Convolutional Neural Networks for Aerial Vehicle Detection and Recognition
This addresses the problem of limited training data for aerial vehicle detection by enabling recognition of more classes in testing than in training, though it is incremental in approach.
The paper tackles aerial vehicle recognition by using a text-guided convolutional neural network that matches aerial images with textual descriptions of vehicle classes and colors, achieving recognition with a yes/no output format.
This paper investigates the problem of aerial vehicle recognition using a text-guided deep convolutional neural network classifier. The network receives an aerial image and a desired class, and makes a yes or no output by matching the image and the textual description of the desired class. We train and test our model on a synthetic aerial dataset and our desired classes consist of the combination of the class types and colors of the vehicles. This strategy helps when considering more classes in testing than in training.