Stitching Process Research Articles

Unmanned aerial vehicle image stitching based on multi‐region segmentation

AbstractUnmanned aerial vehicle (UAV) image stitching is a key technology for aerial remote sensing applications. Most existing image stitching methods based on optimal seamline searching algorithms can eliminate defects such as ghosting and distortion in stitched images, which unfortunately suffer from the problem that the seamline may cross those regions with significant geometric misalignment between different images. Therefore, a novel image stitching method based on multi‐region image segmentation is proposed. The algorithm starts by performing a multi‐scale morphological reconstruction in the overlapping regions between UAV images to obtain superpixel images with precise contours. Then, the fast density peaks clustering based on K‐nearest neighbours is applied to automatically determine the clustering centres and the number of clusters. By constructing a cost function, an energy map is generated in the overlapping regions between UAV images. Finally, the optimal seamline can be determined with a graph‐cut method. Compared to several popular image stitching algorithms in real experiments, the proposed method can essentially prevent the seamline from crossing significant ground objects to ensure the integrity of structural objects while achieving satisfactory accuracy and efficiency during the UAV image stitching process.

A UAV Thermal Imaging Format Conversion System and Its Application in Mosaic Surface Microthermal Environment Analysis.

UAV thermal infrared remote sensing technology, with its high flexibility and high temporal and spatial resolution, is crucial for understanding surface microthermal environments. Despite DJI Drones' industry-leading position, the JPG format of their thermal images limits direct image stitching and further analysis, hindering their broad application. To address this, a format conversion system, ThermoSwitcher, was developed for DJI thermal JPG images, and this system was applied to surface microthermal environment analysis, taking two regions with various local zones in Nanjing as the research area. The results showed that ThermoSwitcher can quickly and losslessly convert thermal JPG images to the Geotiff format, which is further convenient for producing image mosaics and for local temperature extraction. The results also indicated significant heterogeneity in the study area's temperature distribution, with high temperatures concentrated on sunlit artificial surfaces, and low temperatures corresponding to building shadows, dense vegetation, and water areas. The temperature distribution and change rates in different local zones were significantly influenced by surface cover type, material thermal properties, vegetation coverage, and building layout. Higher temperature change rates were observed in high-rise building and subway station areas, while lower rates were noted in water and vegetation-covered areas. Additionally, comparing the temperature distribution before and after image stitching revealed that the stitching process affected the temperature uniformity to some extent. The described format conversion system significantly enhances preprocessing efficiency, promoting advancements in drone remote sensing and refined surface microthermal environment research.

EXPLORING THE EFFECTS OF STITCHING PROCESS ON THE MECHANICAL PROPERTIES OF THREE- DIMENSIONAL (3D) STITCHED UNIDIRECTIONAL COMPOSITES

The stitching process has obvious effects on the out- of- plane mechanical properties of composites such as impact damage mechanism or impact energy absorption. However, the effects on the in- plane mechanical properties of composites have been under discussion and need to be clarified. In the previous studies, tensile, shear and bending behaviors of 3D stitched biaxial woven carbon composite were investigated. The unidirectional carbon woven fabrics constitute the significant part of raw materials in the composite industry. For this reason, the research study was expanded to examine the in- plane mechanics of 3D stitched unidirectional carbon woven composites. In this study, the unstitched and 3D stitched unidirectional woven carbon composites were manufactured and tested under the shear, tensile and bending loads. While the stitching process improved the tensile and shear modulus of composite, it could not create the significant difference in the bending behavior. The highest module and maximum stress values were obtained in the tensile test. The bending and shear test results follow them, respectively. Moreover, it was proven that the fabric architecture of stitched composite layer has the substantial effect on the tensile properties of 3D stitched composite.

Distributed Aerial Image Stitching on Multiple Processors using Message Passing Interface

This study investigates the potential of using Message Passing Interface (MPI) parallelization to enhance the speed of the image stitching process. The image stitching process involves combining multiple images to create a seamless panoramic view. This research explores the potential benefits of segmenting photos into distributed tasks among several identical processor nodes to expedite the stitching process. However, it is crucial to consider that increasing the number of nodes may introduce a trade-off between the speed and quality of the stitching process. The initial experiments were conducted without MPI, resulting in a stitching time of 1506.63 seconds. Subsequently, the researchers employed MPI parallelization on two computer nodes, which reduced the stitching time to 624 seconds. Further improvement was observed when four computer nodes were used, resulting in a stitching time of 346.8 seconds. These findings highlight the potential benefits of MPI parallelization for image stitching tasks. The reduced stitching time achieved through parallelization demonstrates the ability to accelerate the overall stitching process. However, it is essential to carefully consider the trade-off between speed and quality when determining the optimal number of nodes to employ. By effectively distributing the workload across multiple nodes, researchers and practitioners can take advantage of the parallel processing capabilities offered by MPI to expedite image stitching tasks. Future studies could explore additional optimization techniques and evaluate the impact on speed and quality to achieve an optimal balance in real-world applications.

