Vehicle detection method with granularity-level multi-scale characteristic based on asymmetric convolution

Abstract

The invention discloses a vehicle detection method with granularity-level multi-scale characteristic based on asymmetric convolution. The method comprises the following steps: S1, obtaining a plurality of pictures containing vehicles through a video stream, and making a vehicle target detection data set which comprises a training set and a test set; S2, designing an asymmetric convolution AC unit;S3, embedding the asymmetric convolution AC unit into a Res2Net module to construct an asymmetric convolution ACB module with a granularity level multi-scale characteristic; S4, embedding an ACB module into a lightweight model ShuffleNetV2 to construct a vehicle target classification network ACBNet based on a convolutional neural network; S5, training a vehicle target classification network ACBNet by using the manufactured vehicle target training set; and S6, putting test set pictures into the classification network ACBNet for classification, then processing the test set pictures through a residual error prediction module to obtain category and position information of vehicles in the predicted images or videos, and framing out vehicle targets.

Description

technical field [0001] The invention relates to the technical field of video detection in deep learning, in particular to a vehicle detection method with granularity-level multi-scale characteristics based on asymmetric convolution. Background technique [0002] In recent years, with the growth of market demand and the continuous development of artificial intelligence, autonomous driving has gradually become one of the hot issues studied by various scholars. As an important step in automatic driving, vehicle target detection is also one of the main research issues. In intelligent traffic surveillance video, object detection technology has also been widely used. Vehicle detection technology is to use computer vision technology to judge whether there is a vehicle in a static image or a dynamic video and locate the position information of the vehicle. In real-life traffic scenarios, vehicle object detection is interfered by many factors, such as: illumination, occlusion, etc....

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the deficiencies in the prior art, the present invention provides a vehicle detection method with granularity-level multi-scale characteristics based on asymmetric convolution to solve the problem of prior art Problems with low real-time performance and robustness, and relatively poor multi-scale problem detection performance

Images