Research on Remote Sensing Image Target Recognition Based on Deep Convolution Neural Network

Abstract

Target recognition is an important application in the time of high-resolution remote sensing images. However, the traditional target recognition method has the characteristics of artificial design, and the generalization ability is not strong, which makes it difficult to meet the requirement of the current mass data. Therefore, it is urgent to explore new methods for feature extraction and target recognition and location in remote sensing images. Convolutional neural network in deep learning can extract representative and discriminative multi-level features of typical features from images, so it can be used for multi-target recognition of remote sensing big data in complex scenes. In this study, NWPU VHR-10 data was selected, 50% was used for training, and the remainder was used for verification. The target recognition effects of two kinds of convolutional neural network models, Faster R-CNN and SSD, were studied and compared, and the mean average precision (mAP) was used for evaluation. The evaluation results show that the Faster R-CNN has three categories with an accuracy of more than 80%, and the SSD has seven categories with an accuracy of more than 80%, all of which show good results. The SSD model is particularly prominent in running time and recognition results, which proves convolutional neural networks have broad application prospects in the target recognition of remote sensing image data.

[Retracted] Quantitative Evaluation of Plant and Modern Urban Landscape Spatial Scale Based on Multiscale Convolutional Neural Network

“…e experimental results show that the model has good performance in mutation and gradient detection. Han et al [14] studied and compared the target recognition effects of two convolutional neural network models, which are fast r-CNN and SSD, and evaluated by using average accuracy (map). e results show that there are three types of r-CNN with fast speed, with an accuracy of over 80%, SSDs of 7 types and accuracy of over 80%, all of which have achieved good results.…”

Sonar Image Target Detection and Recognition Based on Convolution Neural Network

“…e basic network used by YOLOv3 is Darknet53 [11]. To avoid the gradient explosion caused by the deepening of network layers, Darknet53 adds RESNET (residual neural network) [21][22][23][24][25] residual structure. When classifying the target objects, YOLOv3 uses several independent logistic regression classifiers.…”

“…e feature maps of different levels are used for the border regression of different scale targets and the prediction of different category scores. Finally, the final detection result is obtained by NMS [23]. SSD is combined with a multiscale feature map to detect small targets with shallow feature maps with high resolution and large targets with deep feature maps with low resolution so that targets of different scales can be detected.…”

Weed Detection in Images of Carrot Fields Based on Improved YOLO v4

“…With the recent development of deep learning (DL), convolutional neural network (CNN) has been effectively applied in machine vision [5][6]. Major breakthroughs have been achieved in CNN applications to image recognition [7][8], semantic segmentation [9][10] and object detection [11][12]. Thanks to its strong representation ability of image features, the CNN has been increasingly applied to agriculture.…”