A Bayesian Framework for Intent Prediction in Object Tracking

Ahmad, Bashar I.; Langdon, Patrick; Godsill, Simon

doi:10.1109/icassp.2019.8682603

Cited by 5 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reach full automation, there have been several advances into realising sufficiently connected vehicles [86][87][88][89], which is key to the success of autonomous driving as well as enhancing transportation efficiency and safety. This includes the connection between vehicles, and vehicle-to-cloud communications, imposing new requirements on in-vehicle systems and the supporting infrastructure [90][91][92].…”

Section: Figure 14mentioning

confidence: 99%

6G Opportunities Arising from Internet of Things Use Cases: A Review Paper

et al. 2021

Self Cite

View full text Add to dashboard Cite

The race for the 6th generation of wireless networks (6G) has begun. Researchers around the world have started to explore the best solutions for the challenges that the previous generations have experienced. To provide the readers with a clear map of the current developments, several review papers shared their vision and critically evaluated the state of the art. However, most of the work is based on general observations and the big picture vision, and lack the practical implementation challenges of the Internet of Things (IoT) use cases. This paper takes a novel approach in the review, as we present a sample of IoT use cases that are representative of a wide variety of its implementations. The chosen use cases are from the most research-active sectors that can benefit from 6G and its enabling technologies. These sectors are healthcare, smart grid, transport, and Industry 4.0. Additionally, we identified some of the practical challenges and the lessons learned in the implementation of these use cases. The review highlights the cases’ main requirements and how they overlap with the key drivers for the future generation of wireless networks.

show abstract

Section: Figure 14mentioning

confidence: 99%

6G Opportunities Arising from Internet of Things Use Cases: A Review Paper

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Bayesian framework for intent prediction presented in this article was introduced in Ahmad et al (2016b) and Ahmad et al (2018) for predictive touch and other applications; see Ahmad et al (2019b) for a short overview. It treats the problem within an object tracking formulation, albeit not necessarily seeking state estimation, such that the influence of intended destination is captured by utilizing suitable stochastic motion model with a few unknown parameters.…”

Section: Related Work and Contributionsmentioning

confidence: 99%

Modeling intent and destination prediction within a Bayesian framework: Predictive touch as a usecase

Gan

Liang

Ahmad

et al. 2020

DCE

Self Cite

View full text Add to dashboard Cite

In various scenarios, the motion of a tracked object, for example, a pointing apparatus, pedestrian, animal, vehicle, and others, is driven by achieving a premeditated goal such as reaching a destination. This is albeit the various possible trajectories to this endpoint. This paper presents a generic Bayesian framework that utilizes stochastic models that can capture the influence of intent (viz., destination) on the object behavior. It leads to simple algorithms to infer, as early as possible, the intended endpoint from noisy sensory observations, with relatively low computational and training data requirements. This framework is introduced in the context of the novel predictive touch technology for intelligent user interfaces and touchless interactions. It can determine, early in the interaction task or pointing gesture, the interface item the user intends to select on the display (e.g., touchscreen) and accordingly simplify as well as expedite the selection task. This is shown to significantly improve the usability of displays in vehicles, especially under the influence of perturbations due to road and driving conditions, and enable intuitive contact-free interactions. Data collected in instrumented vehicles are shown to demonstrate the effectiveness of the proposed intent prediction approach.

show abstract

“…Whilst the bridging distributions (BD) approach was introduced in [12], [13], a concise overview of its key results, including schemes for estimating future state and arrival time, was presented in [14]. BD in [12], [13], [14] captures the influence of endpoint D i on the object motion by prescribing that the motion model in (1) has a terminal state x K at arrival time…”

Section: B Related Work and Contributionsmentioning

confidence: 99%

“…In this paper, we introduce a different approach to [12], [13], [14] in which the destination point is considered to be a 'pseudo-observation' rather than a terminal state x K of the system. Consequently, the mathematics of the dynamical model and observation process are made consistent with the Markov state process, in contrast with [12], [13], [14]. This new interpretation leads to two new destination prediction algorithms that can substantially reduce the computational complexity of the inference routine for all Gaussian LTI motion models in (1), e.g.…”

Section: B Related Work and Contributionsmentioning

confidence: 99%

“…The proposed approach not only resolves the consistency issue with the previous bridging distributions construct, but also it can substantially reduce the computational complexity of predicting the target destination. Similar to BD in [12], [13], [14], it however requires prior knowledge of the location of all nominal endpoints, considers Gaussian linear set-ups and treats targets singly, even if they are a group. These can be addressed by extending the BD framework in future work.…”

Section: Conclusion and Final Remarksmentioning

confidence: 99%

See 1 more Smart Citation

On Destination Prediction Based on Markov Bridging Distributions

Liang

Ahmad

Gan

et al. 2019

IEEE Signal Process. Lett.

Self Cite

View full text Add to dashboard Cite

This letter presents an alternative, more consistent, construction for bridging distributions, which enables inferring the destination of a tracked object from the available partial sensory observations. Two algorithms are then introduced to sequentially estimate the probability of all possible endpoints within a generic Bayesian framework. They capture the influence of intended destination on the object's motion via suitably adapted stochastic models. Whilst the bridging approach has low training requirements, the proposed formulation can lead to more efficient predictors, e.g. around 65% less computations for certain models. Synthetic and real data is used to illustrate the effectiveness of the introduced algorithms.

show abstract

A Bayesian Framework for Intent Prediction in Object Tracking

Cited by 5 publications

References 18 publications

6G Opportunities Arising from Internet of Things Use Cases: A Review Paper

6G Opportunities Arising from Internet of Things Use Cases: A Review Paper

Modeling intent and destination prediction within a Bayesian framework: Predictive touch as a usecase

On Destination Prediction Based on Markov Bridging Distributions

Contact Info

Product

Resources

About