The global community has recognized an increasing amount of pollutants entering oceans and other water bodies as a severe environmental, economic, and social issue. In addition to prevention, one of the key measures in addressing marine pollution is the cleanup of debris already present in marine environments. Deployment of machine learning (ML) and deep learning (DL) techniques can automate marine waste removal, making the cleanup process more efficient. This study examines the performance of six well-known deep convolutional neural networks (CNNs), namely VGG19, InceptionV3, ResNet50, Inception-ResNetV2, DenseNet121, and MobileNetV2, utilized as feature extractors according to three different extraction schemes for the identification and classification of underwater marine debris. We compare the performance of a neural network (NN) classifier trained on top of deep CNN feature extractors when the feature extractor is (1) fixed; (2) fine-tuned on the given task; (3) fixed during the first phase of training and fine-tuned afterward. In general, fine-tuning resulted in better-performing models but is much more computationally expensive. The overall best NN performance showed the fine-tuned Inception-ResNetV2 feature extractor with an accuracy of $91.40\%$ and F1-score $92.08\%$, followed by fine-tuned InceptionV3 extractor. Furthermore, we analyze conventional ML classifiers’ performance when trained on features extracted with deep CNNs. Finally, we show that replacing NN with a conventional ML classifier, such as support vector machine (SVM) or logistic regression (LR), can further enhance the classification performance on new data.

The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion-MNIST image datasets.

This study investigates the application of unmanned aerial vehicles with multispectral cameras for monitoring the condition of olive groves with high accuracy. Multispectral images of olive groves provided detailed insight into the spectral data required for the analysis of vegetation indices. Using deep learning-based object detection, individual olive trees were identified within the images, which allowed the extraction of parts corresponding to each tree. To separate the background from the canopy, segmentation based on the monocular depth estimation algorithm, Depth Anything, was applied. In this way, elements that are not part of the tree’s crown were removed for more accurate analysis and calculation of the NDVI (Normalized Difference Vegetation Index) and NDRE (Normalized Difference Red Edge Index) indices. The obtained results were compared with the results obtained for unsegmented patches, threshold-based patches, and manually segmented patches. The comparison and analysis carried out shows that the proposed segmentation approach improved the accuracy of NDVI and NDRE by focusing exclusively on the crowns of the observed trees, excluding the noise of the surrounding vegetation and soil. In addition, measurements were carried out on three observed olive groves at different parts of the vegetation cycle, and the values of the vegetation indices were compared. This integrated method combining drone-based multispectral imaging, deep learning object detection, and advanced segmentation techniques highlights a robust approach to olive tree health monitoring and provides insight into seasonal vegetation dynamics, for winter and spring, to capture differences in vegetative activity.