared to a state-of-the-art TBD method.
The generalized labeled multi-Bernoulli (GLMB) is a family of tractable models that alleviates the limitations of the Poisson family in dynamic Bayesian inference of point processes. In this paper, we derive closed form expressions for the void probability functional and the Cauchy-Schwarz divergence for GLMBs. The proposed analytic void probability functional is a necessary and sufficient statistic that uniquely characterizes a GLMB, while the proposed analytic Cauchy-Schwarz divergence provides a tractable measure of similarity between GLMBs. We demonstrate the use of both results on a partially observed Markov decision process for GLMBs, with Cauchy-Schwarz divergence based reward, and void probability constraint.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
