• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4527-4548
• /
• 2017

This paper proposes a method to generate panoramic images by combining conventional feature extraction algorithms (e.g., SIFT, SURF, MPEG-7 CDVS) with sensed data from inertia sensors to enhance the stitching results. The challenge of image stitching increases when the images are taken from two different mobile phones with no posture calibration. Using inertia sensor data obtained by the mobile phone, images with different yaw, pitch, and roll angles are preprocessed and adjusted before performing stitching process. Performance of stitching (e.g., feature extraction time, inlier point numbers, stitching accuracy) between conventional feature extraction algorithms is reported along with the stitching performance with/without using the inertia sensor data. In addition, the stitching accuracy of video data was improved using the same sensed data, with discrete calculation of homograph matrix. The experimental results for stitching accuracies and speed using sensed data are presented in this paper.

• Composites Research
• /
• v.33 no.5
• /
• pp.296-301
• /
• 2020

Laminated composite materials have excellent in-plane properties, but are vulnerable in thickness directions, making it easy to delamination when bending and torsion loads are applied. Thickness directional reinforcement methods of composite materials that delay delamination include Z-pinning, Stitching, Tufting, etc., and typically Z-pinning and Stitching method are commonly used. The Z-pinning is reinforcement method by inserting metal or carbon pin in the thickness direction of prepreg, and the conventional stitching process is a method of reinforcing the mechanical properties in the thickness direction by intersecting the upper and lower fibers on the preform. In this paper, I-fiber stitching method, which complement and improve weakness of Z-pinning and Stitching method, was proposed, and the static strength of composite single-lap joints using I-fiber stitching process were evaluated. The single-lap joints were fabricated by a co-curing method using an autoclave vacuum bag process. The thickness of the composite adherend was fixed, and 5 types of specimens were manufactured with varying the stitching pattern (5×5, 7×7) and angle (0°, 45°). From the test, the failure load of the specimen reinforced by the I-fiber stitching process was increased by up to 143% compared to that of specimen without reinforcement.

• Composites Research
• /
• v.28 no.3
• /
• pp.136-141
• /
• 2015

The stitching process has been widely utilized for the improvement of through-thickness property of the conventional laminated composites. This paper reports the effects of stitching on the flexural and interlaminar shear properties of multi-axial warp knitted (MWK) composites in order to identify the mechanical property improvements. In order to minimize the geometric uncertainties associated with the stacking pattern of fabrics, the regular lay-up was considered in the examination of the stitching effect. The key parameters are as follows: the stitch spacings, the stitching types, the stitching location, and the location of compression fixture nose. These parameters have little effect on the flexural and interlaminar shear properties, except for the case of stitching location. However, the geometry variations caused by the stitching resulted in minor changes to the mechanical properties consistently. Stitching on the $0^{\circ}$ fibers showed the lowest flexural strength and modulus (12% reduction for both properties). The stitch spacing of 5 mm resulted in 8% reduction for the case of interlaminar strength compared with that of 10 mm spacing.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2004.10a
• /
• pp.216-219
• /
• 2004

The stitching process has been widely utilized for the improvement of through-thickness property of the conventional laminated composites. This paper rep0l1s the effects of stitching on the flexural and interlaminar shear properties of multiaxial warp knitted composites in order to examine the performance improvements. Considered parameters are as follows: the stacking regularity of the multiaxial warp knits, the stitch spacings, the stitching types, the stitching location, and the location of compression fixture nose. These parameters have little effect on the flexural and interlaminar shear properties, except for the case of stitching location. Stitching on the $0^{\circ}$ fibers showed the lowest flexural strength and modulus ($12\%$reduction for both properties). The stitch spacing of 5mm resulted 8% reduction in interlaminar strength compared with 10mm spacing.

• Journal of Broadcast Engineering
• /
• v.22 no.1
• /
• pp.51-61
• /
• 2017

This paper proposes a method to generate panoramic images by combining conventional feature extraction algorithms (e.g., SIFT, SURF, MPEG-7 CDVS) with sensed data from an inertia sensor to enhance the stitching results. The challenge of image stitching increases when the images are taken from two different mobile phones with no posture calibration. Using inertia sensor data obtained by the mobile phone, images with different yaw angles, pitch angles, roll angles are preprocessed and adjusted before performing stitching process. Performance of stitching (e.g., feature extraction time, inlier point numbers, stitching accuracy) between conventional feature extraction algorithms is reported along with the stitching performance with/without using the inertia sensor data.

