In this paper we present a photogrammetry-based approach for deep-sea underwater surveys conducted from a submarine and guided by knowledge-representation combined with a logical approach (ontology). Two major issues are discussed in this paper. The first concerns deep-sea surveys using photogrammetry from a submarine. Here the goal was to obtain a set of images that completely covered the selected site. Subsequently and based on these images, a low-resolution 3D model is obtained in real-time, followed by a very high-resolution model produced back in the laboratory. The second issue involves the extraction of known artefacts present on the site. This aspect of the research is based on an a priori representation of the knowledge involved using systematic reasoning. Two parallel processes were developed to represent the photogrammetric process used for surveying as well as for identifying archaeological artefacts visible on the sea floor. Mapping involved the use of the CIDOC-CRM system (International Committee for Documentation (CIDOC)—Conceptual Reference Model)—This is a system that has been previously utilised to in the heritage sector and is largely available to the established scientific community. The proposed theoretical representation is based on procedural attachment; moreover, a strong link is maintained between the ontological description of the modelled concepts and the Java programming language which permitted 3D structure estimation and modelling based on a set of oriented images. A very recently discovered shipwreck acted as a testing ground for this project; the Xelendi Phoenician shipwreck, found off the Maltese coast, is probably the oldest known shipwreck in the western Mediterranean. The approach presented in this paper was developed in the scope of the GROPLAN project (Généralisation du Relevé, avec Ontologies et Photogrammétrie, pour l'Archéologie Navale et Sous-marine). Financed by the French National Research Agency (ANR) for four years, this project associates two French research laboratories, an industrial partner, the University of Malta, and Texas A & M University.

Melanoma is still a major health problem worldwide. The early diagnosis is the first step toward reducing its mortality, but it remains a challenge even for experienced dermatologists. While computer-aided systems have been developed to help the diagnosis, the lack of insight of their predictions is still a significant limitation towards acceptance by the medical community. To tackle this issue, we designed handcrafted expert features representing color asymmetry within the lesions, which are parts of the approach used by dermatologists in their daily practice. These features are given to an artificial neural network (ANN) classifying between nevi and melanoma. We compare our results with an ensemble of seven state-of-the-art CNNs and merge the two approaches by computing the average prediction. Our experiments are done on a subset of the International Skin Imaging Collaboration (ISIC) 2019 dataset (6296 nevi, 1361 melanomas). The ANN based on asymmetry achieved an AUC of 0.873, Sensitivity 90%, Specificity 67%, the CNN approach achieved an AUC of 0.938, Sensitivity 91%, Specificity 82%, and the fusion of both approaches was 0.942, Sensitivity 92%, Specificity 82%. Merging the knowledge of dermatologists with CNNs showed high performances for melanoma detection, encouraging collaboration between computer science and medical fields.

This paper provides details of hardware and software conception and realization of a stereo embedded system for underwater imaging. The system provides several functions that facilitate underwater surveys and run smoothly in real-time. A first post-image acquisition module provides direct visual feedback on the quality of the taken images which helps appropriate actions to be taken regarding movement speed and lighting conditions. Our main contribution is a light visual odometry method adapted to the underwater context. The proposed method uses the captured stereo image stream to provide real-time navigation and a site coverage map which is necessary to conduct a complete underwater survey. The visual odometry uses a stochastic pose representation and semi-global optimization approach to handle large sites and provides long-term autonomy, whereas a novel stereo matching approach adapted to underwater imaging and system attached lighting allows fast processing and suitability to low computational resource systems. The system is tested in a real context and shows its robustness and promising future potential.

Estimating gaze direction is a key task in computer vision, especially for understanding where a person is focusing their attention. It is essential for applications in assistive technology, medical diagnostics, virtual environments, and human–computer interaction. In this work, we introduce Dual Focus-3D, a novel hybrid deep learning architecture that combines appearance-based features from eye images with 3D head orientation data. This fusion enhances the model’s prediction accuracy and robustness, particularly in challenging natural environments. To support training and evaluation, we present EyeLis, a new dataset containing 5206 annotated samples with corresponding 3D gaze and head pose information. Our model achieves state-of-the-art performance, with a MAE of 1.64° on EyeLis, demonstrating its ability to generalize effectively across both synthetic and real datasets. Key innovations include a multimodal feature fusion strategy, an angular loss function optimized for 3D gaze prediction, and regularization techniques to mitigate overfitting. Our results show that including 3D spatial information directly in the learning process significantly improves accuracy.

Keywords: Visual odometry, underwater imaging, computer vision, probabilistic modelling, embedded systems A light distributed visual odometry method adapted to embedded hardware platform is proposed. The aim is to guide underwater surveys in real time. We rely on image stream captured using portable stereo rig attached to the embedded system. Taken images are analyzed on the fly to assess image quality in terms of sharpness and lightness, so that immediate actions can be taken accordingly. Images are then transferred over the network to another processing unit to compute the odometry. Relying on a standard ego-motion estimation approach, we speed up points matching between image quadruplets using a low level points matching scheme relying on fast Harris operator and template matching that is invariant to illumination changes. We benefit from having the light source attached to the hardware platform to estimate a priori rough depth belief following light divergence over distance low. The rough depth is used to limit points correspondence search zone as it linearly depends on disparity. A stochastic relative bundle adjustment is applied to minimize re-projection errors. The evaluation of the proposed method demonstrates the gain in terms of computation time w.r.t. other approaches that use more sophisticated feature descriptors. The built system opens promising areas for further development and integration of embedded computer vision techniques.

Gaze interpretation is a fundamental aspect of social communication, especially for children with autism spectrum disorder (ASD), who frequently encounter many difficulties in social interactions. Despite the considerable advances made in gaze tracking technologies, such as those based on RGB and RGB-D, the accurate measurement of gaze direction remains a significant scientific challenge. This paper proposes a novel approach utilizing the Azure Kinect to improve the measurement of gaze intention in children with ASD, providing accurate estimations of both gaze direction and head position. To evaluate the effectiveness of the proposed methodology, an experimental trial was conducted with eight participants of varying statures. The intersection of the estimated gaze with the target plane was also analyzed throughout 38-min sessions. The results demonstrated high accuracy, with a minimum angular error of 2.5° using pupil positions, 2.06° using head orientation, and average errors of 4.46° and 3.19°, respectively. This approach was tested on a dataset of children with ASD to track their gaze towards a clinician, as this information is essential for assessing the children’s social intent and interactions with others, facilitating more precise clinical assessments for children with autism.