Search

Trees are essential for climate change adaptation or even mitigation to some extent. To leverage their potential, effective forest and urban tree management is required. Automated tree detection, localisation, and species classification are crucial to any forest and urban tree management plan. Over the last decade, many studies aimed at tree species classification using aerial imagery yet due to several environmental challenges results were sub-optimal. This study aims to contribute to this domain by first, generating a labelled tree species dataset using Google Maps static API to supply aerial images and Trees In Camden inventory to supply species information, GPS coordinates (Latitude and Longitude), and tree diameter. Furthermore, this study investigates how state-of-the-art deep Convolutional Neural Network models including VGG19, ResNet50, DenseNet121, and InceptionV3 can handle the species classification problem of the urban trees using aerial images. Experimental results show our best model, InceptionV3 achieves an average accuracy of 73.54 over 6 tree species.

The international climate emergency has triggered actions for understanding and controlling the Green House Gases (GHGs) all over the world to achieve the net zero 'dream'. It is important to understand the global trend in the GHG emissions, particularly focusing on Carbon dioxide. This paper investigates the trends in carbon dioxide emissions between 1965 and 2019. A retrospective look at this data will help us understand the major global trends and help designing better strategies to work towards the zero carbon target. This data analysis will look at breakdown of carbon emissions by geographical regions, which could provide a greater insight into the regions experiencing a rise in carbon emissions. The relationship between energy consumption and carbon emissions are also tested. The work also aims to provide a forecast of future energy consumption based on the learning from this analysis.

Beavers' habitat is known to alter the terrain, providing biodiversity in the area, and recently their lifestyle is linked to climatic changes by reducing greenhouse gases levels in the region. To analyse the impact of beavers’ habitat on the region, it is, therefore, necessary to estimate the terrain alterations caused by beaver actions. Furthermore, such terrain analysis can also play an important role in domains like wildlife ecology, deforestation, land-cover estimations, and geological mapping. Deep learning models are known to provide better estimates on automatic feature identification and classification of a terrain. However, such models require significant training data. Pre-existing terrain datasets (both real and synthetic) like CityScapes, PASCAL, UAVID, etc, are mostly concentrated on urban areas and include roads, pathways, buildings, etc. Such datasets, therefore, are unsuitable for forest terrain analysis. This paper contributes, by providing a finely labelled novel dataset of forest imagery around beavers’ habitat, captured from a high-resolution camera on an aerial drone. The dataset consists of 100 such images labelled and classified based on 9 different classes. Furthermore, a baseline is established on this dataset using state-of-the-art semantic segmentation models based on performance metrics including Intersection Over Union (IoU), Overall Accuracy (OA), and F1 score.

Urban trees help regulate temperature, reduce energy consumption, improve urban air quality, reduce wind speeds, and mitigating the urban heat island effect. Urban trees also play a key role in climate change mitigation and global warming by capturing and storing atmospheric carbon-dioxide which is the largest contributor to greenhouse gases. Automated tree detection and species classification using aerial imagery can be a powerful tool for sustainable forest and urban tree management. Hence, This study first offers a pipeline for generating labelled dataset of urban trees using Google Map's aerial images and then investigates how state of the art deep Convolutional Neural Network models such as VGG and ResNet handle the classification problem of urban tree aerial images under different parameters. Experimental results show our best model achieves an average accuracy of 60% over 6 tree species.

In the light of Artificial Intelligence aiding modern society in tackling climate change, this research looks at how to detect vegetation from aerial view images using deep learning models. This task is part of a proposed larger framework to build an eco-system to monitor air quality and the related factors like weather, transport, and vegetation, as the number of trees for any urban city in the world. The challenge involves building or adapting the tree recognition models to a new city with minimum or no labeled data. This paper explores self-supervised approaches to this problem and comes up with a system with 0.89 mean average precision on the Google Earth images for Cambridge city.

The advent of statistical parametric speech synthesis has paved new ways to a unified framework for hidden Markov model (HMM) based text to speech synthesis (TTS) and automatic speech recognition (ASR). The techniques and advancements made in the field of ASR can now be adopted in the domain of synthesis. Speaker adaptation is a well-advanced topic in the area of ASR, where the adaptation data from a target speaker is used to transform the canonical model parameters to represent a speaker specific model. Feature adaptation techniques like vocal tract length normalization (VTLN) perform the same task by transforming the features ; this can be shown to be equivalent to model transformation. The main advantage of VTLN is that it can demonstrate noticeable improvements in performance with very little adaptation data and can be classified as a rapid adaptation technique. VTLN is a widely used technique in ASR, and can be used in TTS to improve the rapid adaptation performance. In TTS, the task is to synthesize speech that sounds like a particular target speaker. Using VTLN for TTS is found to make the output synthesized speech sound quite similar to the target speaker from his very first utterance. An all-pass filter based bilinear transform was implemented for the mel-generalized cepstral (MGCEP) features of the HMM-based speech synthesis system (HTS). The initial implementation was using a grid search approach that selects the best warping factor for the speech spectrum from a grid of available values using the maximum likelihood criterion. VTLN was shown to give performance improvements in the rapid adaptation framework where the number of adaptation sentences from the target speaker was limited. But, this technique involves huge time and space complexities and the rapid adaptation demands for an efficient implementation of the VTLN technique. To this end, an efficient expectation maximization (EM) based VTLN approach was implemented for HTS using Brent’s search. Unlike the ASR features, MGCEP does not use a filter bank (in order to facilitate the speech reconstruction) and this provides equivalence to the model transformation for the EM implementation. This facilitates the estimation of warping factors to be embedded in the HMM training using the same sufficient statistics as in constrained maximum likelihood linear regression (CMLLR). This work addresses a lot of challenges faced in the process of adopting VTLN for synthesis due to the higher dimensionality of the cepstral features used in the TTS models. The main idea was to unify the theory and practise in the implementation of VTLN for both ASR and TTS. Several techniques have been proposed in this thesis, in order to find the best feasible warping factor estimation procedure. Estimation of the warping factor using the lower order cepstral features representing the spectral envelope is demonstrated to be the best approach. Different evaluations on standard databases are performed in this work to illustrate the performance improvements and perceptual challenges involved in the VTLN adaptation. VTLN has only a single parameter to represent the speaker characteristics and hence, has the limitation of not scaling to the performance of other linear transform based adaptation methods with the availability of large amounts of adaptation data. Several techniques are demonstrated in this work to combine the model based adaptation like constrained structural maximum a posteriori linear regression (CSMAPLR) with VTLN, one such technique being using VTLN as the prior transform at the root node of the tree structure of the CSMAPLR system. Thus, along with rapid adaptation, the performance scales with the availability of more adaptation data. These techniques although developed for TTS, can also be effectively used in ASR. It was also shown to give improvements in ASR especially for scenarios like noisy speech conditions. Other improvements to rapid adaptation including a bias term for VTLN, multiple transform based VTLN using regression classes and VTLN prior for non-structural MAPLR adaptation are also proposed. These techniques also demonstrated both ASR and TTS performance improvements. Also, a few special scenarios, specifically cross-lingual speech, cross-gender speech, child speech and noisy speech evaluations are presented where the rapid adaptation methods presented in this work was shown to be highly beneficial. Most of these methods will be published as extensions to the open-source HTS toolkit.