ABSTRACT One of the most recent areas of research in agriculture is the detection along with classification of diseases from plant leaf images. Since rice is the most widely consumed staple food worldwide, it is crucial to increase paddy production’s quality and quantity. In the production of paddy, early detection of pests and diseases at various growth stages is very important. Utilising image processing scheme to spot diseases of agricultural plants will lessen the need for farmers to safeguard agricultural products. The use of VGG-16 along with a Convolutional Neural Network (CNN) for the classification and recognition of paddy leaf diseases is proposed in this work. The rice plant leaves images taken from the kaggle dataset is utilised for the purpose of image acquisition. The Gaussian filter is used in pre-processing. The clustering technique is utilised for the segmentation of the diseased part, the normal part, and the surroundings. The proposed model is then utilised for disease classification. This study classifies 10 categories of paddy images. VGG16, InceptionV3, MobileNetV2, and ResNet-152, among other transfer learning methods, are evaluated and contrasted with the experimental results. The outcome accuracy of the proposed model achieves of nearly 99.9%.

ABSTRACT Due to factors such as smoke, the non fire identification rate and fire identification accuracy in building fire identification are low, resulting in poor identification results. Therefore, a simplified identification method for building fire spread risk based on digital image processing technology is proposed. A fire spread model is constructed by considering both thermal radiation and thermal plumes, and based on this model, changes in smoke, temperature, and other factors during the occurrence of a fire are obtained. Using K-means to improve the dark channel defogging algorithm, the image after defogging is obtained, making the colour of the image more prominent and the feature information more abundant. Using the area threshold method to further extract the flame target contour in the defogged image, and determine whether the suspected flame area is a flame. Finally, four aspects of colour, sharp corner characteristics, area growth characteristics, and automatic estimation of propagation direction were identified to obtain simplified identification results for fire propagation risk. The experimental results show that the average non fire recognition rate of the proposed method reaches 95.8%, with good fire recognition accuracy and recognition effect, which verifies its feasibility.

ABSTRACT Agriculture is one crucial industry that expects to profit from these improvements in maintaining financial stability and availability of food. Accurate agricultural output prediction is critical for efficient policy formation, allocation of resources, and preparedness for catastrophes. This work intends to propose a novel insight generation for improving e-Governance towards crop yield prediction model. In the first stage, the data is preprocessed by conducting improved data normalisation and data augmentation. The outlier handling, custom weighted Min-Max scaling and using a custom scaling range are the steps to be followed in the improved data normalisation. Then the augmented data is subjected to a second stage called feature extraction. From the augmented data, the raw feature, Unbiased Estimator based Correlation (UEC) feature, correlation feature, and statistical features are extracted. In the UEC-based feature, the unbiased estimator is deployed to estimate outliers and sparse data. These extracted features are fed to a hybrid DL-based prediction model, wherein it contains Bidirectional Long Short Term Memory (Bi-LSTM) and Shifted Beamish Activation-Deep Convolutional Neural Network (SBA-DCNN) models. The SBA activation function is employed in SBA-DCNN at each convolutional layer. By taking the mean of both models, this hybrid prediction model accurately predicts the yield.

ABSTRACT Using particle swarm optimisation algorithm to optimise support vector machines enhances urban heat island observation methods, while remote sensing technology aids in selecting temperature estimation parameters. Then the two are combined to construct a model for estimating urban near-surface temperature. A contribution study is conducted on the selected parameters. The selected parameters have contributions in the near-surface temperature estimation. The determination coefficient of the constructed urban near-surface temperature estimation model was 0.892. The root mean square error was 0.42°C, the F1 value is 0.82, and the running time is 0.41 seconds, which was superior to other comparison models. Additionally, this model was applied to observe the urban heat island in Xi’an. The overall spatial distribution was low in the south and high in the north, with the central area being higher than the surrounding area, the highest temperature is 23.51°C, and the lowest temperature is 19.05°C. Moreover, the intensity level in the high-temperature area accounted for 16.9%. Based on the above results, the near-surface temperature estimation model constructed in the study has shown high accuracy and efficiency in urban heat island observation. It can be applied in practice, providing theoretical reference for urban planning and ecological environment protection.

ABSTRACT This research presents the novel application of v-Support Vector Machine (v-SVM) to hyperspectral image classification. The essence of this work is to test the suitability of v-SVM for hyperspectral image classification. The v-SVM provides an enhancement to the regularisation parameter in the classical Support Vector Machine (SVM). The regularisation parameter controls the trade-off between obtaining a high training error and a low training error which is the ability of the model to generalise the unseen data (or test data). The value of the regularisation parameter in the classical SVM ranges from 0 to + ∞ ; this makes it usually challenging to determine the most appropriate optimal regularisation parameter value. The invention of the v-SVM has made it easier to find an appropriate optimal regularisation parameter value since the regularisation parameter is narrowed down from a wide range of 0 to + ∞ to a narrow range of 0 to 1 . In this study, two hyperspectral images of Indian Pines region in Northwest Indiana, USA and University of Pavia, Italy are used as test beds for the experiment. The result of the experiment shows that the v-SVM performed fairly better than the classical SVM; however, it fell short of the notable conventional classifiers.

