A Time-Delay Control Approach for a Stereo Vision Based Human-Machine Interaction System

Macesanu, Gigel; Comnac, V.; Moldoveanu, Florica; Grigorescu, Sorin Mihai

doi:10.1007/s10846-013-9994-4

Cited by 11 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the analysis of the image processing step is limited to a measurement or estimate of the computational delay and is assumed to be negligible compared to other delays in the control loop [2][3] [20]. Control engineers tackle a long sample period of IBC systems using state estimation [12], robust design [13], predictive control [14], observer-based [1], multi-rate sampling [26] and reconfigurable pipelining methods [15]. However, these approaches do not model and consider platform constraints like resource availability and mapping, and/or workload variations in image processing [1].…”

Section: Related Workmentioning

confidence: 99%

Optimising Quality-of-Control for Data-Intensive Multiprocessor Image-Based Control Systems Considering Workload Variations

Mohamed¹,

Zhu²,

Goswami³

et al. 2018

2018 21st Euromicro Conference on Digital System Design (DSD)

View full text Add to dashboard Cite

Image-Based Control (IBC) systems have a long sample period. Sensing in these systems consists of computeintensive image processing algorithms whose response times are dependent on image workload. IBC systems are typically designed for the worst-case workload that results in a long sample period and hence suboptimal quality-of-control (QoC). This worst-case based design is further considered for mapping of controller tasks and allocating platform resources, resulting in significant resource over-provisioning. Our design philosophy is to sample as fast as possible to optimise QoC for a given platform allocation, and for this, we present a structured design flow. Workload variations determine how fast we can sample and we model this dynamic behaviour using the concept of workload scenarios. Our choice of scenario-aware dataflow as the formal model for our application enables us to: i) model dynamic behaviour, analyse timing, and optimally map application tasks to the platform for maximising the effective utilisation of allocated resources, ii) relate throughput of the dataflow graph to the sample period, and thus combine dataflow analysis and mapping with control design parameters and QoC to identify system scenarios, and iii) to efficiently implement a run-time mechanism that manages necessary dynamic reconfiguration between system scenarios. Our results show that our design approach outperforms the worst-case based design with respect to optimising QoC and maximising effective resource utilisation.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimising Quality-of-Control for Data-Intensive Multiprocessor Image-Based Control Systems Considering Workload Variations

Mohamed¹,

Zhu²,

Goswami³

et al. 2018

2018 21st Euromicro Conference on Digital System Design (DSD)

View full text Add to dashboard Cite

show abstract

“…Mouth extremities are extracted using the method proposed in [31]. Nose tip detection is based on the same algorithm but completed with additional stages, as described in [32]. Eye extremities and iris detection are performed using Haar classifiers and the method presented in [32].…”

Section: Feature Detectionmentioning

confidence: 99%

“…Nose tip detection is based on the same algorithm but completed with additional stages, as described in [32]. Eye extremities and iris detection are performed using Haar classifiers and the method presented in [32]. Inside a reasonable ROI, chosen according to the rough head pose detection result, a Haar classifier is applied to establish an overall ROI for the eye.…”

Section: Feature Detectionmentioning

confidence: 99%

“…This library is a powerful programming tool for low-to-medium complexity models, and also allows for easy design, prototyping and testing of high complexity models, such as the framework presented in this paper. Currently, these models are running in real-time using a GPU-based massively parallel solution described in [33].…”

Section: Probabilistic Inference Implementation and Random Variable Smentioning

confidence: 99%

See 1 more Smart Citation

A Bayesian hierarchy for robust gaze estimation in human–robot interaction

Lanillos

Ferreira

Dias

2017

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

In this text, we will present a probabilistic solution for robust gaze estimation in the context of human-robot interaction. Gaze estimation, in the sense of continuously assessing gaze direction of an interlocutor so as to determine his/her focus of visual attention, is important in several important computer vision applications, such as the development of non-intrusive gaze-tracking equipment for psychophysical experiments in neuroscience, specialised telecommunication devices, video surveillance, human-computer interfaces (HCI) and artificial cognitive systems for human-robot interaction (HRI), our application of interest. We have developed a robust solution based on a probabilistic approach that inherently deals with the uncertainty of sensor models, but also and in particular with uncertainty arising from distance, incomplete data and scene dynamics. This solution comprises a hierarchical formulation in the form of a mixture model that loosely follows how geometrical cues provided by facial features are believed to be used by the human perceptual system for gaze estimation. A quantitative analysis of the proposed framework's performance was undertaken through a thorough set of experimental sessions. Results show that the framework performs according to the difficult requirements of HRI applications, namely by exhibiting correctness, robustness and adaptiveness.

show abstract

“…This is essential for many engineering tasks and is especially true of systems that cannot afford to have feedback time delays or systems with nontrivial time delays. One example is vision-based system, in which [10] indicated significant presence of dead time affecting robustness and stability of the system. Thus, Hermite-Biehler feedback controller was designed to work for restricted delay margin, which was obtained from stability analysis.…”

Section: Introductionmentioning

confidence: 99%

Echo state networks with Tikhonov regularization: optimization using integral gain

2015

View full text Add to dashboard Cite

This study proposes feed-forward echo state networks (ESN) as an estimator, and couples it with second-order proportional-integral-derivative (PID) feedback extension to compensate for dead time in feedback systems. The system is tested for two-dimensional space motion patterns recognition and prediction using simulations, which allows control of noise input. Tikhonov regularization is employed for training readouts and second-order PID feedback minimizes prediction bias. Evaluation is done using mean squared error and the coupled system performs well compared to any of its standalone versions. The results suggest it is feasible to (1) 'compress' the memory capacity of the system, and (2) reduce the number optimization parameters, while maintaining the estimation performance and following the excitation property of the estimator. It is feasible to optimize the ESN using feedback gain although it plays a significant role in the proposed system because the improvement by bias correction is far greater than that of optimization; thus, simplifying the estimation to a feedback problem which is easily tuned using the Ziegler-Nichols method.

show abstract

A Time-Delay Control Approach for a Stereo Vision Based Human-Machine Interaction System

Cited by 11 publications

References 28 publications

Optimising Quality-of-Control for Data-Intensive Multiprocessor Image-Based Control Systems Considering Workload Variations

Optimising Quality-of-Control for Data-Intensive Multiprocessor Image-Based Control Systems Considering Workload Variations

A Bayesian hierarchy for robust gaze estimation in human–robot interaction

Echo state networks with Tikhonov regularization: optimization using integral gain

Contact Info

Product

Resources

About