Instance segmentation method and device, electronic equipment and storage medium

Abstract

The invention provides an instance segmentation method and device, electronic equipment and a computer readable storage medium. The instance segmentation method comprises the following steps: performing feature extraction processing on a to-be-segmented image to obtain a first global feature map of the to-be-segmented image; performing feature prediction according to the first global feature map to obtain a first instance feature map, a first dynamic convolution feature map and a first classification feature map of the to-be-segmented image; according to the first instance feature map and the first dynamic convolution feature map, obtaining a binary segmentation map of the to-be-segmented image; and obtaining an instance segmentation result of the to-be-segmented image according to the binarization segmentation image and the first classification feature image. According to the method and the device, the problem of position information loss in the process of performing feature extraction on the ROI region is avoided, and the prediction precision of instance segmentation is improved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and specifically relates to an instance segmentation method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] Computer vision uses various imaging systems instead of visual organs as input sensitive means, and the computer replaces the brain to complete processing and interpretation. Among them, instance segmentation is a common processing task in computer vision. Instance segmentation is to distinguish and label each object in the image. Instance segmentation has great guiding significance for behavior recognition, public safety, video surveillance and other fields. [0003] Existing instance segmentation is generally done based on the target detection algorithm. For example, on the basis of the target frame obtained by the target detection algorithm, that is, the ROI (region of interest, region of interest) of the target is ob...

AI Technical Summary

Problems solved by technology

[0005] The present application provides an instance segmentation method, device, electronic equipment, and computer-readable storage medium, aiming to solve the problem of feature map due to the scale adjustment and zooming of the feature layer during the feature extraction process of the ROI region in the existing instance segmentation method. The loss of location information, which in turn causes the problem of low prediction accuracy of instance segmentation

Images