• Journal of the Korean Society of Radiology
• /
• v.17 no.1
• /
• pp.47-52
• /
• 2023

In whole spine radiography using the stitching technique, overlapping parts occur in the process of synthesizing the three segmented images, so some anatomical structures may be repeatedly exposed, and it has been thought that the dose increases as the scan range increases. However, in the whole spine radiography using the stitching technique in this study, under the condition that the stitching range is taken in the same three splits, the overlapping area decreases as the stitching range increases, so in the case of breasts included in the overlapping range, the dose value decreased by almost half as the stitching range increased from 90 cm to 105 cm. During spinal full-length radiological examination using the stitching method, an appropriately long stitching range could be set to reduce the exposure dose of the breast.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.20-30
• /
• 2022

Recently, as VR (Virtual Reality) technology has been in the spotlight, 360° panoramic images that can view lively VR contents are attracting a lot of attention. Image stitching technology is a major technology for producing 360° panorama images, and many studies are being actively conducted. Typical stitching algorithms are based on feature point-based image stitching. However, conventional feature point-based image stitching methods have a problem that stitching results are intensely affected by feature points. To solve this problem, deep learning-based image stitching technologies have recently been studied, but there are still many problems when there are few overlapping areas between images or large parallax. In addition, there is a limit to complete supervised learning because labeled ground-truth panorama images cannot be obtained in a real environment. Therefore, we produced three fisheye images with different camera centers and corresponding ground truth image through carla simulator that is widely used in the autonomous driving field. We propose image stitching model that creates a 360° panorama image with the produced fisheye image. The final experimental results are virtual datasets configured similar to the actual environment, verifying stitching results that are strong against various environments and large parallax.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.965-973
• /
• 2019

In this paper, Stereo 4K@60fps 360 VR real-time video capture system which consists of video stream capture, video encoding and stitching module is been designed. The system captures stereo 4K@60fps 360 VR video by stitching 6 of 2K@60fps stream which are captured through HDMI interface from 6 cameras in real-time. In video capture phase, video is captured from each camera using multi-thread in real-time. In video encoding phase, raw frame memory transmission and parallel encoding are used to reduce the resource usage in data transmission between video capture and video stitching modules. In video stitching phase, Real-time stitching is secured by stitching calibration preprocessing.

• Journal of the Optical Society of Korea
• /
• v.18 no.4
• /
• pp.341-344
• /
• 2014

This study proposes a modified sub-aperture stitching algorithm, which uses an image sharpening algorithm and particle swarm optimization to improve the stitching accuracy. In sub-aperture stitching interferometers with high positional accuracy, the high-frequency components of measurements are more important than the low-frequency components when compensating for position errors using a sub-aperture stitching algorithm. Thus we use image sharpening algorithms to strengthen the high-frequency components of measurements. When using image sharpening algorithms, sub-aperture stitching algorithms based on the least-squares method easily become trapped at locally optimal solutions. However, particle swarm optimization is less likely to become trapped at a locally optimal solution, thus we utilized this method to develop a more robust algorithm. The results of simulations showed that our algorithm compensated for position errors more effectively than the existing algorithm. An experimental comparison with full aperture-testing results demonstrated the validity of the new algorithm.

• Advances in Automotive Engineering
• /
• v.1 no.1
• /
• pp.143-152
• /
• 2018

In this study an economical image stitching algorithm for use in automotive industry is developed for retrofittable panoramic image assistance applications. The aim of this project is to develop a driving assistance system known as Panoramic Parking Assistance (PPA) which is cheap, retrofittable and compatible for every type of automobiles. PPA generates bird's eye view image using cameras installed on the automobiles. Image stitching requires to get bird's eye view position of the vehicle. Panoramic images are wide area images that cannot be available by taking one shot, attained by stitching the overlapping areas. To achieve correct stitching many algorithms are used. This study includes some type of these algorithms and presents a simple one that is economical and practical. Firstly, the mathematical model of a wide view of angle camera is provided. Then distorted image correction is performed. Stitching is implemented by using the SIFT and SURF algorithms. It has been seen that using such algorithms requires complex image processing knowledge and implementation of high quality digital processors, which would be impracticle and costly for automobile use. Thus a simpler algorithm has been developed to decrase the complexity. The proposed algorithm uses one matching point for every couple of images and has ease of use and does not need high power processors. To show the efficiency, images coming from four distinct cameras are stitched by using the algorithm developed for the study and usability for automotive application is analyzed.