Classification Assisted Tracking for Autonomous Driving Domain

Haag, Stefan; Duraisamy, Bharanidhar; Koch, Wolfgang; Dickmann, Jürgen

doi:10.1109/sdf.2018.8547138

Cited by 11 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work in [16], provides the combination of radar measurements with deep neural network output using an inventive extended objects monitoring (EOM) strategy built on the hidden Markov models and random matrix model. With the aid of fusion methodology, high clutter-rated extended tracking in environments is shown to be possible.…”

Section: A Associationmentioning

confidence: 99%

See 1 more Smart Citation

Resource-Optimized Vehicular Edge Networks With Fairness Constraints

Rashid,

Khan,

Khan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Intelligent transportation systems (ITSs) have witnessed a rising interest from researchers because of their promising features. These features include lane change assistance, infotainment, and collision avoidance, among others. To effectively operate ITSs for these functions, there is a need for edge computing. One can install edge computing servers at the roadside units (RSUs). There must be seamless communication between the edge servers and the cars. Additionally, there will be some cars that experience higher delays and thus, are not preferable because they will highly degrade the performance. Therefore, in this work, we consider a vehicular network scenario and define a cost function that takes into account the latency that is determined by the car's computing frequency, association, and resource allocation while considering fairness constraints. Our cost function is to minimize the total latency (i.e., both local computing latency and transmission latency). The cost of the optimization problem is minimized by optimizing the car's local frequency allocation, resource allocation, and association. The problem is separable, therefore, we first compute the local frequencies of the cars using a convex optimizer. Then, due to the NP-hard nature of the remaining formulated problem (i.e., joint association and resource allocation), we decompose the main problem into two sub-problems: (a) resource allocation and (b) association. Then, we propose an iterative solution. Finally, we provide numerical results for validating the proposed solution.

show abstract

Section: A Associationmentioning

confidence: 99%

“…Different from the existing works [10]- [16], [18], [20]- [24], our work considers cost optimization issue in cars with fairness constraints. The cost takes into account the transmission latency and local computing latency that is minimized by optimizing local devices operating frequencies, resource allocation, and association.…”

Section: B Resource Allocationmentioning

confidence: 99%

Resource-Optimized Vehicular Edge Networks With Fairness Constraints

Rashid,

Khan,

Khan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Considering the filtering algorithm, the probabilistic methods can be distributed between the Kalman filter (KF) and the particle filter (PF). Popular techniques include the Probability Data Association Filter (PDAF) [33], Global Nearest Neighbor (GNN) [34], Probability Hypothesis Density (PHD) filter [35], etc. The hierarchical methods do not require the filter to provide state and covariance estimations as with KF or PF.…”

Section: Data Processing Modulementioning

confidence: 99%

Analysis of Perception Accuracy of Roadside Millimeter-Wave Radar for Traffic Risk Assessment and Early Warning Systems

Zhao

Ding

et al. 2023

IJERPH

View full text Add to dashboard Cite

Millimeter-wave (MMW) radar is essential in roadside traffic perception scenarios and traffic safety control. For traffic risk assessment and early warning systems, MMW radar provides real-time position and velocity measurements as a crucial source of dynamic risk information. However, due to MMW radar’s measuring principle and hardware limitations, vehicle positioning errors are unavoidable, potentially causing misperception of the vehicle motion and interaction behavior. This paper analyzes the factors influencing the MMW radar positioning accuracy that are of major concern in the application of transportation systems. An analysis of the radar measuring principle and the distributions of the radar point cloud on the vehicle body under different scenarios are provided to determine the causes of the positioning error. Qualitative analyses of the radar positioning accuracy regarding radar installation height, radar sampling frequency, vehicle location, posture, and size are performed. The analyses are verified through simulated experiments. Based on the results, a general guideline for radar data processing in traffic risk assessment and early warning systems is proposed.

show abstract

“…However, static maps cannot handle dynamic obstacles common to autonomous driving, such as traffic and pedestrians. One possible approach to integrate dynamic object tracking is to use a combination of clustering and hand-crafted filtering algorithms such as Extended Object Tracking (EOT) [1], where each object is explicitly instantiated. While these systems are effective, they are not flexible in size and shape of the tracked objects, meaning they do not generalize sufficiently and have numerous complex edge cases.…”

Section: Introductionmentioning

confidence: 99%

UNIFY: Multi-Belief Bayesian Grid Framework based on Automotive Radar

Haag,

Duraisamy,

Pfrommer

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Grid maps are widely established for the representation of static objects in robotics and automotive applications. Though, incorporating velocity information is still widely examined because of the increased complexity of dynamic grids concerning both velocity measurement models for radar sensors and the representation of velocity in a grid framework. In this paper, both issues are addressed: sensor models and an efficient grid framework, which are required to ensure efficient and robust environment perception with radar. To that, we introduce new inverse radar sensor models covering radar sensor artifacts such as measurement ambiguities to integrate automotive radar sensors for improved velocity estimation.Furthermore, we introduce UNIFY, a multiple belief Bayesian grid map framework for static occupancy and velocity estimation with independent layers. The proposed UNIFY framework utilizes a grid-cell-based layer to provide occupancy information and a particle-based velocity layer for motion state estimation in an autonomous vehicle's environment. Each UNIFY layer allows individual execution as well as simultaneous execution of both layers for optimal adaption to varying environments in autonomous driving applications.UNIFY was tested and evaluated in terms of plausibility and efficiency on a large real-world radar data-set in challenging traffic scenarios covering different densities in urban and rural sceneries.

show abstract

Classification Assisted Tracking for Autonomous Driving Domain

Cited by 11 publications

References 11 publications

Resource-Optimized Vehicular Edge Networks With Fairness Constraints

Resource-Optimized Vehicular Edge Networks With Fairness Constraints

Analysis of Perception Accuracy of Roadside Millimeter-Wave Radar for Traffic Risk Assessment and Early Warning Systems

UNIFY: Multi-Belief Bayesian Grid Framework based on Automotive Radar

Contact Info

Product

Resources

About