Enhancing Facial Expression Recognition through Light Field Cameras.

In this paper, we study facial expression recognition (FER) using three modalities obtained from a light field camera: sub-aperture (SA), depth map, and all-in-focus (AiF) images. Our objective is to construct a more comprehensive and effective FER system by investigating multimodal fusion strategies. For this purpose, we employ EfficientNetV2-S, pre-trained on AffectNet, as our primary convolutional neural network. This model, combined with a BiGRU, is used to process SA images. We evaluate various fusion techniques at both decision and feature levels to assess their effectiveness in enhancing FER accuracy. Our findings show that the model using SA images surpasses state-of-the-art performance, achieving 88.13% ± 7.42% accuracy under the subject-specific evaluation protocol and 91.88% ± 3.25% under the subject-independent evaluation protocol. These results highlight our model's potential in enhancing FER accuracy and robustness, outperforming existing methods. Furthermore, our multimodal fusion approach, integrating SA, AiF, and depth images, demonstrates substantial improvements over unimodal models. The decision-level fusion strategy, particularly using average weights, proved most effective, achieving 90.13% ± 4.95% accuracy under the subject-specific evaluation protocol and 93.33% ± 4.92% under the subject-independent evaluation protocol. This approach leverages the complementary strengths of each modality, resulting in a more comprehensive and accurate FER system.

Fast Visual Odometry for a Low-Cost Underwater Embedded Stereo System †.

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.

Underwater Photogrammetry and Object Modeling: A Case Study of Xlendi Wreck in Malta.

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.