Neural network-based tracking target dynamic and static state judgment method and system

• Main Authors: WENG LIHONG, HU YIFEI
• Format: Patent
• Language: Chinese; English
• Published: 24.08.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention relates to a neural network-based tracking target dynamic and static state judgment method and system. The method comprises the following steps: a training step: for each tracking target in a tracking target set, extracting feature points, converting the feature points into feature vectors, labeling truth values of dynamic and static states of the tracking targets, and training a neural network by taking the feature vectors and the corresponding truth values of the dynamic and static states as training sample parameters, obtaining a trained neural network classification model; and a testing step: extracting a feature vector of a tracking target, and inputting the feature vector into the neural network classification model to obtain a dynamic and static state classification result of the tracking target. According to the invention, dynamic and static judgment of the laser radar tracking target is carried out by using the neural network method, and the accuracy of the judgment result can be improv