Aircraft Detection in Remote Sensing Image based on Multi-scale Convolution Neural Network with Attention Mechanism

Abstract

Detecting aircraft from remote sensing image (RSI) is an important but challenging task due to the variations of aircraft type, size, pose, angle, complex background and small size of aircraft in RSIs. An aircraft detection method is proposed based on multi-scale convolution neural network with attention (MSCNNA), consisting of encoder, decoder, attention and classification. In MSCNNA, the multiple convolutional and pooling kernels with different sizes are utilized to learn the multi-scale discriminant features, and the global attention mechanism (GAM) is employed to capture the spatial and channel dependencies and adaptively preserve the relationships of the entire image. Compared with the standard deep CNN, multi-scale convolution neural networks (CNN) and GAM are integrated to learn the multi-scale features for aircraft detection, especially small aircrafts. Experiment results on the aircraft image dataset of the public EORSSD dataset show that the proposed method outperforms the state-of-the-art method on the same dataset and the obtained multi-size aircraft edge is clearer.

Matrix Factorization Recommendation Algorithm Based on Attention Interaction

“…To preserve the original rating information and improve the structure of the model stability and training efficiency, we normalized the sum of Self-attention and Rating. The residual network can maintain the performance of the network model with an increase in the number of network layers and then slow down the degradation of the model performance [48].…”

Remote sensing image denoising algorithm based on improved Transformer network

“…In the decoding phase, the decoder receives the feature map from the encoder. Through the Transformer module and the upsampling stage, the decoder conducts decoding operations while also performing skip connections [18] . Ultimately, in the final layer of the network structure, the decoder outputs a denoised image of size 512×512.…”

A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition

“…With the increase in GPU computing power and the research of neural networks in recent years, object detection has become a hot spot in global artificial intelligence research. Most of the current mainstream object detection methods are based on convolutional neural networks, and in recent years, two main categories have been formed: candidate region-based and regression-based [ 18 ]. Candidate region-based object detection methods, also known as two-stage methods, divide the object detection problem into two stages; one is to generate candidate regions, and the other is to put the candidate regions into the classifier to classify and correct the position.…”