Geo-Location Algorithm for Building Targets in Oblique Remote Sensing Images Based on Deep Learning and Height Estimation

Abstract

To improve the accuracy of the geographic positioning of a single aerial remote sensing image, the height information of a building in the image must be considered. Oblique remote sensing images are essentially two-dimensional images and produce a large positioning error if a traditional positioning algorithm is used to locate the building directly. To address this problem, this study uses a convolutional neural network to automatically detect the location of buildings in remote sensing images. Moreover, it optimizes an automatic building recognition algorithm for oblique aerial remote sensing images based on You Only Look Once V4 (YOLO V4). This study also proposes a positioning algorithm for the building target, which uses the imaging angle to estimate the height of a building, and combines the spatial coordinate transformation matrix to calculate high-accuracy geo-location of target buildings. Simulation analysis shows that the traditional positioning algorithm inevitably leads to large errors in the positioning of building targets. When the target height is 50 m and the imaging angle is 70°, the positioning error is 114.89 m. Flight tests show that the algorithm established in this study can improve the positioning accuracy of building targets by approximately 20%–50% depending on the difference in target height.

Precise Target Geo-Location of Long-Range Oblique Reconnaissance System for UAVs

“…The deviation of the projection point from the CCD center is m pixels and n pixels in the X C and Y C direction. Sensors 2022, 22,1903 4 of 25…”

“…In order to solve the problem that DEM data does not include the height information of a building, a geo-location algorithm for building targets, based on the image method, was proposed in [22]. A convolutional neural network was used to automatically detect the location of buildings, and the imaging angle was used to estimate the height of a building.…”

Long Distance Ground Target Tracking with Aerial Image-to-Position Conversion and Improved Track Association

“…This approximate conversion consi and y directions separately. Thus, a simple reverse process is possible from posit image, and it will be shown that the detection result is significantly improved in t periments although the coordinate conversion can be accompanied by various inev errors [28,29]. In the experiments, the altitude h is set to 400 m; W and H are 3840 and 2160 pixels; a x and a y are set to AFOV of the camera, 70 • and 40 • , respectively; θ T is set to 60 • ; thus y H/2 is calculated at 692.8 m by Equation (1), and d H/2 is 800 m accordingly.…”

“…This approximate conversion consi and y directions separately. Thus, a simple reverse process is possible from posit image, and it will be shown that the detection result is significantly improved in t periments although the coordinate conversion can be accompanied by various inev errors[28,29].…”

Systematic Error Correction for Geo-Location of Airborne Optoelectronic Platforms

“…In all the above references, the authors either didn't take into account the effect of the systematic error [4,19,24,25], or just introduced it as a fixed bias [6,8]. Eliminating systematic error is the basis for improving the accuracy of target geo-location since it directly affects the geo-location accuracy and the filtering algorithms [6,[13][14][15][16][17] cannot eliminate systematic error.…”