Cloud three-dimensional map construction method, system and equipment

Abstract

The invention provides a cloud three-dimensional map construction method, system and device and a computer readable storage medium, and the cloud three-dimensional map construction method comprises the steps: employing different communication devices to collect multiple groups of map data; uploading the collected multiple groups of map data to a cloud; in the cloud, carrying out parallel processing on the multiple groups of map data according to a unit of each group through a visual inertial mileage calculation method, and obtaining a processing result of each group of map data; optimizing the processing result, and obtaining and an optimization result; and performing map fusion on each group of optimization results to construct a three-dimensional map. The technical scheme provided by the invention can support multi-device acquisition and is high in efficiency and speed, the algorithm is carried out at the cloud and is not restricted by the computing performance of the platform, parallel processing can be carried out, and efficiency and precision are considered at the same time.

Description

technical field [0001] The present invention relates to the field of communications, and in particular to a cloud-based three-dimensional map construction method, system, device, and computer-readable storage medium. Background technique [0002] 3D visual map is one of the key technologies in fields such as augmented reality, robotics, and unmanned driving. It is the core of technologies such as automatic recognition of the surrounding environment and visual positioning. With the popularization of various sensors, the enhancement of processing power, and the promotion of various application requirements, more and more image data are collected every day, and three-dimensional maps are generated and updated at the same time. [0003] At present, unmanned driving and augmented reality fields have higher and higher requirements for the accuracy and efficiency of 3D maps. On the one hand, efficient collection equipment and methods are required, and on the other hand, high-precis...

AI Technical Summary

Problems solved by technology

At present, most of the mapping systems on the market are independently collected and constructed by a single device, which is inefficient. The existing technology relies on the singleness of external devices, and cannot support the combination of data collected by multiple devices such as mobile phones, robots, AR / VR devices, and sports cameras. Mapping

When the maps collected by multiple devices are duplicated, storage and computing resources are wasted, and the multi-sensor fusion mapping of multiple devices is also a technical problem. Multi-time, multi-time map update and fusion is a complex problem.

At the same time, when collecting data on a large scale, more efficient collection methods are required. The storage of massive data and the processing capacity of the mapping center are also huge challenges. Constraints, there are bottlenecks in the scale, speed and accuracy of mapping

Images