Parking space detection method and system based on deep learning and big data

Abstract

The invention relates to a parking space detection method and system based on deep learning. The method includes: obtaining relevant detection data on whether parking is on the parking space in the parking lot; obtaining relevant states on whether parking is on the parking space in the parking lot; using the relevant detection data as an input of a deep neural network, and converting the relevant state As the output of the deep neural network, train the deep neural network; obtain the relevant detection data of whether there is parking on the parking space to be tested in the parking lot at the current moment; input the relevant detection data into the trained deep neural network for deep learning; The corresponding output of the deep neural network is used as the relevant state of the machine to determine whether there is parking on the parking space to be tested. The present invention adopts deep learning and deep neural network to identify relevant detection data of parking spaces, which can remove the false and keep the true from the ever-changing and interfering parking space detection data, and obtain the state of the parking spaces to achieve a detection accuracy that satisfies users.

Description

technical field [0001] The present invention relates to parking indication in a parking lot, in particular to a parking space detection method based on deep learning and big data, and also to a parking space detection system based on deep learning and big data. Background technique [0002] When the traditional technology detects the parking space, it adopts the threshold method or the pattern recognition method. These two methods have poor anti-interference ability, and cars come and go in the parking lot, different car owners have different parking modes, and different parking spaces suffer from different interferences, so there will be ever-changing detection data in this complex environment, so use fixed Several thresholds or fixed several patterns to identify the relevant state of the parking space, prone to misidentification (for example) can not achieve satisfactory detection accuracy. Contents of the invention [0003] Based on this, it is necessary to provide a p...

AI Technical Summary

Problems solved by technology

These two methods have poor anti-interference ability, and cars come and go in the parking lot, different car owners have different parking modes, and different parking spaces suffer from different interferences, so there will be ever-changing detection data in this complex environment, so use fixed Several thresholds or fixed several patterns to identify the relevant state of the parking space, prone to misidentification (for example) can not achieve satisfactory detection accuracy

Images