Comparison of two deep learning methods for ship target recognition with optical remotely sensed data

Forest growing stock volume (GSV) is an important parameter in the context of forest resource management. National Forest Inventories (NFIs) are routinely used to estimate forest parameters, including GSV, for national or international reporting. Remotely sensed data are increasingly used as a source of auxiliary information for NFI data to improve the spatial precision of forest parameter estimates. In this study, we combine data from the NFI in Poland with satellite images of Landsat 7 and 3D point clouds collected with airborne laser scanning (ALS) technology to develop predictive models of GSV. We applied an area-based approach using 13,323 sample plots measured within the second cycle of the NFI in Poland (2010–2014) with poor positional accuracy from several to 15 m. Four different predictive approaches were evaluated: multiple linear regression, k-Nearest Neighbours, Random Forest and Deep Learning fully connected neural network. For each of these predictive methods, three sets of predictors were tested: ALS-derived, Landsat-derived and a combination of both. The developed models were validated at the stand level using field measurements from 360 reference forest stands. The best accuracy (RMSE% = 24.2%) and lowest systematic error (bias% = −2.2%) were obtained with a deep learning approach when both ALS- and Landsat-derived predictors were used. However, the differences between the evaluated predictive approaches were marginal when using the same set of predictor variables. Only a slight increase in model performance was observed when adding the Landsat-derived predictors to the ALS-derived ones. The obtained results showed that GSV can be predicted at the stand level with relatively low bias and reasonable accuracy for coniferous species, even using field sample plots with poor positional accuracy for model development. Our findings are especially important in the context of GSV prediction in areas where NFI data are available but the collection of accurate positions of field plots is not possible or justified because of economic reasons.

Download Full-text

Estimating crop yields with deep learning and remotely sensed data

2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) ◽

10.1109/igarss.2015.7325900 ◽

2015 ◽

Cited By ~ 26

Author(s):

Kentaro Kuwata ◽

Ryosuke Shibasaki

Keyword(s):

Deep Learning ◽

Crop Yields ◽

Remotely Sensed ◽

Remotely Sensed Data

Download Full-text

Automatic Detection of Impervious Surfaces from Remotely Sensed Data Using Deep Learning

Remote Sensing ◽

10.3390/rs13163166 ◽

2021 ◽

Vol 13 (16) ◽

pp. 3166

Author(s):

Jash R. Parekh ◽

Ate Poortinga ◽

Biplov Bhandari ◽

Timothy Mayer ◽

David Saah ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Large Scale ◽

Mean Squared Error ◽

Remotely Sensed ◽

Landsat 8 ◽

Impervious Surfaces ◽

Remotely Sensed Data ◽

Statistical Indices ◽

Deep Learning Neural Network

The large scale quantification of impervious surfaces provides valuable information for urban planning and socioeconomic development. Remote sensing and GIS techniques provide spatial and temporal information of land surfaces and are widely used for modeling impervious surfaces. Traditionally, these surfaces are predicted by computing statistical indices derived from different bands available in remotely sensed data, such as the Landsat and Sentinel series. More recently, researchers have explored classification and regression techniques to model impervious surfaces. However, these modeling efforts are limited due to lack of labeled data for training and evaluation. This in turn requires significant effort for manual labeling of data and visual interpretation of results. In this paper, we train deep learning neural networks using TensorFlow to predict impervious surfaces from Landsat 8 images. We used OpenStreetMap (OSM), a crowd-sourced map of the world with manually interpreted impervious surfaces such as roads and buildings, to programmatically generate large amounts of training and evaluation data, thus overcoming the need for manual labeling. We conducted extensive experimentation to compare the performance of different deep learning neural network architectures, optimization methods, and the set of features used to train the networks. The four model configurations labeled U-Net_SGD_Bands, U-Net_Adam_Bands, U-Net_Adam_Bands+SI, and VGG-19_Adam_Bands+SI resulted in a root mean squared error (RMSE) of 0.1582, 0.1358, 0.1375, and 0.1582 and an accuracy of 90.87%, 92.28%, 92.46%, and 90.11%, respectively, on the test set. The U-Net_Adam_Bands+SI Model, similar to the others mentioned above, is a deep learning neural network that combines Landsat 8 bands with statistical indices. This model performs the best among all four on statistical accuracy and produces qualitatively sharper and brighter predictions of impervious surfaces as compared to the other models.

Download Full-text

Super-resolution of remotely sensed data using channel attention based deep learning approach

International Journal of Remote Sensing ◽

10.1080/01431161.2021.1934598 ◽

2021 ◽

Vol 42 (16) ◽

pp. 6050-6067

Author(s):

Peijuan Wang ◽

Bulent Bayram ◽

Elif Sertel

Keyword(s):

Deep Learning ◽

Super Resolution ◽

Remotely Sensed ◽

Learning Approach ◽

Remotely Sensed Data

Download Full-text

Road Extraction from Remotely Sensed Data: A Review

Proceedings of Intelligent Computing and Technologies Conference ◽

10.21467/proceedings.115.14 ◽

2021 ◽

Author(s):

Mohd Jawed Khan ◽

Pankaj Pratap Singh

Keyword(s):

Deep Learning ◽

Traffic Management ◽

Remotely Sensed ◽

Future Research ◽

Learning Approaches ◽

Road Extraction ◽

Remotely Sensed Data ◽

Remotely Sensed Imagery ◽

Urban Rural ◽

Future Research Directions

Up-to-date road networks are crucial and challenging in computer vision tasks. Road extraction is yet important for vehicle navigation, urban-rural planning, disaster relief, traffic management, road monitoring and others. Road network maps facilitate a great number of applications in our everyday life. Therefore, a systematic review of deep learning approaches applied to remotely sensed imagery for road extraction is conducted in this paper. Four main types of deep learning approaches, namely, the GANs model, deconvolutional networks, FCNs, and patch-based CNNs models are presented in this paper. We also compare these various deep learning models applied to remotely sensed imagery to show their performances in extracting road parts from high-resolution remote sensed imagery. Later future research directions and research gaps are described.

Download Full-text