Search results
1 – 10 of 579Alexandra Pereira Nunes, Ana Rita Silva Gaspar, Andry M. Pinto and Aníbal Castilho Matos
This paper aims to present a mosaicking method for underwater robotic applications, whose result can be provided to other perceptual systems for scene understanding such as…
Abstract
Purpose
This paper aims to present a mosaicking method for underwater robotic applications, whose result can be provided to other perceptual systems for scene understanding such as real-time object recognition.
Design/methodology/approach
This method is called robust and large-scale mosaicking (ROLAMOS) and presents an efficient frame-to-frame motion estimation with outlier removal and consistency checking that maps large visual areas in high resolution. The visual mosaic of the sea-floor is created on-the-fly by a robust registration procedure that composes monocular observations and manages the computational resources. Moreover, the registration process of ROLAMOS aligns the observation to the existing mosaic.
Findings
A comprehensive set of experiments compares the performance of ROLAMOS to other similar approaches, using both data sets (publicly available) and live data obtained by a ROV operating in real scenes. The results demonstrate that ROLAMOS is adequate for mapping of sea-floor scenarios as it provides accurate information from the seabed, which is of extreme importance for autonomous robots surveying the environment that does not rely on specialized computers.
Originality/value
The ROLAMOS is suitable for robotic applications that require an online, robust and effective technique to reconstruct the underwater environment from only visual information.
Details
Keywords
Jianran Lv, Hongyao Shen and Jianzhong Fu
3D printing for objects whose size exceeds the scope of the printer is still a tough challenge in application. The purpose of this paper is to propose a visual stitching…
Abstract
Purpose
3D printing for objects whose size exceeds the scope of the printer is still a tough challenge in application. The purpose of this paper is to propose a visual stitching large-scale (VSLS) 3D-printing method to solve this problem.
Design/methodology/approach
The single segmentation point method and multiple segmentation point method are proposed to adaptively divide each slice of the model into several segments. For each layer, the mobile robot will move to different positions to print each segment, and every time it arrives at the planned location, the contours of the printed segments are captured with a high-definition camera by the feature point recognition algorithm. Then, the coordinate transformation is implemented to adjust the printing codes of the next segment so that each part can be perfectly aligned. The authors print up layer by layer in this manner until the model is complete.
Findings
In Section 3, two specimens, whose sizes are 166 per cent and 252 per cent of the scope of the 3D-printing robot, are successfully printed. Meanwhile, the completed models of the specimens are printed using a suitable traditional printer for comparison. The result shows that the specimens in the test group have basically identical sizes to those in the control group, which verifies the feasibility of the VSLS method.
Originality/value
Unlike most of the current solutions that demand harsh requirement for positioning accuracy of the mobile robots, the authors use a camera to compensate for the lost positioning accuracy of the device during movement, thereby avoiding precise control to the device’s location. And the coordinate transformation is implemented to adjust the printing codes of the next sub-models so that each part can be aligned perfectly.
Details
Keywords
Andreas Koschan, David Page, Jin‐Choon Ng, Mongi Abidi, David Gorsich and Grant Gerhart
The current threats to US security, both military and civilian, have led to an increased interest in the development of technologies to safeguard national facilities such as…
Abstract
The current threats to US security, both military and civilian, have led to an increased interest in the development of technologies to safeguard national facilities such as military bases, federal buildings, nuclear power plants, and national laboratories. As a result, the imaging, robotics, and intelligent systems (IRIS) laboratory at the University of Tennessee has established a research consortium, known as security automation and future electromotive robotics (SAFER), to develop, test, and deploy sensing and imaging systems. In this paper, we describe efforts made to build multi‐perspective mosaics of infrared and color video data for the purpose of under vehicle inspection. It is desired to create a large, high‐resolution mosaic that may be used to quickly visualize the entire scene shot by a camera making a single pass underneath the vehicle. Several constraints are placed on the video data in order to facilitate the assumption that the entire scene in the sequence exists on a single plane. Therefore, a single mosaic is used to represent a single video sequence.
Details
Keywords
Nan Zhang, Lichao Zhang, Senlin Wang, Shifeng Wen and Yusheng Shi
In the implementation of large-size additive manufacturing (AM), the large printing area can be established by using the tiled and fixed multiple printing heads or the single…
Abstract
Purpose
In the implementation of large-size additive manufacturing (AM), the large printing area can be established by using the tiled and fixed multiple printing heads or the single dynamic printing head moving in the x–y plane, which requires a layer decomposition after the mesh slicing to generate segmented infill areas. The data processing flow of these schemes is redundant and inefficient to some extent, especially for the processing of complex stereolithograph (STL) models. It is of great importance in improving the overall efficiency of large-size AM technics software by simplifying the redundant steps. This paper aims to address these issues.
