The invention relates to the technical field of intelligent traffic, and discloses a vehicle collision detection method based on a deep residual shrinkage network and a device thereof, and the method specifically comprises the following steps: S1, collecting real-time audio data of a vehicle collision accident-prone section as sample data, and carrying out the category labeling of the audio data; S2, preprocessing the collected audio data; S3, performing feature calculation on the preprocessed audio data; S4, performing feature fusion; S5, constructing a deep residual shrinkage network model, carrying out model training, and storing the trained model; and S6, predicting vehicle collision: performing preprocessing, feature calculation and feature fusion on a new input sample, inputting the new input sample into the stored model, and calculating the probability value of the new input sample belonging to each category so as to judge whether vehicle collision occurs or not. According to the method, noise can be better eliminated, the precision of the model is improved, and finally the precision of vehicle collision prediction is improved.
本申请涉及智能交通技术领域,公开了一种基于深度残差收缩网络的车辆碰撞检测方法及装置,具体包括以下步骤:S1、采集车辆碰撞事故多发地段的实时音频数据作为样本数据,并对音频数据进行类别标注;S2、对采集的音频数据进行预处理;S3、对预处理后的音频数据进行特征计算;S4、特征融合;S5、构造深度残差收缩网络模型并进行模型训练,保存训练好的模型;S6、车辆碰撞预测,对新的输入样本做预处理、特征计算以及特征融合后输入至保存好的模型中,计算其属于每个类别的概率值大小,以此来判断是否发生了车辆碰撞。本申请能够更好的消除噪声,提高模型的精度,并最终提高车辆碰撞预测的精度。
Vehicle collision detection method based on deep residual shrinkage network and device thereof
基于深度残差收缩网络的车辆碰撞检测方法及装置
2021-07-27
Patent
Elektronische Ressource
Chinesisch
IPC: | G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G10L Analyse oder Synthese von Sprache , SPEECH ANALYSIS OR SYNTHESIS |
An Intelligent Quadrotor Fault Diagnosis Method Based on Novel Deep Residual Shrinkage Network
DOAJ | 2021
|COLLISION DETECTION DEVICE FOR VEHICLE AND COLLISION DETECTION METHOD FOR VEHICLE
Europäisches Patentamt | 2018
|Collision detection device for vehicle and collision detection method for vehicle
Europäisches Patentamt | 2020
|COLLISION DETECTION DEVICE FOR VEHICLE AND COLLISION DETECTION METHOD FOR VEHICLE
Europäisches Patentamt | 2018
|Vehicle Forward Collision Warning Based on Improved Deep Neural Network
SAE Technical Papers | 2023
|