CNN based learning: object classification on images from Aerial Photography
Jian-min Liu1, 2, Min-hua Yang1
COMPUTER MODELLING & NEW TECHNOLOGIES 2016 20(2) 30-32
1School of Geosciences and Info-Physics, Central South University, Changsha, 41000, China
2School of Information Science and Engineering, Hunan Institute of Humanities Science and Technology, Loudi, 417000, China
These years, object recognition on remote sensing images with high resolution had boomed. We trained a multilayer convolutional neural network caffe based to classify the 79 thousand high-resolution and unlabeled optical remote sensing images via the Internet into the 4500 different classes. On the unlabeled test dataset, we obtained error rates of 19.7% which run really well than traditional machine learning techniques. With pre-trained model-aided, GTX750Ti GPU, Intel® Core™ i5-4590 processor, we sharply accelerated progress time. The results compared with the published ones, and good agreement is acquired.