Design/methodology/approach
In this paper, a method of directly generating segmented layered infill areas is proposed for AM. Initially, a vertices–mesh hybrid representation of STL models is constructed based on a divide-and-conquer strategy. Then, a trimming–mapping procedure is performed on sliced contours acquired from partial surfaces. Finally, to link trimmed open contours and inside-signal square corners as segmented infill areas, a region-based open contour closing algorithm is carried out in virtue of the developed data structures.
Findings
In virtue of the proposed approach, the segmented layered infill areas can be directly generated from STL models. Experimental results indicate that the approach brings us the good property of efficiency, especially for complex STL models.
Practical implications
The proposed approach can generate segmented layered infill areas efficiently in some cases.
Originality/value
The region-based layered infill area generation approach discussed here will be a supplement to current data process technologies in large-size AM, which is very suitable for parallel processing and enables us to improve the efficiency of large-size AM technics software.
Details
Keywords
Wen-Yang Chang and Chih-Ping Tsai
This study aims to investigate the spectral illumination characteristics and geometric features of bicycle parts and proposes an image stitching method for their automatic visual…
Abstract
Purpose
This study aims to investigate the spectral illumination characteristics and geometric features of bicycle parts and proposes an image stitching method for their automatic visual inspection.
Design/methodology/approach
The unrealistic color casts of feature inspection is removed using white balance for global adjustment. The scale-invariant feature transforms (SIFT) is used to extract and detect the image features of image stitching. The Hough transform is used to detect the parameters of a circle for roundness of bicycle parts.
Findings
Results showed that maximum errors of 0°, 10°, 20°, 30°, 40° and 50° for the spectral illumination of white light light-emitting diode arrays with differential shift displacements are 4.4, 4.2, 7.8, 6.8, 8.1 and 3.5 per cent, respectively. The deviation error of image stitching for the stem accessory in x and y coordinates are 2 pixels. The SIFT and RANSAC enable to transform the stem image into local feature coordinates that are invariant to the illumination change.
Originality/value
This study can be applied to many fields of modern industrial manufacturing and provide useful information for automatic inspection and image stitching.
Details
Keywords
Dubravko Rogale, Zvonko Dragčevic´ and Anica Hursa
An investigation is presented of the impact of mechanical auxiliary devices on sewing‐machines upon the processing parameters of sewing operations. Processing parameters are…
Abstract
An investigation is presented of the impact of mechanical auxiliary devices on sewing‐machines upon the processing parameters of sewing operations. Processing parameters are investigated at an ergonomically designed workplace, on a modern sewing‐machine, equipped with a processing microcomputer. Measuring samples are 300 to 1,000mm long, and stitching speeds are pre‐programmed – 1,500 to 4,700rpm. Values for sewing operation processing parameters are measured and stored using the measuring system for processing parameters MMPP, developed especially for the purpose of research in the field of garment engineering. The results obtained indicate that using a tape piper the basic time needed to perform the sewing operation is reduced by up to 61.2 per cent, while the use of a hemmer reduces it by 38.3 per cent. Specific time for sewing 1m of seam is reduced using the above auxiliary devices as follows: by 64.5 per cent using a tape piper and by 41.8 per cent using a hemmer. The degree of sewing‐machine utilisation is increased by 110.6 per cent using a tape piper, and by 59.8 per cent using a hemmer. Average stitching in machine‐hand sub‐operations is increased with a tape piper from 1,041 to 3,914rpm, and from 1,176 to 3,959rpm with a hemmer. The operation structure is altered by using auxiliary devices, achieving rationalisation of the movements constituting auxiliary‐hand sub‐operations, which has a considerable impact on the processing parameters involved.
Details
Keywords
Dubravko Rogale, Igor Petrunić, Zvonko Dragčević and Snježana Firšt Rogale
The equipment for computerised measuring of electrical power and energy is presented, adapted to the needs of investigating processing parameters of garment sewing operations.
Abstract
Purpose
The equipment for computerised measuring of electrical power and energy is presented, adapted to the needs of investigating processing parameters of garment sewing operations.
Design/methodology/approach
The method of measuring the energy necessary to run the sewing‐machine driving electrical motor is also presented, correlated to the stitching speed in joining a straight seam in a single, two, or three, segments. Electrical energy consumption is analysed as dependent on the stitching speed, varying the number of stitches in the seam.
Findings
The investigations described have shown the impact of the method of work applied and the effect of the changes in garment sewing operation in processing parameters on the level of electrical energy consumed by the sewing‐machine drive electrical motor. A new measuring method has been introduced in garment engineering, aimed at predicting electrical energy consumption in garment sewing operations, thus opening a completely new field of investigation in the area of garment technologies.
Originality/value
A method of calculating the energy processing parameters of sewing operations.
Details
Keywords
Yanming Fan and Ming Li
The purpose of this paper is to present weighted Euclidean distance for measuring whether the fitting of projective transformation matrix is more reliable in feature-based image…
Abstract
Purpose
The purpose of this paper is to present weighted Euclidean distance for measuring whether the fitting of projective transformation matrix is more reliable in feature-based image stitching.
