The embodiment of the invention provides a target object state recognition method and device, a storage medium and an electronic device, and the method comprises the steps: obtaining a target frame image which is an image obtained through the photographing of a target object; identifying the target frame image based on a first rule to obtain a first state identification result of the target object; analyzing the target frame image by using a first model to obtain a second state recognition result of the target object, wherein the first model is obtained by performing machine learning trainingon an initial model by using multiple groups of data, and each group of data in the multiple groups of data includes a frame image and a state recognition result of the object included in the frame image; and synthesizing the first state identification result and the second state identification result to determine the state of the target object. According to the method and the device, the problemof inaccurate target object state identification in related technologies is solved, and the identification accuracy is improved.
本发明实施例提供了一种目标对象状态识别方法、装置、存储介质及电子装置,其中,该方法包括:获取目标帧图像,其中,目标帧图像为对目标对象进行拍摄所得到的图像;基于第一规则对目标帧图像进行识别,以得到目标对象的第一状态识别结果;使用第一模型对目标帧图像进行分析,以得到目标对象的第二状态识别结果,其中,第一模型为使用多组数据通过对初始模型进行机器学习训练所得到的,多组数据中的每组数据均包括:帧图像和帧图像中包括的对象的状态识别结果;综合第一状态识别结果和第二状态识别结果确定目标对象的状态。通过本发明,解决了相关技术中存在的目标对象状态识别不准确的问题,提高了识别的准确率。
Target object state recognition method and device, storage medium and electronic device
目标对象状态识别方法、装置、存储介质及电子装置
2020-10-16
Patent
Electronic Resource
Chinese
Target object detection method and device, electronic device and storage medium
European Patent Office | 2025
|Target object screening method and device, electronic device, storage medium and vehicle
European Patent Office | 2023
|Target object determination method and device, electronic equipment and storage medium
European Patent Office | 2022
|European Patent Office | 2023
|Target object track prediction method and device, storage medium and electronic equipment
European Patent Office | 2022
|