Drone Image Stitching Using Local Mesh-Based Bundle Adjustment and Shape-Preserving Transform

Wan, Qi; Chen, Jun; Luo, Lei; Gong, Wenping; Wei, Longsheng

doi:10.1109/tgrs.2020.3025528

Cited by 17 publications

(4 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another option is the use of SIFT to estimate the global transformation parameter. The result will accumulate registration errors and disregard multiple constraints between images [107] to improve the stitching performance. A shape-preserving transform is used to preserve the geometric similarity before reprojecting, which attempts to retain the shapes of local regions and use multiband fusion to process the gain compensation and obtain a natural-looking panoramic image.…”

Section: Feature-based: Local Hybrid Transformationmentioning

confidence: 99%

See 1 more Smart Citation

Image Mosaicing Applied on UAVs Survey

et al. 2022

View full text Add to dashboard Cite

The use of UAV (unmanned aerial vehicle) technology has allowed for advances in the area of robotics in control processes and application development. Such is the case of image processing, in which, by the use of aerial photographs taken by these aircrafts, it is possible to perform surveillance and monitoring tasks. As an example, we can mention the use of aerial photographs for the generation of panoramic images through the process of stitching images without losing image resolution. Some applications are photogrammetry and mapping, where the main problems to be solved are image alignment and ghosting images, for which different stitching techniques can be applied. These methodologies can be categorized into direct methods or feature-based methods. This paper aims to show an overview of the most frequently applied mosaicing techniques in UAVs by providing an introduction to those interested in developing in this area. For this purpose, a summary of the most applied techniques and their applications is given, showing the trend of the research field and the contribution of different countries over time.

show abstract

Section: Feature-based: Local Hybrid Transformationmentioning

confidence: 99%

“…Q. Wan et al [107] The local alignment model introduces parallax errors as a constraint term into the minimum energy function and uses the mesh-based deformation to accelerate the calculation.…”

Section: Feature-based: Local Hybrid Transformationmentioning

confidence: 99%

Image Mosaicing Applied on UAVs Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Nowadays, feature-matching algorithms have powerful functions and are often used for image stitching [ 29 , 30 , 31 ], positioning, mapping, registration, and other visual tasks. However, using this technology for scenes with sparse textures and tasks requiring a high real-time performance and accuracy remains challenging.…”

Section: Related Workmentioning

confidence: 99%

A Real-Time Registration Algorithm of UAV Aerial Images Based on Feature Matching

Liu

Xiao

et al. 2023

J. Imaging

View full text Add to dashboard Cite

This study aimed to achieve the accurate and real-time geographic positioning of UAV aerial image targets. We verified a method of registering UAV camera images on a map (with the geographic location) through feature matching. The UAV is usually in rapid motion and involves changes in the camera head, and the map is high-resolution and has sparse features. These reasons make it difficult for the current feature-matching algorithm to accurately register the two (camera image and map) in real time, meaning that there will be a large number of mismatches. To solve this problem, we used the SuperGlue algorithm, which has a better performance, to match the features. The layer and block strategy, combined with the prior data of the UAV, was introduced to improve the accuracy and speed of feature matching, and the matching information obtained between frames was introduced to solve the problem of uneven registration. Here, we propose the concept of updating map features with UAV image features to enhance the robustness and applicability of UAV aerial image and map registration. After numerous experiments, it was proved that the proposed method is feasible and can adapt to the changes in the camera head, environment, etc. The UAV aerial image is stably and accurately registered on the map, and the frame rate reaches 12 frames per second, which provides a basis for the geo-positioning of UAV aerial image targets.

show abstract

“…They also proposed a UAV patrol system based on panoramic image stitching and object detection. This system uses the SPHP algorithm [23] which is combined with a region growing algorithm [24] based on image differences to produce panoramic images and to eliminate motion ghosts [25].…”

Section: Releted Workmentioning

confidence: 99%

Implementation of Random Search Algorithm with FSSRS (Fixed Step Size Random Search) for Applicating the Patrol System Based on Mobile Computing

Riady,

Apriani,

Shadiq

2023

International Journal of Advances in Data and Information Syste

View full text Add to dashboard Cite

Environmental security is very influential for the sustainability of human life. In order for environmental security to remain in a safe condition, a system is needed that can control the environment, such as patrolling at every point to ensure that the environmental conditions are safe. However, it is felt that this is not enough if the patrol system is not assisted by tools or systems that are digitalized and integrated with community service officers, such as firefighters, ambulances, and police, and are easy for officers to use when conducting patrols. So, it is necessary to schedule patrols to several points with different routes for each activity so that it is not easily read by unwanted parties in terms of crime. In order for the system to obtain patrol scheduling in a timely and efficient manner, an appropriate and efficient algorithm is needed, the algorithm is random search with FSSRS (Fixed Step Size Random Search) which can suggest random and precise patrol scheduling. From the results of training using four iterations, namely 50, 100, 150, and 200, the best value was produced in the 200th iteration. Data was taken from the results of a case study survey with eight patrol points using coordinates at each point. So, it can be concluded that the FSSRS algorithm is effectively used to randomize patrol points and can be implemented in the application patrol system.

show abstract

Drone Image Stitching Using Local Mesh-Based Bundle Adjustment and Shape-Preserving Transform

Cited by 17 publications

References 57 publications

Image Mosaicing Applied on UAVs Survey

Image Mosaicing Applied on UAVs Survey

A Real-Time Registration Algorithm of UAV Aerial Images Based on Feature Matching

Implementation of Random Search Algorithm with FSSRS (Fixed Step Size Random Search) for Applicating the Patrol System Based on Mobile Computing

Contact Info

Product

Resources

About