Automatic Sensor Placement for Model-Based Robot Vision

Chen, Shengyong; Li, Youfu

doi:10.1109/tsmcb.2003.817031

Cited by 163 publications

(88 citation statements)

References 38 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Systems used for 3D model reconstruction can be listed into three classes comprises of those which work with active sensor (range-based systems) [14], passive sensors (image-based systems) [15] and those which work with both active and passive sensors [16]. However, range-based systems are more costly than image-based systems.…”

Section: Related Workmentioning

confidence: 99%

Image Based 3D Reconstruction of Texture-less Objects for VR Contents

Hafeez¹,

Lee²,

Kwon³

et al. 2017

International journal of advanced smart convergence

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Image Based 3D Reconstruction of Texture-less Objects for VR Contents

Hafeez¹,

Lee²,

Kwon³

et al. 2017

International journal of advanced smart convergence

View full text Add to dashboard Cite

show abstract

“…[3]; this is true for all reasonable choices of U . Finding the global minimum is a difficult problem, and the prevailing approach in the literature seems to be more or less exhaustive search over a discretized parameter space, [4,7], or stochastic optimization methods, [13,14]. In the interest of speed, however, we adopt a gradient based optimization scheme, using the well-known Levenberg-Marquardt (LM) method.…”

Section: Proposed Algorithmmentioning

confidence: 99%

Optimal View Path Planning for Visual SLAM

Haner

Heyden

2011

Image Analysis

View full text Add to dashboard Cite

Abstract. In experimental design and 3D reconstruction it is desirable to minimize the number of observations required to reach a prescribed estimation accuracy. Many approaches in the literature attempt to find the next best view from which to measure, and iterate this procedure. This paper discusses a continuous optimization method for finding a whole set of future imaging locations which minimize the reconstruction error of observed geometry along with the distance traveled by the camera between these locations. A computationally efficient iterative algorithm targeted toward application within real-time SLAM systems is presented and tested on simulated data.

show abstract

“…These two problems are variations of the measurement selection problem [20], with applications in control engineering [23], structural dynamics [24], and robotics [25], among others. The measurement selection problem is an instance of the set covering problem [26], which is known to be NPcomplete.…”

Section: Formulating the Design Problem For Distributed Diagnosismentioning

confidence: 99%

Designing Distributed Diagnosers for Complex Continuous Systems

Roychoudhury

Biswas

Koutsoukos

2009

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Abstract-Wear and tear from sustained operations cause systems to degrade and develop faults. Online fault diagnosis schemes are necessary to ensure safe operation and avoid catastrophic situations, but centralized diagnosis approaches have large memory and communication requirements, scale poorly, and create single points of failure. To overcome these problems, we propose an online, distributed, model-based diagnosis scheme for isolating abrupt faults in large continuous systems. This paper presents two algorithms for designing the local diagnosers and analyzes their time and space complexity. The first algorithm assumes the subsystem structure is known and constructs a local diagnoser for each subsystem. The second algorithm creates a partition structure and local diagnosers simultaneously. We demonstrate the effectiveness of our approach by applying it to the Advanced Water Recovery System developed at the NASA Johnson Space Center.Note to Practitioners-Fault detection, isolation, and recovery approaches are important for maintaining performance and safety in large safety-critical systems, such as the Advanced Life Support (ALS) System for future long-duration NASA manned missions that we present in this paper. These systems consist of a number of complex, interacting, spatially-distributed subsystems. Centralized model-based diagnosis approaches are expensive in memory and communication requirements, and they create single points of failure. Previous distributed diagnosis approaches apply to discrete event system models, but these approaches become computationally intractable when applied to complex continuous systems. This paper develops a systematic modelbased approach to distributing the diagnosis task by designing multiple diagnosers that operate independently and generate globally correct diagnoses. We present a complete approach that includes a topological modeling scheme for constructing the dynamic system models, algorithms for constructing the distributed diagnosers, and a systematic methodology for deriving efficient subsystem diagnosis using these diagnosers. We then demonstrate the applicability of this approach to the ALS system.

show abstract

Automatic Sensor Placement for Model-Based Robot Vision

Cited by 163 publications

References 38 publications

Image Based 3D Reconstruction of Texture-less Objects for VR Contents

Image Based 3D Reconstruction of Texture-less Objects for VR Contents

Optimal View Path Planning for Visual SLAM

Designing Distributed Diagnosers for Complex Continuous Systems

Contact Info

Product

Resources

About