Method for detecting small and medium objects in a structured road based on deep learning

Abstract

A method for detecting small objects in a structured road based on deep learning comprises the steps that image data, containing the small objects, on the real structured road are collected, and the positions and the category information of the small objects in the structured road are marked through a manual method; Constructing a deep convolutional neural network suitable for small object detection in the structured road and a corresponding loss function; Inputting the acquired image and the labeled data into the convolutional neural network constructed in the previous step, updating the parameter value in the neural network according to the loss value between the output value and the target value, and finally obtaining an ideal network parameter. The invention provides a brand new network structure for the problem that the current neural network is poor in small object detection. On the premise that the calculated amount is not increased basically, the performance of small object detection is greatly improved, and the method can be conveniently deployed in an existing intelligent driving system, so that an intelligent driving automobile can detect dangerous objects on a road in along distance and respond in time, and the safety in the driving process is improved.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving, and in particular relates to a target detection method in a specific scene combining computer vision with deep learning. Background technique [0002] Object detection is one of the basic tasks in the field of computer vision. In recent years, with the rapid development of deep learning technology, object detection algorithms have also shifted from traditional algorithms based on manual features to detection technologies based on deep neural networks. The method of target detection has developed from the initial R-CNN and OverFeat to the more mature Fast / Faster R-CNN, SSD, YOLO series, until the latest CornerNet, from the PC side to the mobile phone side, many good ones have emerged. Algorithmic technology, these algorithms have excellent detection effects and performance on open object detection datasets. However, deep convolutional networks are currently used for general object det...

AI Technical Summary

Problems solved by technology

[0003] First, the downsampling degree of the existing deep convolutional network is relatively large, and the small objects in the image have fewer pixels, and the information will be lost during the downsampling process, resulting in the network being unable to output the detection results of small objects;

[0004] Second, the existing deep convolutional network is to detect objects on the whole image, which takes a long time, takes up a lot of resources, and is prone to problems such as misidentification

Images