Self-healing potential of stitched glass/polypropylene/epoxy hybrid composites with various fibers

This study compares the impact damage response and self-healing potential of unstitched and stitched glass/polypropylene (PP) fiber reinforced thermoset composite structures. The novelty of this study is weaving preforms with an intra-ply hybridization of glass and thermoplastic PP fibers and stitching these preforms with a unique stitching pattern by considering the effect of stitching fiber types (PP, Kevlar®, Dyneema®, carbon and silk) on impact damage response and self-healing potential of composites. The mechanical properties of the stitching fiber influenced the composite’s behavior against impact and compressive loads. The unstitched composite deflected more than stitched composites under the same impact energy levels due to delaying of delamination via stitching process. The stitching process reduced the damage areas of composites subjected to 30 J and 60 J impact energies by 57 and 86%, respectively. Structural healing significantly decreased the damaged areas of both unstitched and stitched composite structures up to 87%, while it was more effective on stitched composites. The polypropylene melted and accumulated along the path of the stitch pattern, regardless of whether the stitching fiber was thermoplastic. Due to the reduced impacted area, compression after impact (CAI) strength retention of the stitched composite materials increased by up to 94%.

Cost-effective reliability enhancement for video stitching applications based on error-tolerance

Image (video) stitching technology has been widely used in real-time video applications. In this paper, for the first time, we address design and implementation of a reliable image (video frame) stitching system and focus on its video applications. In particular, we show that by well exploiting the inherent error-tolerability of the image stitching process, a cost-effective reliability enhancement solution can be enabled. For input images (video frames), the proposed system carries out a unique no-reference error detection process where the acceptability of potential errors in input image data can be tested. Particularly, no golden data are required, which greatly facilitates the implementation of an on-line testing process. Based on the testing results, a simple yet effective repair process is enabled for transforming unacceptable stitching results into acceptable ones. Our experimental results show that acceptability testing accuracy of our error detection process achieves 98.4 %. The experimental results on 864,000 various test cases also show that 80 % of the unacceptably erroneous stitched video frames can be successfully repaired, thereby achieving 5× lifetime extension. In addition, when compared to the typical ECC (Error Correcting Code) or TMR (Triple Modular Redundancy) reliability improvement methods, our system not only requires much less hardware cost, but also incurs only ignorable performance overhead. These lead to almost no loss in the achievable FPS (Frame Per Second), and thus real-time video stitching can still be achieved but with high reliability.

Synchronous Driving Method for Stitching Pixel Arrays Based on an Adaptive Correction Technique.

With the application of stitching technology in large-pixel-array CMOS image sensors, the problem of non-synchronized output signals from pixel array bilateral driver circuits has become progressively more serious and has led to the DC perforation of bilateral driver circuits, while conventional clock tree synchronization design methodology does not apply to stitching technology. Therefore, this paper analyses reasons for the inconsistency in the output signals of bilateral driving circuits and proposes a synchronous driving method applicable to stitching pixel arrays based on the idea of on-chip output signal delay detection and calibration. This method detects and corrects the non-synchrony of the row driver output signals on both sides according to changes in the operating environment of the chip. This method is characterized by a simple structure and high reliability. Finally, based on the 55 nm stitching process, simulations are carried out in a CMOS image sensor with a chip area of 77 mm × 84 mm to verify that this method is feasible. This large image sensor with a 150 M pixel array has a frame rate of over 10 FPS.

Small Target Detection in Refractive Panorama Surveillance Based on Improved YOLOv8

Panoramic imaging is increasingly critical in UAVs and high-altitude surveillance applications. In addressing the challenges of detecting small targets within wide-area, high-resolution panoramic images, particularly issues concerning accuracy and real-time performance, we have proposed an improved lightweight network model based on YOLOv8. This model maintains the original detection speed, while enhancing precision, and reducing the model size and parameter count by 10.6% and 11.69%, respectively. It achieves a 2.9% increase in the overall mAP@0.5 and a 20% improvement in small target detection accuracy. Furthermore, to address the scarcity of reflective panoramic image training samples, we have introduced a panorama copy–paste data augmentation technique, significantly boosting the detection of small targets, with a 0.6% increase in the overall mAP@0.5 and a 21.3% rise in small target detection accuracy. By implementing an unfolding, cutting, and stitching process for panoramic images, we further enhanced the detection accuracy, evidenced by a 4.2% increase in the mAP@0.5 and a 12.3% decrease in the box loss value, validating the efficacy of our approach for detecting small targets in complex panoramic scenarios.

