Lightweight deep network image target detection method suitable for Raspberry Pi

Abstract

A lightweight deep network image target detection method applicable to Raspberry Pi belongs to the field of deep learning and target detection, and comprises the following steps: firstly, collecting an image containing a to-be-detected target, and preprocessing the collected image for network training; secondly, inputting the preprocessed image into a depth separable expansion convolutional neural network for feature extraction to obtain feature maps with different resolutions; inputting the feature maps with different resolutions into a feature pyramid network for feature fusion, and generating a fusion feature map carrying richer information; and then carrying out classification and positioning of a to-be-detected target on the fusion feature map by adopting a detection network, and finally carrying out non-maximum suppression to obtain an optimal target detection result. The image target detection method based on the deep neural network overcomes the difficulties that the image target detection method based on the deep neural network is difficult to realize on the Raspberry Pi platform and the image target detection method based on the lightweight network is low in detection accuracy on the Raspberry Pi platform.

Description

technical field [0001] The invention belongs to the field of deep learning and target detection, and in particular relates to a lightweight deep network image target detection method suitable for Raspberry Pi. Background technique [0002] Object detection is a fundamental task in computer vision. The main purpose of object detection is to locate objects of interest from an input image or video, accurately classify the category of each object, and provide a bounding box for each object. The early target detection technology used the method of manually extracting features, and combined the manually extracted features with a classifier to achieve the target detection task. The method of manually extracting features is not only complicated, but also the extracted features do not have good expressive ability and robustness, so the researchers proposed a target detection method based on convolutional neural network. The convolutional neural network can learn the useful features...

AI Technical Summary

Problems solved by technology

With the deepening of the network level, the hardware resources required for training the model have changed from ordinary hardware platforms to large-scale high-performance servers, and large-scale intensive calculations enable deep detection models to be implemented on resource-limited micro-computing platforms (such as Raspberry Pi). become difficult

In view of the above problems, the current technical solution is mainly to compress and accelerate the deep convolutional neural network, reduce the network parameters and the amount of calculation, so that the memory usage and computing power of the deep neural network model meet the requirements of low configuration, but the cost is accurate detection performance drops drastically

Images