Target detection method and device and electronic equipment

Abstract

The embodiment of the invention provides a target detection method. The method comprises the steps that based on a preset feature extractor, conducting multi-layer convolution operation on an obtainedimage to be detected, target feature maps corresponding to at least two layers of target convolution operations are obtained, and the at least two layers of target convolution operations at least comprise the last layer of convolution operation; based on a preset region extraction network model and a target feature map corresponding to the last layer of convolution operation, determining region position information of a suspected target region of the to-be-detected image; and based on a preset classification model, the obtained target feature map and the determined area position information of the suspected target area, obtaining target information from the to-be-detected image, the target information comprising the target type and the target position information of the target object in the to-be-detected image. By applying the embodiment of the invention, more accurate detection of the target object can be realized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a target detection method, device and electronic equipment. Background technique [0002] The existing target detection process is generally as follows: First, based on the pre-trained feature extractor, a series of convolution and pooling operations are performed on the image to be detected to perform feature extraction and downsampling of the image to be detected; then, the final volume The first feature map obtained after the product operation is completed, and the pre-trained RPN (Region Proposal Network, region extraction network) model is used to extract a plurality of suspected target regions based on the obtained first feature map (that is, the suspected target object is in the area to be detected. The location area in the image); further, based on the extracted multiple suspected target areas, the region pooling operation is performed on the obtained first featu...

AI Technical Summary

Problems solved by technology

However, the deeper the feature, the less detailed information it has on the target object, which easily causes the problem that the detection of the smaller target object in the image to be detected is more difficult or even impossible to detect

It can be seen that in the existing target detection process, there will be problems such as inaccurate or even difficult detection of small target objects.

Images