Gesture recognition method based on Head lightweight Mask Scoring R-CNN

Abstract

The invention relates to a gesture recognition method based on a Head lightweight Mask Scoring R-CNN. A lightweight position sensitive score graph and a position sensitive RoIAlign are introduced after an output feature graph of an original Mask Scoring R-CNN backbone network; therefore, the input RoI channel number of the Head structure becomes very small, and two continuous full-connection layers in the Head structure are changed into a single full-connection layer to reduce the calculation amount. According to the method, the DetNet59 is combined with the FPN to serve as a backbone network,so the extracted multi-scale feature map can contain rich semantic information and position information at the same time and can adapt to detection of objects of various sizes. The average accuracy of the instance segmentation model improved by the method is obviously improved, the number of model parameters is effectively reduced, and the training and detection speed of the model is effectivelyimproved.

Description

technical field [0001] The invention relates to a gesture recognition method based on Head lightweight Mask Scoring R-CNN, belonging to the fields of computer vision and deep learning. Background technique [0002] Gesture recognition is an important branch in the field of computer vision. Its core is to use "machine eyes" to replace human eyes to recognize hand gestures in image or video capture devices, and input the captured images or videos into visual algorithms for calculation. Finally get hand information. There are many kinds of vision algorithms mentioned here, such as traditional image processing methods and deep learning methods in recent years. Before the emergence of deep learning, traditional image processing and machine learning methods could not complete a simple image classification task very well, and the emergence of deep learning has made it possible for computers to reach human levels. In fact, the emergence of AlphaGo has proved that in some fields, c...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the precision of the gesture detector in the first stage is not high enough to make a detailed prediction on the gesture mask; the speed of the gesture detector in the second stage is too slow

Images