Deep neural network target detection method integrated with pixel-level attention mechanism

Abstract

The invention relates to a deep neural network target detection method integrated with a pixel-level attention mechanism. The deep neural network target detection method comprises the following steps:collecting a training sample image; converting data in the collected image data set into a format required by training the deep convolutional neural network through preprocessing, and performing dataenhancement to improve the training effect of the neural network; designing a deep convolutional neural network structure integrated with a pixel-level attention mechanism, the network structure being used for receiving an input image and outputting bounding box regression information and category information to an object in the image: the network structure comprising two parts, one part being abasic network for preliminarily extracting features; the other part being a plurality of cascaded convolutional layers or downsampling layers added at the tail end of the basic network and being usedfor extracting convolutional feature maps with different scales and fusing the multi-scale feature maps with a pixel-level attention mechanism; and training.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

In this new technology called Deep Convolution Neural Network (DCNN), an ensemble of neurons are connected together through layers containing filters or connections made up from different parts like pixels on top of each other. These networks work by learning how images look better when they have specific areas within them rather than just looking for certain things inside it. By doing these techniques, DCNs help detect objects more accurately even over long distances compared to previous methods such as Random Forests. Overall, DLC Nets enhance object recognition capabilities while reducing their computation requirements.

Problems solved by technology

This patented technical problem addressed in this patents relates to improving depth learning systems that can recognize complex patterns like faces without losing their shape due to limitations associated with conventional techniques used for recognition purposes. Specifically, current approaches involve embedding hidden layer functions into an entire space called kernel domain, but there may still exist some areas where no significant changes occur during training. Therefore, it becomes necessary to develop better algorithms capable of detecting specific types of targets while maintaining accurate results over large dataset sets.

Images