A Target Detection Algorithm for Remote Sensing Images Based on Deep Learning
Open Access
- 18 December 2021
- journal article
- research article
- Published by Wiley in Contrast Media & Molecular Imaging
- Vol. 2021, 1-6
Abstract
In order to improve the accuracy of remote sensing image target detection, this paper proposes a remote sensing image target detection algorithm DFS based on deep learning. Firstly, dimension clustering module, loss function, and sliding window segmentation detection are designed. The data set used in the experiment comes from GoogleEarth, and there are 6 types of objects: airplanes, boats, warehouses, large ships, bridges, and ports. Training set, verification set, and test set contain 73490 images, 22722 images, and 2138 images, respectively. It is assumed that the number of detected positive samples and negative samples is A and B, respectively, and the number of undetected positive samples and negative samples is C and D, respectively. The experimental results show that the precision-recall curve of DFS for six types of targets shows that DFS has the best detection effect for bridges and the worst detection effect for boats. The main reason is that the size of the bridge is relatively large, and it is clearly distinguished from the background in the image, so the detection difficulty is low. However, the target of the boat is very small, and it is easy to be mixed with the background, so it is difficult to detect. The MAP of DFS is improved by 12.82, the detection accuracy is improved by 13, and the recall rate is slightly decreased by 1 compared with YOLOv2. According to the number of detection targets, the number of false positives (FPs) of DFS is much less than that of YOLOv2. The false positive rate is greatly reduced. In addition, the average IOU of DFS is 11.84 higher than that of YOLOv2. For small target detection efficiency and large remote sensing image detection, the DFS algorithm has obvious advantages.Keywords
Funding Information
- Ministry of Education of the People's Republic of China (20180520017JH)
This publication has 20 references indexed in Scilit:
- Photon-limited face image super-resolution based on deep learningOptics Express, 2018
- Recurrent neural networks for remote sensing image classificationIET Computer Vision, 2018
- Small target detection based on reweighted infrared patch‐image modelIET Image Processing, 2018
- Deep kernel learning method for SAR image target recognitionReview of Scientific Instruments, 2017
- Hyperspectral Image Target Detection Improvement Based on Total VariationIEEE Transactions on Image Processing, 2016
- Multispectral detection and tracking of multiple moving targets in cluttered urban environmentsOptical Engineering, 2015
- Edge detection based on the Shannon Entropy by piecewise thresholding on remote sensing imagesIET Computer Vision, 2015
- Spatial Coherence-Based Batch-Mode Active Learning for Remote Sensing Image ClassificationIEEE Transactions on Image Processing, 2015
- Change-Based Image Cropping with Exclusion and Compositional FeaturesInternational Journal of Computer Vision, 2015
- Spatial analysis of groundwater potential using remote sensing and GIS-based multi-criteria evaluation in Raya Valley, northern EthiopiaHydrogeology Journal, 2014