Object detection method, system and medium for fusion of feature layers of receptive fields at different scales

Abstract

The present invention provides a target detection method, system and medium for fusion of feature layers of receptive fields of different scales, including: a step of increasing the amount of data: performing incremental processing on the labeled training data set, increasing the data amount of the training data set, adjusting The training image size of the training data is the same as the model input scale, and the training data set after data increase is obtained; the target detection network model building steps: the classic network model is used as the network basis of the target detector, and the dense connection is used instead of the feature pyramid network in FPN Horizontally connected to obtain a densely connected FPN object detection network model. The present invention improves the shortcoming of the existing target detection model that only uses feature information in part of the feature layers to detect target objects, and fuses multiple feature layers with different receptive fields through FPN dense connection, and can obtain objects that are beneficial to multiple scale ranges. The required feature information can improve the feature extraction ability and target detection performance of the target detector.

Description

technical field [0001] The invention relates to the field of intelligent detection and recognition of target objects in images, in particular to a target detection method, system and medium for fusion of feature layers of receptive fields of different scales. In particular, it relates to a target detection method based on the fusion of feature information in different feature layers based on deep learning Background technique [0002] Object Detection is an important basic research field in computer vision. Its main work is to locate the object of interest (ROI) in the image (Localization) and classify the category of the object ROI (Classification). Before the emergence of the convolutional neural network model (CNN), the main research method of target detection was to manually extract the feature information required for target object detection in images, while the deep learning-based target detector (CNN-based Object Detector) relies on Its excellent feature extraction a...

AI Technical Summary

Problems solved by technology

[0004] Although FPN solves the problem of spatial information loss to a certain extent, the detection effect of extreme-scale objects is still not ideal. The study found that the feature information required for object detection at a certain scale is not only distributed on the feature layer corresponding to its scale, but also There is a large amount of relevant information distributed on other feature layers, and only obtaining the feature information contained in a single-layer feature layer cannot meet the needs of target detection

Images