This paper introduces a method to automatically learn the unary and pairwise potentials of a conditional random field (CRF) from the input data in a non-parametric fashion, within the framework of the semantic segmentation of remote sensing images. The proposed model is based on fully convolutional networks (FCNs) and fully connected neural networks (FCNNs) to extensively exploit the semantic and spatial information contained in the input data and in the intermediate layers of an FCN. The idea of the model is twofold: first to learn the statistics of a CRF via a convolutional layer, whose kernel defines the clique of interest, and, second, to favor the interpretability of the intermediate layers as posterior probabilities through the FCNNs. The method was tested with the ISPRS 2D Semantic Labeling Challenge Vaihingen dataset, after modifying the ground truths to approximate the ones found in realistic remote sensing applications, characterized by scarce and spatially non-exhaustive annotations. The results confirm the effectiveness of the proposed technique for the semantic segmentation of satellite images.
Drug sample comparison is a process used by the French National Police to identify drug distribution networks. The current approach is based on a manual comparison done by forensic experts. In this article, we present our approach to acquire, formalise, and specify expert knowledge to improve the current process. We use an ontology coupled with logical rules to model the underlying knowledge. The different steps of our approach are designed to be reused in other application domains.The results obtained are explainable making them usable by experts in different fields.
Guided image processing techniques are widely used for extracting information from a guiding image to aid in the processing of the guided one. These images may be sourced from different modalities, such as 2D and 3D, or different spectral bands, like visible and infrared. In the case of guided cross-spectral super-resolution, features from the two modal images are extracted and efficiently merged to migrate guidance information from one image, usually high-resolution (HR), toward the guided one, usually low-resolution (LR). Different approaches have been recently proposed focusing on the development of architectures for feature extraction and merging in the cross-spectral domains, but none of them care about the different nature of the given images. This paper focuses on the specific problem of guided thermal image super-resolution, where an LR thermal image is enhanced by an HR visible spectrum image. To improve existing guided super-resolution techniques, a novel scheme is proposed that maps the original guiding information to a thermal image-like representation that is similar to the output. Experimental results evaluating five different approaches demonstrate that the best results are achieved when the guiding and guided images share the same domain.
This paper introduces a novel approach for assessing the quality of 3D point clouds using a deep learning-based no-reference (NR) method. Our framework employs transfer learning to extract high-level features from distorted point clouds. We incorporate the VGG16 model as the foundation for our modified trained model. To achieve this, we make slight modifications to the VGG16 model, transforming them into 1D variants. Additionally, we leverage the weights from ImageNet-trained 2D models to obtain weights for our 1D model. By utilizing this model, we extract both geometric and perceptual features. The point cloud characteristics are estimated using statistical properties such as entropy, standard deviation, skewness, kurtosis, median, and mean. We employ the Support Vector Regressor (SVR) for regression and quality score prediction. To validate our method, we conduct experiments on subjective databases, including (SJTU-PCQA, and ICIP2020). The results demonstrate that the proposed method outperforms several competing methods.
This paper proposes a framework for efficient personalized adaptation remote service support in meta-verse and thus, provides a human-centered computing approach. This work was initiated by an empathy-driven sensitive listening counselor bot enhanced by real and virtual services including digital twins selected by a powerful need/offer matching. This matching is leveraged on Autonomous Decentralization Network, Intention Based Network for efficiency and Distributed Ledger Technology for safety. This framework combines proven technologies such as fusing the real and virtual world by interactive connections between them, an intelligent AI matching algorithm, gaining experience from its own use, and using well-proven “old” technologies such as spatio-temporally encryption, Blockchain, Distributed Ledger Technology, distributed storage with redundancy, for example. This framework makes it possible to provide highly efficient teleservice including telemedicine in virtual spaces, which enables eternal evolution. Moreover, this paper introduces a concept for an integrated learning and evolutionary self-improvement of our metaverse system.
