Stitching quality evaluation method and system and redundancy reduction method and system for low-altitude unmanned aerial vehicle remote sensing images

A stitching quality evaluation system for low-altitude unmanned aerial vehicle (UAV) remote sensing images, the system comprising a processor and a memory storing instructions that, when executed by the processor, cause the system:

• to acquire ground images by utilizing a UAV under a preset overlap degree to obtain a low-altitude UAV remote sensing image set under the preset overlap degree, wherein the low-altitude UAV remote sensing image set comprises a plurality of remote sensing images, and the remote sensing images are visible images or multispectral images, and a lower limit of the preset overlap degree is determined under a condition that the obtained low-altitude UAV remote sensing image set is able to be stitched and an upper limit of the preset overlap degree is determined according to a camera exposure time, a camera sensor size, a pixel size and a UAV flight speed under a condition that the obtained low-altitude UAV remote sensing image set is not distorted;
• to stitch the low-altitude UAV remote sensing image set to obtain a stitched image;
• and
• to perform a quality evaluation on the stitched image by utilizing an improved BRISQUE algorithm to obtain an image quality score.

A redundancy reduction method for low-altitude unmanned aerial vehicle (UAV) remote sensing images, comprising:

• acquiring ground images by utilizing a UAV under a preset overlap degree to obtain a low-altitude UAV remote sensing image set under the preset overlap degree, wherein the low-altitude UAV remote sensing image set comprises a plurality of remote sensing images, and the remote sensing images are visible images or multispectral images;
• performing a quality evaluation on each remote sensing image by utilizing an improved BRISQUE algorithm to obtain an image quality score;
• taking a lower limit of the preset overlap degree as a fixed redundancy interval;
• performing a redundancy reduction on the low-altitude UAV remote sensing image set according to the fixed redundancy interval and the image quality score of each remote sensing image to obtain a redundancy-reduced image set;
• determining whether the redundancy-reduced image set is able to be stitched or not;
• when the redundancy-reduced image set can be stitched, increasing the fixed redundancy interval by 1 to obtain a new redundancy interval, taking the new redundancy interval as a fixed redundancy interval of a next cycle, and returning to the step of performing the redundancy reduction on the low-altitude UAV remote sensing image set according to the fixed redundancy interval and the image quality score of each remote sensing image;
• and
• when the redundancy-reduced image set is unable to be stitched, stitching a redundancy-reduced image set obtained in a previous cycle to obtain a stitched image.

A redundancy reduction system for low-altitude unmanned aerial vehicle (UAV) remote sensing images, the system comprising a processor and a memory storing instructions that, when executed by the processor, cause the system:

• to acquire ground images by utilizing a UAV under a preset overlap degree to obtain a low-altitude UAV remote sensing image set under the preset overlap degree, wherein the low-altitude UAV remote sensing image set comprises a plurality of remote sensing images, and the remote sensing images are visible images or multi spectral images;
• to perform a quality evaluation on each remote sensing image by utilizing an improved BRISQUE algorithm to obtain an image quality score;
• to take a lower limit of the preset overlap degree as a fixed redundancy interval and perform a redundancy reduction on the low-altitude UAV remote sensing image set according to the fixed redundancy interval and the image quality score of each remote sensing image to obtain a redundancy-reduced image set;
• to determine whether the redundancy-reduced image set can be stitched or not;
• when the redundancy-reduced image set can be stitched, increase the fixed redundancy interval by 1 to obtain a new redundancy interval, take the new redundancy interval as a fixed redundancy interval of a next cycle, and return to the step of performing the redundancy reduction on the low-altitude UAV remote sensing image set according to the fixed redundancy interval and the image quality score of each remote sensing image;
• and
• when the redundancy-reduced image set is unable to be stitched, stitch a redundancy-reduced image set obtained in a previous cycle to obtain a stitched image.