Multi-human-body-posture estimation detection and segmentation optimization method and device based on instance segmentation

Abstract

The invention discloses a multi-human-body-posture estimation detection and segmentation optimization method and device based on instance segmentation, and the method comprises the following steps: 1, collecting a frame of image at regular intervals, and carrying out the preprocessing of the image through the instance segmentation; 2, based on instance segmentation, different human individuals are marked with masks of different colors, key points of human body postures are marked, and the human body postures are estimated and detected; according to the method, different human individuals are marked with masks of different colors based on instance segmentation, key points of human body postures are marked, the human body postures are estimated and detected, the masks of the corresponding colors are continuously used for marking the different human individuals, and the key points of the human body postures are continuously marked until the human body postures can be estimated and detected. Finally, difference judgment is conducted on the human body posture estimation detection result, the human body posture estimation detection result is obtained, dynamic detection is conducted on the human body posture, and the detection precision is improved.

Description

technical field [0001] The invention belongs to the technical field of multi-human body posture estimation and detection, and in particular relates to a multi-human body posture estimation detection and segmentation optimization method and device based on instance segmentation. Background technique [0002] Object detection or localization is a progressive process from coarse to fine digital images. It not only provides the class of the image object, but also the location of the object in the classified image. The position is given as a border or center. Semantic segmentation gives better reasoning by predicting the label of each pixel in the input image. Each pixel is labeled according to the object class it is in. For further development, instance segmentation provides different labels for individual instances of objects belonging to the same class; therefore, instance segmentation can be defined as a technique that simultaneously solves the problem of object detection ...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the existing defects and provide a method and device for multi-human pose estimation detection and segmentation optimization based on instance segmentation, so as to solve the problem of being easily frustrated in the face of occlusion proposed in the above-mentioned background technology, The detection accuracy is low, resulting in a large deviation in the human body pose estimation results

Images