Amr Abd-Elrahman

A community-based urban forest inventory using online mapping services and consumer-grade digital images

Abstract Community involvement in gathering and submitting spatially referenced data via web mapping applications has recently been gaining momentum. Urban forest inventory data analyzed by programs such as the i-Tree ECO inventory method is a good candidate for such an approach. In this research, we tested the feasibility of using spatially referenced data gathered and submitted by non-professional individuals through a web application to augment urban forest inventory data. We examined the use of close range photogrammetry solutions of images taken by consumer-grade cameras to extract quantitative metric information such as crown diameter, tree heights and trunk diameters. Several tests were performed to evaluate the accuracy of the photogrammetric solutions and to examine their use in addition to existing aerial image data to supplement or partially substitute for standard i-Tree ECO field measurements. Digital images of three sample sites were acquired using different consumer-grade cameras. Several photogrammetric solutions were performed using the acquired image sets. Each model was carried out using a relative orientation process followed by baseline model scaling. Several distances obtained through this solution were compared to the corresponding distances obtained through direct measurements in order to assess the quality of the model scaling approach. Measured i-Tree ECO field plot inventory data, online aerial image measurements and photogrammetric observations were compared. The results demonstrate the potential for using aerial image digitizing in addition to ground images to assist in participatory urban forest inventory efforts.

Mapping potential carbon and timber losses from hurricanes using a decision tree and ecosystem services driver model

Information on the effect of direct drivers such as hurricanes on ecosystem services is relevant to landowners and policy makers due to predicted effects from climate change. We identified forest damage risk zones due to hurricanes and estimated the potential loss of 2 key ecosystem services: aboveground carbon storage and timber volume. Using land cover, plot-level forest inventory data, the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model, and a decision tree-based framework; we determined potential damage to subtropical forests from hurricanes in the Lower Suwannee River (LS) and Pensacola Bay (PB) watersheds in Florida, US. We used biophysical factors identified in previous studies as being influential in forest damage in our decision tree and hurricane wind risk maps. Results show that 31% and 0.5% of the total aboveground carbon storage in the LS and PB, respectively was located in high forest damage risk (HR) zones. Overall 15% and 0.7% of the total timber net volume in the LS and PB, respectively, was in HR zones. This model can also be used for identifying timber salvage areas, developing ecosystem service provision and management scenarios, and assessing the effect of other drivers on ecosystem services and goods.

Modeling Relationships among 217 Fires Using Remote Sensing of Burn Severity in Southern Pine Forests

Pine flatwoods forests in the southeastern US have experienced severe wildfires over the past few decades, often attributed to fuel load build-up. These forest communities are fire dependent and require regular burning for ecosystem maintenance and health. Although prescribed fire has been used to reduce wildfire risk and maintain ecosystem integrity, managers are still working to reintroduce fire to long unburned areas. Common perception holds that reintroduction of fire in long unburned forests will produce severe fire effects, resulting in a reluctance to prescribe fire without first using expensive mechanical fuels reduction techniques. To inform prioritization and timing of future fire use, we apply remote sensing analysis to examine the set of conditions most likely to result in high burn severity effects, in relation to vegetation, years since the previous fire, and historical fire frequency. We analyze Landsat imagery-based differenced Normalized Burn Ratios (dNBR) to model the relationships between previous and future burn severity to better predict areas of potential high severity. Our results show that remote sensing techniques are useful for modeling the relationship between elevated risk of high burn severity and the amount of time between fires, the type of fire (wildfire or prescribed burn), and the historical frequency of fires in pine flatwoods forests.

Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system

Deep learning networks have shown great success in several computer vision applications, but its implementation in natural land cover mapping in the context of object-based image analysis (OBIA) is rarely explored area especially in terms of the impact of training sample size on the performance comparison. In this study, two representatives of deep learning networks including fully convolutional networks (FCN) and patch-based deep convolutional neural networks (DCNN), and two conventional classifiers including random forest and support vector machine were implemented within the framework of OBIA to classify seven natural land cover types. We assessed the deep learning classifiers using different training sample sizes and compared their performance with traditional classifiers. FCN was implemented using two types of training samples to investigate its ability to utilize object surrounding information. Our results indicate that DCNN may produce inferior performance compared to conventional classifiers when the training sample size is small, but it tends to show substantially higher accuracy than the conventional classifiers when the training sample size becomes large. The results also imply that FCN is more efficient in utilizing the information in the training sample than DCNN and conventional classifiers, with higher if not similar achieved accuracy regardless of sample size. DCNN and FCN tend to show similar performance for the large sample size when the training samples used for training the FCN do not contain object surrounding label information. However, with the ability of utilizing surrounding label information, FCN always achieved much higher accuracy than all the other classification methods regardless of the number of training samples.

Object-based classification of wetland vegetation using very high-resolution unmanned air system imagery

ABSTRACT The purpose of this study is to examine the use of multi-resolution object-based classification methods for the classification of Unmanned Aircraft Systems (UAS) images of wetland vegetation and to compare its performance with pixel-based classification approaches. Three types of classifiers (Support Vector Machine, Artificial Neural Network and Maximum Likelihood) were utilized to classify the object-based images, the original 8-cm UAS images and the down-sampled (30 cm) version of the image. The results of the object-based and two pixel-based classifications were evaluated and compared. Object-based classification produced higher accuracy than pixel-based classifications if the same type of classifier is used. Our results also showed that under the same classification scheme (i.e. object or pixel), the Support Vector Machine classifier performed slightly better than Artificial Neural Network, which often yielded better results than Maximum Likelihood. With an overall accuracy of 70.78%, object-based classification using Support Vector Machine showed the best performance. This study also concludes that while UAS has the potential to provide flexible and feasible solutions for wetland mapping, some issues related to image quality still need to be addressed in order to improve the classification performance.

Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features

Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge from remotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery. There are only a few studies using high spatial resolution imagery and machine learning image classification algorithms for mapping heterogeneous wetland plant communities. This study addresses this void by analyzing whether machine learning classifiers such as decision trees (DT) and artificial neural networks (ANN) can accurately classify graminoid/sedge communities using high resolution aerial imagery and image texture data in the Everglades National Park, Florida. In addition to spectral bands, the normalized difference vegetation index, and first- and second-order texture features derived from the near-infrared band were analyzed. Classifier accuracies were assessed using confusion tables and the calculated kappa coefficients of the resulting maps. The results indicated that an ANN (multilayer perceptron based on back propagation) algorithm produced a statistically significantly higher accuracy (82.04 %) than the DT (QUEST) algorithm (80.48 %) or the maximum likelihood (80.56 %) classifier (α<0.05). Findings show that using multiple window sizes provided the best results. First-order texture features also provided computational advantages and results that were not significantly different from those using second-order texture features.

Building Extraction from High Resolution Space Images in High Density Residential Areas in the Great Cairo Region

This study evaluates a methodology for using IKONOS stereo imagery to determine the height and position of buildings in dense residential areas. The method was tested on three selected sites in an area of 8.5 km long by 7 km wide and covered by two overlapping (97% overlap) IKONOS images. The images were oriented using rational function models in addition to ground control points. Buildings were identified using an algorithm that utilized the Digital Surface Model (DSM) extracted from the images in addition to the image spectral properties. A digital terrain model was used with the DSM created from the IKONOS stereo imagery to compute building heights. Positional accuracy and building heights were evaluated using corner coordinates extracted from topographic maps and surveyed building heights. The results showed that the average building detection percentage for the test area was 82.6% with an average missing factor of 0.16. When the image rational polynomial coefficients were used to build the image model, results showed a horizontal accuracy of 2.42 and 2.39 m Root Mean Square Error (RMSE) for the easting and northing coordinates, respectively. When ground control points were used, the results improved to the sub-meter level. Differences between building heights extracted from the image model and the corresponding heights obtained through traditional ground surveying had a RMSE of 1.05 m.

Accuracy Evaluation of Terrestrial LIDAR and Multibeam Sonar Systems Mounted on a Survey Vessel

AbstractThis research provides a performance test of terrestrial light detection and ranging (LIDAR) and multibeam echo sounder scanners integrated with Global Navigation Satellite System/Inertial Navigation System positioning and orientation on a survey vessel platform. To measure the accuracy of the data, experiments were designed to allow the LIDAR and sonar scanners to acquire scans of a control target that extended above and below the water surface. The scans were acquired under normal and induced conditions expected in a marine survey environment, such as variations in speed, range, motion, and orientation. SD, root-mean-square error (RMSE), and mean were computed across all data sets for each experiment. Horizontal RMSE values of 0.06 and 0.03 m were achieved for the LIDAR and sonar data, respectively. Vertical RMSE results of 0.04 m were found for both data types. These results were comparable with previous mobile mapping research involving similar systems. Contributing uncertainty and error sourc...

Filtering high-resolution hyperspectral imagery in a maximum noise fraction transform domain using wavelet-based de-striping

Ever improving technology and computer processing power and decreasing cost have made hyperspectral image acquisition and analysis affordable in many applications. Hyperspectral images, acquired normally using pushbroom sensing systems, are tainted with noise and nonperiodic stripes. Few methods, including wavelet-based ones, have been proposed for reducing nonperiodic stripes from multispectral images; there are even fewer studies dealing with nonperiodic stripes in high-resolution hyperspectral images. Applying de-striping filters directly to individual hyperspectral image bands can be computationally inefficient and complicated considering the large number of bands in this type of image. This article compares the performance of wavelet-based de-striping algorithms as applied on high-resolution hyperspectral imagery. The algorithms are implemented directly on individual bands in the image domain and on selected bands in the image maximum noise fraction (MNF) transform domain. Two wavelet-based de-striping algorithms were tested and compared. The first algorithm eliminates wavelet detail components in the striping direction, while the second algorithm adaptively filters these components. The filtering methods are evaluated through visual and quantitative assessments. Quantitative assessment is performed by analysing the autocorrelation coefficient and signal-to-noise-ratio. The results show that images filtered in the MNF domain are superior in reducing stripes and noise while retaining the image information and without introducing distortions. The technique is computationally effective through filtering fewer bands, which reduces the need for filtering parameter determination and fine tuning. Visual and quantitative assessments also show that adaptive filtering of wavelet components is better than eliminating entire components due to the retention of image content.

Design and Development of a Multi-Purpose Low-Cost Hyperspectral Imaging System

Hyperspectral image analysis is gaining momentum in a wealth of natural resources and agricultural applications facilitated by the increased availability of low-cost imaging systems. In this study, we demonstrate the development of the Vegetation Mobile Mapping System (VMMS), a low-cost hyperspectral sensing system that is supported by consumer-grade digital camera(s). The system was developed using off-the-shelf imaging and navigation components mainly for ground-based applications. The system integrates a variety of components including timing and positioning GPS receivers and an Inertial Measurement Unit (IMU). The system was designed to be modular and interoperable allowing the imaging components to be used with different navigation systems. The technique used for synchronizing captured images with GPS time was presented. A relative radiometric calibration technique utilizing images of homogeneous targets to normalize pixel gain and offset parameters was used. An empirical spectral calibration method was used to assign wavelengths to image bands. Data acquisition parameters to achieve appropriate spatial coverage were presented. The system was tested in ground-based data collection and analysis experiments that included water quality and vegetation studies.