A vehicle multi-attribute detection method based on single-network multi-task learning

Abstract

The invention discloses a vehicle multi-attribute detection method based on single-network multi-task learning. The method comprises the following steps of collecting and screening pictures; making adata set; carrying out network design on the basis of a Darknet deep learning framework, designing a network structure by adopting an end-to-end and one-stage non-cascade mode according to the characteristic of multiple attributes of the vehicle, and constructing a network model; carrying out model training, setting and adjusting model parameters, training a vehicle multi-attribute data set according to a designed network model, and carrying out data enhancement and multi-scale training during training; and carrying out model testing and model evaluation. The Darknet-based deep learning framework platform is designed according to the Darknet-based deep learning framework platform; a network model is built and is of an end-to-end one-stage non-cascade structure, the network improves the detection effect of multiple attributes of a vehicle by adopting the technologies of data enhancement, convolution kernel separation, multi-scale feature fusion and the like, and better real-time performance is achieved while the higher detection accuracy and recall ratio are achieved.

Description

technical field [0001] The invention relates to the technical field of target detection in the direction of computer vision, in particular to a vehicle multi-attribute detection method based on single-network multi-task learning. Background technique [0002] With the continuous development of the economy, automobiles have become the most important means of transportation for people. While providing convenience to people, problems such as road traffic congestion and vehicle supervision caused by them are becoming more and more serious. Intelligent transportation systems and vehicle supervision systems have been generally recognized by the public. As part of smart cities, they are mainly used in road traffic management, public security criminal investigation, parking lot monitoring, and intelligent community management. With the advent of the information age, how to efficiently achieve real-time vehicle detection (that is, vehicle positioning and identification) and accurate ...

AI Technical Summary

Problems solved by technology

[0006] (1) The scale difference of different attributes of vehicles is not considered

[0007] (2) The size of the convolution kernel used by the network is too large, resulting in too many parameters for network training, and the amount of calculation increases and it is easy to overfit

[0008] (3) It does not consider that the vehicle photos in the actual scene are easily affected by factors such as resolution, rotation angle, saturation, exposure, and hue

[0009] (4) Defects in the above three aspects lead to high complexity, low accuracy, high missed detection rate, and poor real-time performance of vehicle multi-attribute detection

Images