Deep learning technology-based field investigation method and system

Abstract

The invention provides a deep learning technology-based field investigation method and system. The method comprises the steps of S101, obtaining a deep learning model and a proof photo obtained by training a deep learning platform based on a sample set; S102, obtaining an identification type result of the proof photograph through a deep learning model, judging whether the proof photograph of the same target pattern spot has feature consistency or not according to the identification type result of the proof photograph, if yes, executing S103, and if not, executing S104; S103, analyzing and judging by using a rule engine according to the identification type result of the proof photograph in combination with the current land utilization situation so as to obtain an investigation result of thetarget pattern spot; and S104, determining that the proof photograph does not have feature consistency. According to the method, the land type corresponding to the proof photo can be automatically recognized through the deep learning model, recognition is more accurate, repeated work is avoided by reminding the abnormal photo which does not meet the requirement, the survey result is obtained through the rule engine, the speed is high, and errors are not likely to happen.

Description

technical field [0001] The invention relates to the field of land survey, in particular to a field survey method and system based on deep learning technology. Background technique [0002] National land survey is the basic work to find out the status of land use. In order to accurately find out the use nature of each piece of land, investigators need to carry out field surveys. According to the corresponding survey rules, the data of farmland and other land types are judged, and on-site photos reflecting the characteristics of the land types are collected as evidence. [0003] The current technical scheme of national land survey mainly integrates the work process in the way of man-machine combination, and the specific operation and rule analysis and judgment are still mainly carried out manually. However, the national land survey is quite professional and complex, requiring investigators to have corresponding experience and ability in land use feature recognition, photo sho...

AI Technical Summary

Problems solved by technology

[0004] (1) The existing technical schemes identify land use characteristics (land use conditions, planting conditions, etc.) based on the subjective cognition of investigators, and there are many people involved in the survey work, so it is difficult to unify the standard through quantitative methods for subjective cognition

[0005] (2) The existing technical solutions cannot control the rationality and shooting quality of the collected photos in real time, and cannot promptly remind typical errors such as inadequate execution of shooting requirements and unreasonable shooting methods, and can only be manually checked afterwards and re-shot, resulting in Repeated work

[0006] (3) The national land survey rules are relatively complex, involving the analysis and comparison of the proportion and area of ​​land use status, permanent basic farmland and other data, and the logic is mutually constrained

Existing technical solutions rely on manual and mechanical execution against rules, which is slow and error-prone

Images