Aerial Image Stitching via Transformation Space Filtering

2020 ◽  
Author(s):  
Hao Wang ◽  
Zhengyan Ding ◽  
Zhiguo Yan
Keyword(s):  
Aerial Image ◽  
Image Stitching ◽  
Transformation Space

scholarly journals Fast and Efficient Method for Large-scale Aerial Image Stitching

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Nam Thanh Pham ◽  
Sihyun Park ◽  
Chun-Su Park
Keyword(s):  
Efficient Method ◽  
Large Scale ◽  
Aerial Image ◽  
Image Stitching

scholarly journals Real-time and automatic map stitching through aerial images from UAV

2021 ◽  
Vol 2120 (1) ◽  
pp. 012025
Author(s):  
J N Goh ◽  
S K Phang ◽  
W J Chew
Keyword(s):  
Real Time ◽  
Matrix Multiplication ◽  
Image Features ◽  
Aerial Images ◽  
Aerial Image ◽  
Process Time ◽  
Image Stitching ◽  
Singular Value Decomposition Method ◽  
Value Decomposition ◽  
Computational Resources

Abstract Real-time aerial map stitching through aerial images had been done through many different methods. One of the popular methods was a features-based algorithm to detect features and to match the features of two and more images to produce a map. There are several feature-based methods such as ORB, SIFT, SURF, KAZE, AKAZE and BRISK. These methods detect features and compute homography matrix from matched features to stitch images. The aim for this project is to further optimize the existing image stitching algorithm such that it will be possible to run in real-time as the UAV capture images while airborne. First, we propose to use a matrix multiplication method to replace a singular value decomposition method in the RANSAC algorithm. Next, we propose to change the workflow to detect the image features to increase the map stitching rate. The proposed algorithm was implemented and tested with an online aerial image dataset which contain 100 images with the resolution of 640 × 480. We have successfully achieved the result of 1.45 Hz update rate compared to original image stitching algorithm that runs at 0.69 Hz. The improvement shown in our proposed improved algorithm are more than two folds in terms of computational resources. The method introduced in this paper was successful speed up the process time for the program to process map stitching.

Aerial Image Stitching Algorithm for Unmanned Aerial Vehicles Based on Improved ORB and PROSAC

2019 ◽  
Vol 56 (23) ◽  
pp. 231003
Author(s):  
李振宇 Li Zhenyu ◽  
田源 Tian Yuan ◽  
陈方杰 Chen Fangjie ◽  
韩军 Han Jun
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Aerial Image ◽  
Image Stitching ◽  
Aerial Vehicles

scholarly journals A FAST APPROACH FOR STITCHING OF AERIAL IMAGES

2016 ◽  
Vol XLI-B3 ◽  
pp. 769-774 ◽  
Author(s):  
A. Moussa ◽  
N. El-Sheimy
Keyword(s):  
Computation Time ◽  
Image Data ◽  
Aerial Images ◽  
Aerial Image ◽  
Image Stitching ◽  
Scale Invariant ◽  
Main Challenge ◽  
Transformation Parameters ◽  
Automatic Image Stitching ◽  
Scale Invariant Feature

The last few years have witnessed an increasing volume of aerial image data because of the extensive improvements of the Unmanned Aerial Vehicles (UAVs). These newly developed UAVs have led to a wide variety of applications. A fast assessment of the achieved coverage and overlap of the acquired images of a UAV flight mission is of great help to save the time and cost of the further steps. A fast automatic stitching of the acquired images can help to visually assess the achieved coverage and overlap during the flight mission. This paper proposes an automatic image stitching approach that creates a single overview stitched image using the acquired images during a UAV flight mission along with a coverage image that represents the count of overlaps between the acquired images. The main challenge of such task is the huge number of images that are typically involved in such scenarios. A short flight mission with image acquisition frequency of one second can capture hundreds to thousands of images. The main focus of the proposed approach is to reduce the processing time of the image stitching procedure by exploiting the initial knowledge about the images positions provided by the navigation sensors. The proposed approach also avoids solving for all the transformation parameters of all the photos together to save the expected long computation time if all the parameters were considered simultaneously. After extracting the points of interest of all the involved images using Scale-Invariant Feature Transform (SIFT) algorithm, the proposed approach uses the initial image’s coordinates to build an incremental constrained Delaunay triangulation that represents the neighborhood of each image. This triangulation helps to match only the neighbor images and therefore reduces the time-consuming features matching step. The estimated relative orientation between the matched images is used to find a candidate seed image for the stitching process. The pre-estimated transformation parameters of the images are employed successively in a growing fashion to create the stitched image and the coverage image. The proposed approach is implemented and tested using the images acquired through a UAV flight mission and the achieved results are presented and discussed.

Sign in / Sign up

Export Citation Format

Share Document