Design/methodology/approach
The hybrid model of weighted Euclidean distance criterion and intelligent chaotic genetic algorithm (CGA) is established to achieve a more accurate matrix in image stitching. Feature-based image stitching is used in this paper for it can handle non-affine situations. Scale invariant feature transform is applied to extract the key points, and the false points are excluded using random sampling consistency (RANSAC) algorithm.
Findings
This work improved GA by combination with chaos's ergodicity, so that it can be applied to search a better solution on the basis of the matrix solved by Levenberg-Marquardt. The addition of an external loop in RANSAC can help obtain more accurate matrix with large probability. Series of experimental results are presented to demonstrate the feasibility and effectiveness of the proposed approaches.
Practical implications
The modified feature-based method proposed in this paper can be easily applied to practice and can obtain a better image stitching performance with a good robustness.
Originality/value
A hybrid model of weighted Euclidean distance criterion and CGA is proposed for optimization of projective transformation matrix in image stitching. The authors introduce chaos theory into GA to modify its search strategy.
Details
Keywords
Seungryeol Yoo and Daniel Walczyk
To provide an advanced cutting trajectory algorithm for the profiled edge laminae (PEL) rapid tooling (RT) process, which is ideally suited for large‐scale dies and molds. The…
Abstract
Purpose
To provide an advanced cutting trajectory algorithm for the profiled edge laminae (PEL) rapid tooling (RT) process, which is ideally suited for large‐scale dies and molds. The process involves assembling an array of laminae whose top edges are simultaneously profiled and beveled using a line‐of‐sight cutting method based on a CAD model of the intended tool surface.
Design/methodology/approach
The cutting profiles for an individual tool lamina are based on intersection curves obtained directly from the CAD model, and generated with exact geometrical accuracy. Two adjacent slice profiles, which define a lamination's top edge and are represented as polylines, are stitched together using an adaptive surface reconstruction algorithm. A cutting trajectory algorithm then develops a series of suitable cutting vectors (i.e. position and cutting direction) that minimize abrasive waterjet (AWJ) cutting errors due to non‐uniform motion and variations in kerf geometry resulting from process parameter variations. The proposed cutting trajectory generation process is demonstrated virtually for an actual production tool.
Findings
The proposed algorithm yields well‐behaved AWJ cutting trajectories for individual lamina used in a PEL tool that are better than those obtained using any other algorithm found in the literature.
Research limitations/implications
The algorithm is intended for use with AWJ cutting of PEL tool surfaces. Suggested future research includes assessment of the algorithm for other lamina cutting methods including laser cutting and wire‐type electro‐discharge machining, extending the algorithm to handle conformal cooling/heating channels and internal cavities, and application of the algorithm to several industrial tool case studies.
Practical implications
The algorithm generates cutting trajectories directly from CAD geometry that are ideal for AWJ cutting of profiled edge lamina. It will simply make industrial implementation of the PEL RT process easier.
Originality/value
This paper provides a new cutting trajectory algorithm for the PEL RT process that is a significant improvement over comparable algorithms proposed in the literature.
Details
Keywords
Biqin Zhan, Xian Huang, Chenyuan Cai and Honglian Cong
Fully formed knitting technology is a cutting-edge technology in the design and production of knitted apparel. Using this technology and its supporting design system, a new…
Abstract
Purpose
Fully formed knitting technology is a cutting-edge technology in the design and production of knitted apparel. Using this technology and its supporting design system, a new development mode of fully formed knitted apparel with double-layer structure and fake two-piece knitwear is proposed.
Design/methodology/approach
Based on the upper body structure feature points of human body characteristics and single-layer knitted garment prototype, a double-layer structure knitted garment pattern was established by pattern expansion method. The model was introduced into SDS-APPEX3 design system for process design, including three aspects consists: the inner vest, the outer blouse and double-layer joint part, analysis of the process and forming principle. Weaving on four-needle bed computerized flat knitting machine of MACH-2XS, through the setting of the machine parameters. Finally, a full-shaped fake two-piece knitted blouse was formed.
Findings
On the basis of single-layer knitted garment pattern, a double-layer garment pattern is constructed, and the design and weaving are completed on the four-needle bed computerized knitting machine of MACH-2XS and its supporting SDS-APPEX3 design system through the fake two-piece double-layer garment style design. The double-layer joint model is an effective reference for the construction of this kind of fake two-piece fully formed knitted clothing.
Originality/value
In this paper, a design and knitting method of fully formed double-layer structure fake two-piece knitted garment is proposed. The integrated knitting of fully formed double-layer structure sweater is realized for the first time, which provides ideas for the development of fully formed double-layer structure knitted clothing style and enriches the fully formed clothing style.
Details