Robot photographing method and device, computer equipment and storage medium

Abstract

The application relates to a robot photographing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a guide image corresponding to a targetobject and type information corresponding to the target object; according to edge information of the target object, extracting saliency maps of the guide image at different candidate positions; for each candidate position, respectively determining an area ratio between the corresponding saliency map and the guide image, determining a first parameter set according to the centers of the corresponding saliency maps and the guide image, and determining a second parameter set according to the boundaries of the corresponding saliency maps and the guide image; constructing an objective function based on differences between the area ratios, the first parameter set, and the second parameter set and corresponding reference values determined by the type information respectively; and taking the candidate position corresponding to the target function when the target function is minimized to be within a preset threshold value as a target position, and photographing the target object at the target position. Therefore, the photographing efficiency of the robot is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method, device, computer equipment and storage medium for taking pictures of a robot. Background technique [0002] With the development of computer technology, unmanned aircraft, or "drone" for short, appeared. UAVs are unmanned aircraft operated by radio-controlled equipment and self-contained program controls, or operated entirely or intermittently autonomously by an on-board computer. UAVs can be equipped with airborne remote sensing equipment, such as high-resolution digital cameras, light optical cameras, infrared scanners, laser scanners, magnetic detectors, etc. to obtain information, and use computers to process image information, and make it according to certain precision requirements. image. At present, the use of UAVs to take pictures of objects is usually done by remotely operating the UAV to an artificially designated location. [0003] However, the...

AI Technical Summary

Problems solved by technology

[0003] However, the current method of taking pictures by drones requires human control of the position information and angle of the pictures, which makes the image capture lack of intelligence, and the quality of the captured images is poor, which leads to low photographing efficiency.

Images