An Effective Correction Method for Seriously Oblique Remote Sensing Images Based on Multi-View Simulation and a Piecewise Model

Wang, Chun-Yuan; Liu, Xiang; Zhao, Xiaoli; Wang, Yongqi

doi:10.3390/s16101725

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, in a previous paper [ 30 ], the orientation process of oblique aerial images is presented based on the Binary Robust Independent Elementary Features (BRIEF) descriptor. The effective method of geometric correction of remote sensing images using the SIFT and Affine-Scale Invariant Feature Transform (ASIFT) algorithm is also presented in a previous research [ 66 ], where the authors obtained geometric correction errors in the range from 0.63 to 3.74 pixels in the image defocus function from 30° to 70°. In other studies [ 67 ], similar results were obtained by mosaicking UAV images based on SIFT descriptor and RANSAC to remove the wrong matching points.…”

Section: Discussionmentioning

confidence: 99%

Multi-Camera Imaging System for UAV Photogrammetry

Wierzbicki

2018

Sensors

View full text Add to dashboard Cite

In the last few years, it has been possible to observe a considerable increase in the use of unmanned aerial vehicles (UAV) equipped with compact digital cameras for environment mapping. The next stage in the development of photogrammetry from low altitudes was the development of the imagery data from UAV oblique images. Imagery data was obtained from side-facing directions. As in professional photogrammetric systems, it is possible to record footprints of tree crowns and other forms of the natural environment. The use of a multi-camera system will significantly reduce one of the main UAV photogrammetry limitations (especially in the case of multirotor UAV) which is a reduction of the ground coverage area, while increasing the number of images, increasing the number of flight lines, and reducing the surface imaged during one flight. The approach proposed in this paper is based on using several head cameras to enhance the imaging geometry during one flight of UAV for mapping. As part of the research work, a multi-camera system consisting of several cameras was designed to increase the total Field of View (FOV). Thanks to this, it will be possible to increase the ground coverage area and to acquire image data effectively. The acquired images will be mosaicked in order to limit the total number of images for the mapped area. As part of the research, a set of cameras was calibrated to determine the interior orientation parameters (IOPs). Next, the method of image alignment using the feature image matching algorithms was presented. In the proposed approach, the images are combined in such a way that the final image has a joint centre of projections of component images. The experimental results showed that the proposed solution was reliable and accurate for the mapping purpose. The paper also presents the effectiveness of existing transformation models for images with a large coverage subjected to initial geometric correction due to the influence of distortion.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Camera Imaging System for UAV Photogrammetry

Wierzbicki

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…However, due to the special bird’s eye view image acquisition mode, as shown in Figure 1 , RS images have different degrees of affine transformation and scale changes [ 6 ], which make traditional methods ineffective. Figure 2 shows the image deformation caused by the change of the external orientation elements of the imaging sensor, in which the change of location X Y Z and the azimuth angle K produce linear deformations, such as translation, scale, and rotation deformations, while changing the yaw angle

and pitch angle

causes the nonlinear deformation of the image.…”

Section: Introductionmentioning

confidence: 99%

Scene Recognition Using Deep Softpool Capsule Network Based on Residual Diverse Branch Block

Wang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

With the improvement of the quality and resolution of remote sensing (RS) images, scene recognition tasks have played an important role in the RS community. However, due to the special bird’s eye view image acquisition mode of imaging sensors, it is still challenging to construct a discriminate representation of diverse and complex scenes to improve RS image recognition performance. Capsule networks that can learn the spatial relationship between the features in an image has a good image classification performance. However, the original capsule network is not suitable for images with a complex background. To address the above issues, this paper proposes a novel end-to-end capsule network termed DS-CapsNet, in which a new multi-scale feature enhancement module and a new Caps-SoftPool method are advanced by aggregating the advantageous attributes of the residual convolution architecture, Diverse Branch Block (DBB), Squeeze and Excitation (SE) block, and the Caps-SoftPool method. By using the residual DBB, multiscale features can be extracted and fused to recover a semantic strong feature representation. By adopting SE, the informative features are emphasized, and the less salient features are weakened. The new Caps-SoftPool method can reduce the number of parameters that are needed in order to prevent an over-fitting problem. The novel DS-CapsNet achieves a competitive and promising performance for RS image recognition by using high-quality and robust capsule representation. The extensive experiments on two challenging datasets, AID and NWPU-RESISC45, demonstrate the robustness and superiority of the proposed DS-CapsNet in scene recognition tasks.

show abstract

“…The perspective effect is due to oblique shooting, so it can be eliminated by vertical correction. However, the correction of oblique images typically depends on the control points information of the scene (Wang et al, 2011;Wang et al, 2016) or the 3D information of the scene (Habib et al, 2007;Dong et al, 2019). Information of this sorts is difficult to obtain in the case of fully mechanized mining faces, making it a challenge to correct the video obliquity.…”

Section: Introductionmentioning

confidence: 99%

Video Stitching method for a Surveillance System Deployed at a Fully Mechanized Mining Face

Li¹,

Yang²,

Mao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Using video stitching technology, video images with overlapping parts can be stitched into a complete image, with characteristics such as intuitiveness, visualization, and measurable analysis. This technology could be applied in the operation of coal mines for a remote monitoring and control of coal production. However, when the technology is used in coal mines, there are several challenges such as non-uniform illumination, missing scenes, and oblique panorama. In this paper, methods were purposed to solve the above problems: (1) To overcome the non-uniform illumination on a mining face, we applied the wide dynamic range technology to the images from a single camera and histogram matching algorithm on multiple images to reduce the color difference between the images; (2) To overcome the missing scene problem due to the narrow field of view (FOV) of a single camera, the SURF matching and template recognition methods are combined to achieve a stable stitching; (3) To overcome the oblique panorama issue, we applied the vertical correction technology exploiting the posture information of the camera, and then the adjacent images are concatenated. The results of practical experiments show that the proposed methods are suitable for solving the above problems in a fully mechanized mining face. The research provides a new approach for displaying extended scenes of stope faces in the intelligent collieries.

show abstract

An Effective Correction Method for Seriously Oblique Remote Sensing Images Based on Multi-View Simulation and a Piecewise Model

Cited by 4 publications

References 25 publications

Multi-Camera Imaging System for UAV Photogrammetry

Multi-Camera Imaging System for UAV Photogrammetry

Scene Recognition Using Deep Softpool Capsule Network Based on Residual Diverse Branch Block

Video Stitching method for a Surveillance System Deployed at a Fully Mechanized Mining Face

Contact Info

Product

Resources

About