High-speed service area parking space identification method

Abstract

The high-speed service area parking space identification method comprises the following steps: 1) collecting images of high-altitude cameras in a large number of parking lots and data sets of other vehicles, calibrating the data sets according to on-site management requirements, and determining a used one-stage target detection algorithm model; 2) constructing a parameter self-adaptive loss function; and 3) constructing a loss function LOSS of a one-stage target detection algorithm model. 4) updating the weight of the one-stage target detection algorithm model by adopting a gradient descent method until the model converges; and enabling the trained model to complete detection of vehicles in an actual system, and calculating the number of remaining parking spaces according to the preset total number of on-site parking spaces and the current number of vehicles so as to achieve management of the parking spaces. The method has the advantages that the provided focus loss function can improve the parameter adaptability of the target detection model, and the accuracy of target detection is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of image recognition and computer vision, and relates to a parking space recognition method in a high-speed service area. Background technique [0002] At present, for the detection of parking spaces in high-speed service areas, traditional detection methods mainly include: micro-radar detection, infrared detection, geomagnetic induction coil detection and radio frequency identification technology. This type of method requires the installation of special sensing equipment for each parking space in the parking lot of the high-speed service area, which requires high engineering costs, difficult maintenance in the later period, and high manpower and material costs. Use the security camera in the parking lot of the existing high-speed service area to identify the status of the parking space in real time, and then count the parking space information in this area. Because it utilizes the existing parking lot moni...

AI Technical Summary

Problems solved by technology

Although the two-stage convolutional neural network model has better detection accuracy, its forward reasoning speed is slow and cannot meet the real-time requirements of business scenarios

In the traditional one-stage target detection algorithm model, the algorithm has better real-time performance, but it cannot reach the detection accuracy of the two-stage convolutional neural network model

Images