ABSTRACT There has been a rapid evolution of tree-based ensemble algorithms which have outperformed deep learning in several studies, thus emerging as a competitive solution for many applications. In this study, ten tree-based ensemble algorithms (random forest, bagging meta-estimator, adaptive boosting (AdaBoost), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), light gradient boosting (LightGBM), histogram-based GBM, categorical boosting (CatBoost), natural gradient boosting (NGBoost), and the regularised greedy forest (RGF)) were comparatively evaluated for the enhancement of Copernicus digital elevation model (DEM) in an agricultural landscape. The enhancement methodology combines elevation and terrain parameters alignment, with feature-level fusion into a DEM enhancement workflow. The training dataset is comprised of eight DEM-derived predictor variables, and the target variable (elevation error). In terms of root mean square error (RMSE) reduction, the best enhancements were achieved by GBM, random forest and the regularised greedy forest at the first, second and third implementation sites respectively. The computational time for training LightGBM was nearly five-hundred times faster than NGBoost, and the speed of LightGBM was closely matched by the histogram-based GBM. Our results provide a knowledge base for other researchers to focus their optimisation strategies on the most promising algorithms.

ABSTRACT Lineaments play a critical role in the study of lunar geological evolution. However, lineaments still need to be extracted manually which constrains lunar research. To fill this gap, a Markov chain-based methodology is introduced for automatically extracting vector-based non-bifurcated lineaments from images. The extracted lineaments are formed by successive nodes and line segments, where nodes denote pixel positions and line segments represented connecting lines between nodes. A modified U-net with residual shortcut connections and dilated convolutions is proposed based on the elongated shapes of lineaments to evaluate the probability of nodes belonging to lineaments. Four connection shape features are proposed to describe the connection shapes of nodes and a Gaussian Mixture Model is used to evaluate the probability of line segments belonging to the lineaments based on the proposed features. In the final stage, the lineament probabilities of both nodes and line segments to extract lineaments are considered in the Markov chain. Our method has experimented on a dataset containing 220 samples and 10-fold cross-validation was used to evaluate the performance. Both qualitative and quantitative results indicated that our method can effectively extract non-bifurcated lunar lineaments with arbitrary bending. The method sheds useful light on automatic lineament extraction.

ABSTRACT A new method for image fusion introduces an inventive strategy for amalgamating data from multiple images, resulting in the creation of a single, improved output image. This approach aims to address the limitations and challenges associated with conventional fusion techniques, paving the way for improved results in various applications. In this research, a novel approach for image fusion is presented, featuring a rescue hunt optimisation-based modified guidance model (RHO-based MG model). The methodology leverages the non-subsampled contourlet transform (NSCT) and non-subsampled shear let transform (NSST) to construct the fusion transform using two input images, typically infrared and visual images. By hybridising high-frequency (HF) and low-frequency (LF) bands from both types of images, the fusion model generates the final HF and LF bands. A distinctive modified guidance strategy is employed in the development of these bands. The proposed approach utilises a rescue hunt algorithm developed through the combination of search and rescue optimisation (SARO) and grey wolf optimisation (GWO) behaviours. In image fusion, optimisation fine-tunes VGG-19 and RESNET 18 models to improve their ability to combine multiple images effectively. This process involves adjusting the models’ internal parameters using optimisation techniques. By analysing the features in different input images, these models learn to extract meaningful information and create a fused image that retains the important details from each source. This strategy is further enhanced by integrating the VGG-19 and RESNET 18 models. The fused image is composed of combined HF and LF bands, with the final result obtained through an inverse hybrid transform. Experimental results, conducted on a dataset of 25 images, demonstrate the effectiveness of the approach with metrics average gradient (AG), edge intensity (EI), PSNR, RMSE, SSIM, and variance attained the values of 24.71, 236.67, 54.96 dB, 0.22, 63.16, and 0.11, respectively. This innovative method offers a promising direction for enhancing image fusion quality and is highlighted by its unique integration of optimisation and guidance strategies.

ABSTRACT The most crucial element in accurately monitoring and assessing cotton development is having effective cotton maps. In order to make decisions about governance, precision agriculture, and field management, the county-scale cotton remote sensing categorisation models must be evaluated. The main objective of this research is to propose novel hyperspectral image segmentation approach for cotton crops to monitor the crops and identify early signs of disease. The proposal for a hyperspectral image-based classification of cotton crops is made in this research. Using ‘Modified Hierarchical density-based spatial clustering of applications with noise (HDBSCAN),’ the procedure begins with the input image being segmented. Following this, features based on vegetation indices, hybrid vegetation indices, and statistical characteristics will be retrieved and trained with the classification model to ensure proper classification. Specifically, EVI, NDVI, and RVI are features that are based on vegetation indices. Using techniques like SVM, CNN, DBN, DT, and Improved Bidirectional Long Short-Term Memory (IBi-LSTM), this study replicates a stacked ensemble framework for classification. While the MHDBSCAN achieved the maximum accuracy value of 97.97%, the conventional techniques achieved limited accuracy. Thus, the MHDBSCAN far more effective at classifying the crop utilising hyperspectral image segmentation and the classification become more precise and accurate.

ABSTRACT Objects or images captured from the remote area will not have good quality and will not be visible because of mist, smoke, moisture and fog. Here, we rub/remove the unwanted hazes from the image using the optimal adaptive technique. An examination of the built-in boundary constraint of the transmission function is extremely valuable to our method. This constraint is handled as an optimisation problem to predict the unknown scene transmission. In addition, transmission refining techniques are used to remedy the issue based on variable splitting methodology. With only a few broad assumptions, the proposed method may recover haze-free, high-quality images having original colours and better image information. Experiment findings are done with plenty of foggy images indicating the efficiency and effectiveness of the proposed technique by using image quality parameters.