An experimental investigation of the mechanical properties and failure mode of 3D stitched composites

Mechanical behavior and failure modes of three-dimensional (3D) stitched composites were experimentally investigated. In addition, a comparative analysis between these materials and equivalent laminates (2D) was accomplished. The 3D composite plates were manufactured using sheets of glass fiber manually sewn with aramid tows and molded with epoxy resin by vacuum-assisted resin transfer molding. Three-points bending, Charpy impact, double cantilever beam (DCB), and short-beam shear (SBS) mechanical tests were carried out on both types of materials. The DCB test results revealed that the action of reinforcement tows inhibited the propagation of the delamination cracks, which led to an increase in the fracture toughness of the 3D composites. However, the damage caused by the stitching process, such as fiber breakage and misalignment as well as crimping, and resin-rich regions, was responsible for reducing the flexural and shear properties of these materials. In addition, it was revealed that the stitching did not influence the impact toughness, although it prevented delamination from quick propagation, avoiding a catastrophic failure, which enhanced the damage tolerance of these materials, mainly for aeronautical applications.

Productivity improvement in the stitching process: a Six Sigma case study of the footwear industry

Productivity improvement in the stitching process: a Six Sigma case study of the footwear industry

Novel silicon detectors in ALICE at the LHC: The ITS3 and ALICE 3 upgrades

The ALICE experiment is preparing for the ITS3 upgrade, which is set to take place during the LHC Long Shutdown 3. The aim of this upgrade is to replace the three innermost tracking layers with truly cylindrical wafer-scale Monolithic Active Pixel Sensors (MAPS). By adopting this innovative technology, ALICE will further reduce the material budget and the distance from the interaction point, thus significantly improving its tracking and vertexing capabilities. The R&D program for ITS3 includes several advancements, such as operability of bent MAPS, validation of the 65 nm CMOS technology, and employment of the stitching process to produce wafer-scale sensors. In addition to the ITS3 upgrade, ALICE is designing a completely new apparatus, ALICE 3, planned for LHC Runs 5 and 6. The detector consists of a large MAPS-based tracking system covering eight units of pseudorapidity, complemented by multiple systems for particle identification, including silicon time-of-flight layers, a ring-imaging Cherenkov detector, a muon identification system, and an electromagnetic calorimeter. The vertex detector is based on an evolution of the ITS3 concept aiming at a track pointing resolution of better than 10 μm for tranverse momenta above 200 MeV/c through the integration of the tracking layers in a retractable structure inside the beam pipe. In this proceeding the detector concept of these upgrades is described, together with their physics motivations and R&D status and achievements.

Development of Technology and Equipment for Non-destructive Testing of Defects in Sewing Mandrels of a Three-roll Screw Mill 30-80

The conditions of heating and cooling of piercing mandrels made of 4X5MFS steel of a three-roll screw mill 30-80 in the production of a closed cavity of steel vessels of small volume are determined. It is established that multiple cycles of heating up to 600 °C and cooling with water up to 80 °C for about 7 seconds/1 cycle lead to the formation of ridges, shells and cracks on the surface and in the volume of the tool. The loss of structural strength of the material leads to the breakdown of the mandrel during the stitching process. The technique and equipment of magnetic powder control have been developed to establish the dynamics of the growth of internal and external defects of mandrels. An equation is obtained that allows determining the increase in the number of defects in the sewing tool of a screw rolling mill. The technology of non-destructive testing made it possible to develop a rational plan for replacing the sewing mandrels, which allows for predicting the appearance of defects leading to a complex breakdown of the deforming tool at the NPO Pribor machine-building enterprise.

Finite Element Analysis of the Effect for Different Thicknesses and Stitching Densities under the Low-Velocity Impact of Stitched Composite Laminates.

