Real-time detection method of single-stage multi-scale specific target based on effective receptive field

Abstract

The invention provides a single-stage multi-scale real-time detection method for a specific target based on an effective receptive field. This method first extracts the corresponding feature layers from the multi-scale architecture of SSD, and selects the scale according to the pixel range covered by the receptive field; secondly, we remove the anchor structure in the traditional method and use fewer feature layers. The characteristics of the natural receptive field are used to directly classify and regress the corresponding receptive field frame of the feature map. Finally, the RF (receptive field) sampling frame is grayed out to avoid learning redundant parameters. This method greatly reduces the complexity of the traditional algorithm based on the anchor sampling frame, improves the detection efficiency and can achieve real-time effects, and is very valuable in the application background of a very large amount of data.

Description

technical field [0001] The invention belongs to the field of computers and relates to a single-stage multi-scale real-time detection method for a specific target based on an effective receptive field. Background technique [0002] Big data can be considered as a hot spot in the current academic and industrial research and gradually affects people's daily life and work style. Its characteristics can be considered as large amount of data and diversity, so real-time becomes very important. [0003] With the development of computer and artificial intelligence technology in the image field, target detection has become a very hot topic, and specific target detection is a key step in many subsequent specific target-related applications, such as: specific target recognition, specific target verification, and specific target tracking etc. Convolutional neural networks have achieved remarkable success in recent years. From image classification to object detection, it also motivates...

AI Technical Summary

Problems solved by technology

[0009] Although the anchor-based method has achieved high accuracy and efficiency in today's target detection tasks, however, due to the complexity of its algorithm (a*a*B, a*a is the size of the feature map, B is the number of anchors )

As the amount of data continues to increase, the efficiency of the detector will drop sharply, for example: the calculation efficiency of Faster-RCNN is very low

Images