Small target vehicle attribute identification method based on feature fusion

Abstract

The invention relates to the technical field of target attribute identification, and provides a small target vehicle attribute identification method based on feature fusion. The method comprises: firstly, constructing a small target vehicle attribute recognition network based on feature fusion, comprising a feature pyramid network, a regional nomination network and a small-size target cascade network; inputting a traffic image to be detected into the feature pyramid network, generating a feature map containing low-level edge detail information, middle-level stacking fusion scale information and high-level semantic information, and stacking and fusing the feature map to obtain a multi-scale feature map; inputting the multi-scale feature map into a regional naming network to generate a candidate box containing a target; inputting the multi-scale feature map and the candidate box into a small-size target positioning network at the same time, outputting target coordinate information, and cutting a target according to the information; and finally, inputting the sheared target into a small-size target classification network, and identifying and outputting the target and the category thereof. According to the invention, the accuracy of small-size target attribute identification can be improved, and the false identification rate and the missing identification rate are reduced.

Description

technical field [0001] The invention relates to the technical field of target attribute recognition, in particular to a feature fusion-based small target vehicle attribute recognition method. Background technique [0002] The main function of target attribute recognition is to identify and locate the target that people are interested in from the input image, and predict the target's attributes, including target location and classification information. At present, the target attribute recognition technology has been widely used in the intelligent urban traffic system, which can effectively relieve the pressure of the traffic control department on the traffic control of each road section. [0003] At present, traditional target attribute recognition methods include target attribute recognition methods based on pixel features, target attribute recognition methods based on feature description, target attribute recognition methods based on traditional pattern recognition, and tar...

AI Technical Summary

Problems solved by technology

[0008] However, none of the existing small target attribute recognition methods combine the feature pyramid network with the location classification cascade network and apply PReLU and FocalLoss for small target attribute recognition. When the ratio of the recognition target area to the entire image area is less than a certain threshold, the target cannot be accurately located or even lost, resulting in serious misidentification and missed recognition.

Images