3D information retrieval for visual odometry system of planetary exploration rovers - A stereo vision approach

Chitra, K.; Dinesh, Sudin; Mishra, Deepak; Brinda, V.; Lalithambika, V.R.; Kumar, B.

doi:10.1109/icacci.2013.6637197

Cited by 5 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step3, as illustrated above, ( ) ρ ρ ρ p x y , T can be determined by using equations (1) and (2). Then the ray ρ → r constituted by ρ p and ρ O C can be determined uniquely.…”

Section: Bpp-based Calibration Methods Of a Stereo Rigmentioning

confidence: 99%

See 1 more Smart Citation

Calibration of stereo rigs based on the backward projection process

Gu¹,

Zhao²,

Ma³

et al. 2016

Meas. Sci. Technol.

View full text Add to dashboard Cite

High-accuracy 3D measurement based on binocular vision system is heavily dependent on the accurate calibration of two rigidly-fixed cameras. In most traditional calibration methods, stereo parameters are iteratively optimized through the forward imaging process (FIP). However, the results can only guarantee the minimal 2D pixel errors, but not the minimal 3D reconstruction errors. To address this problem, a simple method to calibrate a stereo rig based on the backward projection process (BPP) is proposed. The position of a spatial point can be determined separately from each camera by planar constraints provided by the planar pattern target. Then combined with pre-defined spatial points, intrinsic and extrinsic parameters of the stereo-rig can be optimized by minimizing the total 3D errors of both left and right cameras. An extensive performance study for the method in the presence of image noise and lens distortions is implemented. Experiments conducted on synthetic and real data demonstrate the accuracy and robustness of the proposed method.

show abstract

“…Step3, as illustrated above, ( ) ρ ρ ρ p x y , T can be determined by using equations (1) and (2). Then the ray ρ → r constituted by ρ p and ρ O C can be determined uniquely.…”

Section: Bpp-based Calibration Methods Of a Stereo Rigmentioning

confidence: 99%

“…3D measurement based on the binocular vision system is an effective method in shape metrology, non-contact detecting, visual odometry [1,2] and so on. High-accuracy binocular vision measurement is heavily dependent on the accurate calibration of the rigidly-fixed stereo rig.…”

Section: Introductionmentioning

confidence: 99%

Calibration of stereo rigs based on the backward projection process

Gu¹,

Zhao²,

Ma³

et al. 2016

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In this section, we primarily review related works that have investigated view-based techniques for stereo object retrieval. [15][16][17][18] In view-based stereo-model retrieval, features are extracted from 2D images. Visual similarities between the different view images from different models are compared with each other to measure the difference of the models.…”

Section: Related Workmentioning

confidence: 99%

A novel stereo-model retrieval method in manufacturing

Chen

Zhang

Lin

et al. 2015

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

With the development of computer vision technologies, manufacturing is now using stereo models for production, and the amount of stereo models generated recently has increased significantly. Thus, a fast and reliable model retrieval algorithm has become important. In this article, we propose a novel view-based stereo-model retrieval algorithm using a modified principal component analysis algorithm. Unlike a traditional principal component analysis that uses the origin of a two-dimensional image, we apply principal component analysis to extract eigenvectors for each stereo model. First, we extract a set of two-dimensional images from different directions of the stereo object. Because each two-dimensional image can be seen as one sample of the stereo object, we utilize principal component analysis to extract the eigenvectors as a dictionary for each stereo object. Then, those eigenvectors are used to rebuild the query. Finally, the reconstruction residual is applied to represent the similarity between the query and the candidate stereo object. Experimentally, the proposed retrieval algorithm has been evaluated using the ETH-80 and ALOI datasets. Experimental results and comparisons with other methods show the effectiveness of the proposed approach that can be used in engineering manufacturing and computer-aided design applications.

show abstract

“…These characteristics match to most of guiding systems of machine vision. For decades, the machine vision has been used for guiding many robotic system to desirable operating positions [10,11]. Therefore, integrating a guiding system of the machine vision to a 3D printer is an attractive solution of conveniently and affordably implementing the 3D printing for fabricating any product at any position constrained to any physical reference.…”

Section: Motivationmentioning

confidence: 99%

“…In addition, necessary instruments for the machine vision are relatively low-cost and compact [9,23,24]. The machine vision consequently has been a widely used solution of guiding robotic systems to desirable operating positions for decades [10,11].…”

Section: Guiding Robotic Systems To Desirable Operating Positionsmentioning

confidence: 99%

Machine vision integrated three-dimensional printing system

Sithiwichankit

View full text Add to dashboard Cite

Three-dimensional�printing has been a widespread solution of fabricating geometrical customized products. Any 3D printed product is normally�fabricated at a position defined with respect to the coordinate system of the corresponding 3D printer. So, the 3D printing cannot be conveniently implemented in�some fabricating applications in which�fabricating positions are commonly constrained to some physical references, e.g., architecture construction, surface restoration, food decoration, etc.�This research aimed to integrate the 3D printing with machine vision, which is vastly used for guiding robotic systems to operate at desirable positions constrained to physical objects. Hence, the 3D printing can be conveniently and affordably implemented at any position constrained to any physical reference. The proposed machine vision integrated 3D printing system comprises a 3D printer, which is originally constructed in this research, a commercial�web camera, and a commercial computer. The web camera was equipped to the printhead of the 3D printer, and necessary computer programs were developed. Then, evaluating products were�fabricated on evaluating physical reference, in order to evaluate the machine vision integrated 3D printing system. From the successfully fabricated results of the evaluating products, the machine vision integrated 3D printing system gives promise of�conveniently, affordably, and accurately, implementing the 3D printing in the mentioned applications.

show abstract

3D information retrieval for visual odometry system of planetary exploration rovers - A stereo vision approach

Cited by 5 publications

References 13 publications

Calibration of stereo rigs based on the backward projection process

Calibration of stereo rigs based on the backward projection process

A novel stereo-model retrieval method in manufacturing

Machine vision integrated three-dimensional printing system

Contact Info

Product

Resources

About