Vehicle classification method based on multi-branch local attention network

• Main Authors: YAN RUGEN, ZHOU PING, LYU QIANG, CHEN CHEN, ZHAO JIXIANG, HU CHANGLONG, LI TAO
• Format: Patent
• Language: Chinese; English
• Published: 05.11.2021
• 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 discloses a vehicle classification method based on a multi-branch local attention network. The method comprises the following specific steps: obtaining a to-be-classified vehicle picture and dividing the to-be-classified vehicle picture into a training set and a test set; inputting the training set of the vehicle pictures into a vehicle classification model for constructing a multi-branch local attention network for training, wherein the multi-branch local attention network comprises a channel-based convolutional attention module and a space-based local attention module; and performing classification prediction on the test set of the vehicle pictures according to the trained vehicle classification model to obtain a classification result. According to the invention, the multi-branch local attention structure is added in the original ResNet-50 model, the structure can more accurately obtain information of different neighborhoods in the feature map, and the expressivity of key features is enhanced,