A robot visual servo-based approach to the determination of next best views

Zhang, Lei; Zuo, Junqiu; Yao, Xingtian; Zhang, Xingguo; Shuai, Liguo

doi:10.1109/icma.2015.7237906

Cited by 5 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer function is obtained by using Omron K40030H servomotor's specifications. (10) PSO is used as an algorithm that will provide K p , K i and K d values using the optimal output, thus creating the desired values.…”

Section: Control Designmentioning

confidence: 99%

AC Servo Motor Speed and Position Control Using Particle Swarm Optimization (PSO)

et al. 2015

View full text Add to dashboard Cite

W ithout specific design and application difficulties, servomotors, which are regarded as sequenced systems, are preferred in non-linear and dynamic working conditions [1-10]. AC servomotors are also widely used in various control applications such as: numerical control, precise robot applications, and CNC machinery [11-14]. Along with its electrical and mechanical dynamics, one of the most important reasons these motors are so popular is their high efficiency. Ac servomotors need an accurate feedback response for the reference position. The feedback signals are important for servomotor to quickly respond to on-off operations and to maintain its steady state in sudden load changes. In automation applications, where feedback signals are used, such as speed, position and torque, even if a mathematical model is correctly constructed, using this mathematical model may cause complex problems and higher costs. Therefore, implementation of some control algorithms to uncertain, inaccurate, not well defined time-variable and complex systems may be impossible. Some of the leading problems of the complex systems are as follows: non-linearity of system, unknown mathematical model, difficulties in

show abstract

Section: Control Designmentioning

confidence: 99%

AC Servo Motor Speed and Position Control Using Particle Swarm Optimization (PSO)

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Therefore, in order to completely digitise the 3D objects, several range datasets from different vantage points are necessary using a pre-specified set of decision rules or heuristics that will produce a large amount of unknown 3D information. This problem is defined as the view planning problem and has been widely studied in the literatures [1][2][3][4]. The next-best-view (NBV) planning method can be seen as a sequential approach to build 3D object model using all the previously obtained range data.…”

mentioning

confidence: 99%

“…The next-best-view (NBV) planning method can be seen as a sequential approach to build 3D object model using all the previously obtained range data. In the literature, generally the NBV planning method for 3D modelling of unknown objects has been described [1][2][3][4]; however, a complete 3D modelling of the scene (i.e. terrain) comprised of multiple objects is a challenging task.…”

mentioning

confidence: 99%

View planning method for complete 3D digitisation of the scene

2018

View full text Add to dashboard Cite

The problem of where to position the range sensor next for generating a completely seamless integration of a targeted surface from multiple range datasets acquired at different spatial poses is one of the challenging tasks in machine vision. A new view planning method is proposed for complete reconstruction of the real scene from the minimum number of range datasets. The generated surface model covers approximately all major attributes of the scene with minimal a priori knowledge about its geometry. Finally, the experimental results show the effectiveness of the proposed method.

show abstract

“…[1][2][3][4][5] Nowadays, there are two main types of image information used to determine next best view, intensity information, [6][7][8] and depth information. [9][10][11][12][13][14][15] The methods based on intensity information are relatively fewer than the methods based on depth information. Compared with 2D intensity image, it is easier to obtain the 3D information of scene from 2.5D depth image; therefore, the existing next best view methods are usually achieved using depth image.…”

Section: Introductionmentioning

confidence: 99%

“…14 proposed a method based on the contour information of visual object to determine next best view. Zhang et al 15 proposed a method based on visual servo to determine next best view. But methods in the literature [13][14][15] all depend on specific equipment.…”

Section: Introductionmentioning

confidence: 99%

Determining next best view based on occlusion information in a single depth image of visual object

Zhang

Miao

et al. 2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

How to determine the camera's next best view is a challenging problem in vision field. A next best view approach is proposed based on occlusion information in a single depth image. First, the occlusion detection is accomplished for the depth image of visual object in current view to obtain the occlusion boundary and the nether adjacent boundary. Second, the external surface of occluded region is constructed and modeled according to the occlusion boundary and the nether adjacent boundary. Third, the observation direction, observation center point, and area information of external surface of occluded region are solved. And then, the set of candidate observation directions and the visual space of each candidate direction are determined. Finally, the next best view is achieved by solving the next best observation direction and camera's observation position. The proposed approach does not need the prior knowledge of visual object or limit the camera position on a specially appointed surface. Experimental results demonstrate that the approach is feasible and effective. KeywordsDepth image, next best view, occlusion information, external surface of occluded region, visual space Date

show abstract

A robot visual servo-based approach to the determination of next best views

Cited by 5 publications

References 11 publications

AC Servo Motor Speed and Position Control Using Particle Swarm Optimization (PSO)

AC Servo Motor Speed and Position Control Using Particle Swarm Optimization (PSO)

View planning method for complete 3D digitisation of the scene

Determining next best view based on occlusion information in a single depth image of visual object

Contact Info

Product

Resources

About