Target detection tracking method based on yolk neural network, storage medium and equipment

• Main Authors: GUO JINGYAO, TANG YAN
• Format: Patent
• Language: Chinese; English
• Published: 25.10.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention provides a target detection tracking method based on a yolk neural network, a storage medium and equipment, and the method comprises the steps: obtaining a sample data set, and carrying out the preprocessing of the sample data set; obtaining a yolo network structure, and training and detecting at least two different types of detection targets in the sample data set at the same time by using the yolo network structure; post-processing a neural network target detection result; and carrying out image rendering and distortion removal. Compared with the prior art, the target detection tracking method based on the yolo neural network, the storage medium and the equipment provided by the invention shorten the speculation time of the model. 本申请提供了一种基于yolo神经网络的目标检测跟踪方法、存储介质及设备，其中，基于yolo神经网络的目标检测跟踪方法包括获取样本数据集并预处理；获取yolo网络结构，利用yolo网络结构对样本数据集中至少两个不同类别的检测目标同时进行训练与检测；神经网络目标检测结果后处理；图像渲染与去畸变。与相关技术相比，本申请提供的基于yolo神经网络的目标检测跟踪方法、存储介质及设备，缩短了模型的推测时间。