Real-time target detection method based on region convolutional neural network

Abstract

The invention provides a real-time target detection method based on a region convolutional neural network. The real-time target detection method mainly comprises an input image, a target detection system, alternative optimization learning and sharing, and classifier classification and detection. The real-time target detection method comprises the steps of: regarding an image of any size as input, inputting a plurality of regions of interest (RoIs) while inputting the image, proposing a detection region by means of a region proposal network (RPN), utilizing the proposed detection region by an R-CNN detector, sharing all spatial positions by means of complete connection layers, learning shared characteristics by adopting alternative training optimization, and carrying out classification detection by using the classifier. According to the real-time target detection method, the RPNs are used for generating region proposals, and the network parameters are reduced by using shared weights, thus the region proposing step costs almost nothing; and the region proposal network (RPN) and the region convolutional neural network (R-CNN) share two network between a convolutional layer, thereby the cost is significantly reduced, the detection speed is fast, and the efficiency is high.

Description

Technical field [0001] The invention relates to the field of target detection, in particular to a real-time target detection method based on a regional convolutional neural network. Background technique [0002] Object detection can quickly detect various objects in images such as humans, animals, food, homes, etc., and can be used in many fields such as security and transportation. In recent years, the progress in the field of target detection is mainly composed of region suggestion methods and region-based convolution Contributed by neural network. Although the area-based neural network is computationally expensive compared with traditional methods, it costs more in space and time, and the object detection speed is slow, which is the bottleneck encountered in the current detection system test calculation time. [0003] The present invention proposes a real-time target detection method based on a regional convolutional neural network, which mainly includes an input image, a targe...

AI Technical Summary

Problems solved by technology

Although the area-based neural network is computationally expensive compared to the traditional method, it costs more in space and time, and the object detection speed is slow, which is the bottleneck encountered in the test calculation time of the detection system at this stage.

Images