In this study, a progressive damage model was developed for the mechanical response and damage evolution of carbon fiber stitched composite laminates under low-velocity impact (LVI). The three-dimensional Hashin and Hou failure criteria were used to identify fiber and matrix damage. The cohesive zone model was adopted to simulate the delamination damage, combined with the linear degradation discounting of the equivalent displacement method to characterize the stiffness degradation of the material, and the corresponding user material subroutine VUMAT was coded. The finite element analysis of the LVI of stitched composite laminates under different energies was finished in Abaqus/Explicit. Furthermore, the simulation predictions matched well with the results of the experimental tests. Based on this, composite laminates' mechanical response and damage forms with different thicknesses and stitch densities were analyzed. The findings show that the main damages of composite laminates were matrix tensile damage and delamination. The stitching process could improve the impact tolerance of composite laminates, inhibiting delamination and reducing the area of the delamination damage. The higher the density of the stitching, the more noticeable its inhibition would be. The thickness of the laminate also had a more significant effect on the damage to the laminate. Thin plates were more prone to matrix tensile damage due to their lower flexural rigidity, whereas thick plates were more susceptible to delamination because of their higher flexural rigidity.

LMFD: lightweight multi-feature descriptors for image stitching

Image stitching is a fundamental pillar of computer vision, and its effectiveness hinges significantly on the quality of the feature descriptors. However, the existing feature descriptors face several challenges, including inadequate robustness to noise or rotational transformations and limited adaptability during hardware deployment. To address these limitations, this paper proposes a set of feature descriptors for image stitching named Lightweight Multi-Feature Descriptors (LMFD). Based on the extensive extraction of gradients, means, and global information surrounding the feature points, feature descriptors are generated through various combinations to enhance the image stitching process. This endows the algorithm with formidable rotational invariance and noise resistance, thereby improving its accuracy and reliability. Furthermore, the feature descriptors take the form of binary matrices consisting of 0s and 1s, not only facilitating more efficient hardware deployment but also enhancing computational efficiency. The utilization of binary matrices significantly reduces the computational complexity of the algorithm while preserving its efficacy. To validate the effectiveness of LMFD, rigorous experimentation was conducted on the Hpatches and 2D-HeLa datasets. The results demonstrate that LMFD outperforms state-of-the-art image matching algorithms in terms of accuracy. This empirical evidence solidifies the superiority of LMFD and substantiates its potential for practical applications in various domains.

Investigation of the bending and quasi‐static indentation properties of three‐dimensional (3D) textile‐reinforced composites

AbstractThe three‐dimensional (3D) textiles, which are identified as advanced fabric systems, have been under development for decades and are demanded for number of structural or semi‐structural applications. They can be obtained by several production methods. These methods impart distinct, specific properties to the 3D textiles and their composites. However, the discrepancies in the production methods and their effects on the dry structure and composite mechanics need to be elucidated. In this study, the compressibility and bending properties of 3D woven, 3D multiaxis warp knitted, and 3D stitched fabrics were determined. Afterward, their composites were produced and tested under three‐point bending and quasi‐static indentation loads. Therefore, the load bearing capacity of 3D textiles was investigated from the dry structure to the composite. According to the purpose of the end‐uses, significant differences were obtained in their mechanical behaviors. When the indentation properties and damage mechanism are taken into consideration, the 3D woven composite shows the best performance among all composites.Highlights Quadriaxial oriented low crimp carbon yarns gain the best quasi‐static indentation resistance to composites. The stitching process prevents damage progress in composites and restrains smaller areas. Binding warp yarn enables the composite distribute indentation energy more evenly.

Effect of geometric heterogeneity using an auxiliary device on the accuracy of complete arch implant scanning: An in vitro study of different clinical simulations.

Intraoral scanning of implants supporting complete arch prostheses is limited because of the lack of geometric heterogeneity and unique reference points, creating inherent errors in the image stitching process by the scanner software program. The purpose of this in vitro study was to evaluate the significance of geometric heterogeneity on complete arch implant scanning by using a novel auxiliary geometric device. Three different clinical simulations were tested to assess its significance. The study also assessed whether scans produced using the auxiliary device would meet a clinically acceptable threshold. A total of 60 scans (n=20) were performed using an intraoral scanner in 3 different clinical simulations: 2 parallel implants, 4 parallel implants, and 4 implants with a 30-degree posterior angulation of the distal implants. Scanning alternated between using the auxiliary geometric scanning device (test groups; 4IP+, 4IA+, 2IP+) and not using the device (control groups; 4IP-, 4IA-, 2IP-). A reference scan for each model was prepared from a high precision laboratory scanner. The scans were analyzed for accuracy in 3-dimensional deviation, interimplant distance deviation, and angular deviation by using an inspection software program. The effect of the auxiliary device was statistically analyzed by comparing scans of the same group using the paired t test for normally distributed data and the Wilcoxon Signed Rank test when data were not normally distributed (α=.05). Significant effects of the auxiliary geometric device were found in 3-dimensional, distance and angular deviations (P<.05). Scans performed using the device were significantly more accurate in most implant positions (P<.05). Linear and angular deviations were clinically acceptable for all test groups. However, the deviations were above the clinically acceptable threshold for the control groups. Using an auxiliary geometric device significantly improved scanning accuracy and produced scans with clinically acceptable deviations, while standard digital scans exceeded the accepted clinical threshold.

