SLAM with SC-PHD Filters: An Underwater Vehicle Application

Lee, Chee Sing; Nagappa, Sharad; Palomeras, Narcís; Clark, Dan E.; Salví, Joaquím

doi:10.1109/mra.2014.2310132

Cited by 16 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a simple and fast multi-object Bayes (sub-optimal) filter, whose computational complexity grows (only) linearly with the number of objects, the PHD filter has quickly become very popular among researchers. This resulted in numerous practical applications, such as passive radar [39], sonar [40], computer vision [41], traffic monitoring and road mapping [42,43], robotic navigation and mapping [45,46], cell microscopy [47], to name a few.…”

Section: Phd Particle Filtersmentioning

confidence: 99%

“…Here ν b is the expected number of object births between time k − 1 and k (a design parameter, typically small, e.g. 0.1) and b k−1 (x|Z k−1 ) is the birth density (46). Upon receiving the measurement set Z k at time k, the update step of the PHD filter is computed according to:…”

Section: Formulation Of the Phd Filtermentioning

confidence: 99%

“…linear/Gaussian target tracking), then one can effectively apply a Rao-Blackwellised formulation. This is the essence of the algorithms proposed for: tracking groups of targets [57], tracking an extended target [58] and simultaneous localisation and mapping (SLAM) [44,46,59].…”

Section: Calibration Of Tracking Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

An overview of particle methods for random finite set models

2016

View full text Add to dashboard Cite

This overview paper describes the particle methods developed for the implementation of the a class of Bayes filters formulated using the random finite set formalism. It is primarily intended for the readership already familiar with the particle methods in the context of the standard Bayes filter. The focus in on the Bernoulli particle filter, the probability hypothesis density (PHD) particle filter and the generalised labelled multi-Bernoulli (GLMB) particle filter. The performance of the described filters is demonstrated in the context of bearings-only target tracking application.

show abstract

Section: Phd Particle Filtersmentioning

confidence: 99%

Section: Formulation Of the Phd Filtermentioning

confidence: 99%

See 1 more Smart Citation

An overview of particle methods for random finite set models

2016

View full text Add to dashboard Cite

show abstract

“…Further, a visual saliency method was implemented to detect the ships. Lee et al presented a single cluster probability hypothesis density filter method for visual SLAM, which lays the foundation for the tracking tasks of AUVs [8]. On the other hand, tracking without mapping is simple and efficient, which provides additional convenience for known environments.…”

Section: Introductionmentioning

confidence: 99%

Embedded Vision-Guided 3-D Tracking Control for Robotic Fish

Sun

et al. 2016

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

Abstract-Visual tracking of free-swimming robotic fish remains a great challenge by considering imaging qualities in aquatic environments. In this paper, we propose a visual identification and positioning method to obtain accurate position for 3-D tracking control comprising depth control and directional control. Specifically, a depth control method based on fuzzy sliding-mode control is put forward to make the robotic fish swim to the preferred target depth and remain at that depth. A directional control method with multiple stages is proposed, and a series of control strategies is developed to integrate agile locomotion and control accuracy. Experiments on depth control and 3-D tracking control are finally conducted in an indoor pool. The latest results obtained indicate that the proposed algorithms are effective and feasible, which lays a solid foundation for complex underwater task execution.Index Terms-Motion control, robotic fish, threedimensional tracking control, visual identification and positioning.

show abstract

“…This paper applies a recently developed method for unified camera calibration and multi-target tracking and triangulation 1 for smart phone cameras based on a disparity space parameterisation 2-4 and a doubly-stochastic PHD filter. 5,6 The uniqueness of the procedure is the use of non-industrial grade cameras such as smart phones, portable web-cams etc as opposed to expensive industrial cameras. Moving object detection and tracking are the essential steps in object recognition, context analysis, indexing processes for visual surveillance systems, traffic monitoring and many other purposes.…”

Section: Introductionmentioning

confidence: 99%

Calibration of asynchronous smart phone cameras from moving objects

Hagen

Istenič

Bharti

et al. 2015

Twelfth International Conference on Quality Control by Artificial Vision 2015

View full text Add to dashboard Cite

Calibrating multiple cameras is a fundamental prerequisite for many Computer Vision applications. Typically this involves using a pair of identical synchronized industrial or high-end consumer cameras. This paper considers an application on a pair of low-cost portable cameras with different parameters that are found in smart phones. This paper addresses the issues of acquisition, detection of moving objects, dynamic camera registration and tracking of arbitrary number of targets. The acquisition of data is performed using two standard smart phone cameras and later processed using detections of moving objects in the scene. The registration of cameras onto the same world reference frame is performed using a recently developed method for camera calibration using a disparity space parameterisation and the the single-cluster PHD filter.

show abstract

SLAM with SC-PHD Filters: An Underwater Vehicle Application

Cited by 16 publications

References 12 publications

An overview of particle methods for random finite set models

An overview of particle methods for random finite set models

Embedded Vision-Guided 3-D Tracking Control for Robotic Fish

Calibration of asynchronous smart phone cameras from moving objects

Contact Info

Product

Resources

About