Urban Tree Species Classification Using a WorldView-2/3 and LiDAR Data Fusion Approach and Deep Learning.

Urban areas feature complex and heterogeneous land covers which create challenging issues for tree species classification. The increased availability of high spatial resolution multispectral satellite imagery and LiDAR datasets combined with the recent evolution of deep learning within remote sensing for object detection and scene classification, provide promising opportunities to map individual tree species with greater accuracy and resolution. However, there are knowledge gaps that are related to the contribution of Worldview-3 SWIR bands, very high resolution PAN band and LiDAR data in detailed tree species mapping. Additionally, contemporary deep learning methods are hampered by lack of training samples and difficulties of preparing training data. The objective of this study was to examine the potential of a novel deep learning method, Dense Convolutional Network (DenseNet), to identify dominant individual tree species in a complex urban environment within a fused image of WorldView-2 VNIR, Worldview-3 SWIR and LiDAR datasets. DenseNet results were compared against two popular machine classifiers in remote sensing image analysis, Random Forest (RF) and Support Vector Machine (SVM). Our results demonstrated that: (1) utilizing a data fusion approach beginning with VNIR and adding SWIR, LiDAR, and panchromatic (PAN) bands increased the overall accuracy of the DenseNet classifier from 75.9% to 76.8%, 81.1% and 82.6%, respectively. (2) DenseNet significantly outperformed RF and SVM for the classification of eight dominant tree species with an overall accuracy of 82.6%, compared to 51.8% and 52% for SVM and RF classifiers, respectively. (3) DenseNet maintained superior performance over RF and SVM classifiers under restricted training sample quantities which is a major limiting factor for deep learning techniques. Overall, the study reveals that DenseNet is more effective for urban tree species classification as it outperforms the popular RF and SVM techniques when working with highly complex image scenes regardless of training sample size.

A New Optical Remote Sensing Technique for High-Resolution Mapping of Soil Moisture.

The recently developed OPtical TRApezoid Model (OPTRAM) has been successfully applied for watershed scale soil moisture (SM) estimation based on remotely sensed shortwave infrared (SWIR) transformed reflectance (TRSWIR) and the normalized difference vegetation index (NDVI). This study is aimed at the evaluation of OPTRAM for field scale precision agriculture applications using ultrahigh spatial resolution optical observations obtained with one of the world's largest field robotic phenotyping scanners located in Maricopa, Arizona. We replaced NDVI with the soil adjusted vegetation index (SAVI), which has been shown to be more accurate for cropped agricultural fields that transition from bare soil to dense vegetation cover. The OPTRAM was parameterized based on the trapezoidal geometry of the pixel distribution within the TRSWIR-SAVI space, from which wet- and dry-edge parameters were determined. The accuracy of the resultant SM estimates is evaluated based on a comparison with ground reference measurements obtained with Time Domain Reflectometry (TDR) sensors deployed to monitor surface, near-surface and root zone SM. The obtained results indicate an SM estimation error between 0.045 and 0.057 cm3 cm-3 for the near-surface and root zone, respectively. The high resolution SM maps clearly capture the spatial SM variability at the sensor locations. These findings and the presented framework can be applied in conjunction with Unmanned Aerial System (UAS) observations to assist with farm scale precision irrigation management to improve water use efficiency of cropping systems and conserve water in water-limited regions of the world.

Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks.

In spite of advances in object recognition technology, handwritten Bangla character recognition (HBCR) remains largely unsolved due to the presence of many ambiguous handwritten characters and excessively cursive Bangla handwritings. Even many advanced existing methods do not lead to satisfactory performance in practice that related to HBCR. In this paper, a set of the state-of-the-art deep convolutional neural networks (DCNNs) is discussed and their performance on the application of HBCR is systematically evaluated. The main advantage of DCNN approaches is that they can extract discriminative features from raw data and represent them with a high degree of invariance to object distortions. The experimental results show the superior performance of DCNN models compared with the other popular object recognition approaches, which implies DCNN can be a good candidate for building an automatic HBCR system for practical applications.