Research of different feature detection and matching algorithms on panoramic image

Image stitching is the process of combining numerous photos to make a panorama. The technique of image stitching has rapidly advanced and grown to be a significant area of digital image processing. Many image stitching methods have been proposed and studied in prior study. In this paper, the image stitching process is implemented using different algorithms. For keypoints detection, the algorithms of Harris corner detection, SIFT(Scale-Invariant Feature Transform), SURF(Speeded Up Robust Feature) and ORB(Oriented FAST and Rotated BRIEF) algorithms are applied, then use different methods (i.e., Brute Force, etc.) for feature matching. The RANSAC(Random Sample Consensus) method is used to calculate a homography matrix from matched feature vectors and use it to warp the images. Image blending and cropping methods are proposed to enhance the image quality. Given groups of the self-captured images, experiments have been down to shown the performance of different techniques.

A comparison of feature extraction methods in image stitching

The usage of feature detectors for image stitching has become a popular research area in computer vision. Various feature extraction algorithms can be used in the process of image stitching process, but they perform varyingly when handling different images and no single algorithm could outperform all others. This paper focuses on the comparison of feature extraction algorithms used for panoramic image stitching. The research utilizes the SIFT, ORB, AKAZE, and BRISK to conduct feature points and match feature points on a group of image sets. The RANSAC algorithm is then used to filter out the outliers and calculate the homograph matrix. Completes the panoramic with image splicing and smoothing through the matrix transformation. Derived from the comparison of the matching and stitching results, the AKAZE detector is found to be the fastest feature point detection and extraction algorithm, while the SIFT detector will provide more feature points to make more accurate matches possible. These findings have implications for the development of efficient and effective computer vision technologies for various applications.

Effect of stitching on the static and fatigue properties of fibre-dominated and matrix-dominated composite laminates

The paper reports the results of an experimental investigation into the effect of stitching on the static and fatigue response of fibre-dominated and matrix-dominated laminates. The tests were conducted on Kevlar stitched carbon/epoxy laminates with quasi-isotropic ([0/±45/90]s) or angle-ply ([+302/−302]s, [+452/−452]s, [+602/−602]s) layups. The analyses show that stitching significantly reduces both the static and the fatigue strength of fibre-dominated [0/±45/90]s laminates, owing to the presence of localized fibre damage introduced during the stitching process. On the other hand, stitching does not affect the fatigue response of [+602/−602]s laminates but significantly improves the fatigue strength of [+302/–302]s and [+452/−452]s laminates. The effectiveness of stitching on the fatigue performance of the angle-ply layups was found to be directly related to the specific damage mechanisms preceding the ultimate failure, which are controlled by edge delaminations in [+302/–302]s and [+452/−452]s and transverse matrix cracking in [+602/−602]s laminates.

Nighttime Image Stitching Method Based on Image Decomposition Enhancement.

Image stitching technology realizes alignment and fusion of a series of images with common pixel areas taken from different viewpoints of the same scene to produce a wide field of view panoramic image with natural structure. The night environment is one of the important scenes of human life, and the night image stitching technology has more urgent practical significance in the fields of security monitoring and intelligent driving at night. Due to the influence of artificial light sources at night, the brightness of the image is unevenly distributed and there are a large number of dark light areas, but often these dark light areas have rich structural information. The structural features hidden in the darkness are difficult to extract, resulting in ghosting and misalignment when stitching, which makes it difficult to meet the practical application requirements. Therefore, a nighttime image stitching method based on image decomposition enhancement is proposed to address the problem of insufficient line feature extraction in the stitching process of nighttime images. The proposed algorithm performs luminance enhancement on the structural layer, smoothes the nighttime image noise using a denoising algorithm on the texture layer, and finally complements the texture of the fused image by an edge enhancement algorithm. The experimental results show that the proposed algorithm improves the image quality in terms of information entropy, contrast, and noise suppression compared with other algorithms. Moreover, the proposed algorithm extracts the most line features from the processed nighttime images, which is more helpful for the stitching of nighttime images.