A reliable environment perception is a crucial task for autonomous driving, especially in dense traffic areas. Recent improvements and breakthroughs in scene understanding for intelligent transportation systems are mainly based on deep learning and the fusion of different modalities. In this context, we introduce OLIMP: A heterOgeneous Multimodal Dataset for Advanced EnvIronMent Perception. This is the first public, multimodal and synchronized dataset that includes UWB radar data, acoustic data, narrow-band radar data and images. OLIMP comprises 407 scenes and 47,354 synchronized frames, presenting four categories: pedestrian, cyclist, car and tram. The dataset includes various challenges related to dense urban traffic such as cluttered environment and different weather conditions. To demonstrate the usefulness of the introduced dataset, we propose a fusion framework that combines the four modalities for multi object detection. The obtained results are promising and spur for future research.

Vehicular ad hoc networks allow vehicles to share their information for the safety and efficiency of traffic purposes. However, information sharing can threaten the driver’s privacy as it includes spatiotemporal information, and the messages are unencrypted and broadcasted periodically. Therefore, they cannot estimate their privacy level because it also depends on their surroundings. This article proposes a centralized adaptive pseudonym change scheme that permits the certificate’s authority to adjust the pseudonyms assignment for each requesting vehicle. This scheme adapts dynamically depending on the density of the traffic environment and the user’s privacy level, and it aims to solve the trade-off problem between wasting pseudonyms and Sybil attack. We employ a Knapsack problem-based algorithm for target tracking and an entropy-based method to measure each vehicle’s privacy. In order to demonstrate the applicability of our framework, we use real-life data captured during the interoperability tests of the European project InterCor. According to the experimental results, the proposed scheme could easily estimate the level of confidentiality and, therefore, may best respond to the adaptation of the pseudonyms.

Vehicular communications have become essential for functional and road safety purposes due to the development of vehicle fleets. However, these communications have made vehicles more vulnerable to cyber-attacks. The security of data exchanges in vehicular networks currently relies on a centralized architecture that is responsible for managing various security services such as authentication, confidentiality, non-repudiation, real-time misbehavior detection, certificate management and revocation. However, this centralized approach can be challenging and costly for authorities, and it may even weaken the network's overall security. In this paper, we propose a complementary solution that uses a decentralized security framework to help authorities better manage their network security by involving each vehicle in the overall security management. Our framework, TileChain, is blockchain based solution that use road information to manage the network's security dynamically. The architecture is designed to optimize any security service efficiently. To demonstrate the feasibility and performance of our proposed solution, we selected certificate revocation as a critical service and performed simulations using real vehicle traffic data provided by The French road operator DIR Nord. Our Smart Contract achieved an accuracy of 81.3% in misbehavior detection, leading to certificate revocation. Furthermore, the computation load for security management by authorities potentially reduced by a factor of 96.8%. In summary, our proposed solution, TileChain, offers a promising decentralized approach for managing vehicular network security that can potentially improve the overall security of the network while reducing the computational burden on authorities.

The emergence of Vision-Language Models (VLMs) like Contrastive Language-Image Pretraining (CLIP) provides appealing solutions to various vision problems including Dynamic Facial Expression Recognition (DFER). However, most of the proposed approaches face major challenges, particularly related to inefficient full fine-tuning of the encoders and the complexity of the models. Moreover, some of the proposed methods seem to struggle with suboptimal performance due to (i) poor alignment between textual and visual representations, and (ii) ineffective temporal modeling. To address these challenges, we propose PE-CLIP, a parameter-efficient fine-tuning (PEFT) framework that elegantly adapts CLIP for dynamic facial expression recognition, requiring significantly reduced number of trainable parameters while maintaining high accuracy. At its core, to enhance efficiency and performance, PE-CLIP introduces two specialized adapters namely a Temporal Dynamic Adapter (TDA) and a Shared Adapter (ShA). The TDA is a GRU-based module with a dynamic scaling mechanism, capturing sequential dependencies while adaptively modulating the contribution of each temporal feature to emphasize the most informative ones while mitigating irrelevant variations. The ShA is a lightweight adapter refine representations within both textual and visual encoders, ensuring consistent feature processing while maintaining parameter efficiency. Additionally, we leverage Multi-modal Prompt Learning (MaPLe), which introduces learnable prompts to both visual and action unit-based textual description inputs, further improving the semantic alignment between modalities and enabling the efficient adaptation of CLIP for dynamic tasks. We evaluate our proposed PE-CLIP on two benchmark datasets, namely DFEW, FERV39K, and AFEW, achieving competitive performance compared to state-of-the-art methods while requiring fewer trainable parameters. By striking an optimal balance between parameter efficiency and performance, PE-CLIP sets a new benchmark in resource-efficient DFER. The source code of the proposed PE-CLIP will be publicly available at https://github.com/Ibtissam-SAADI/PE-CLIP .

This paper presents a novel vehicular environment identification approach based on deep learning. It consists of exploiting the vehicular wireless channel characteristics in the form of Channel State Information (CSI) in the receiver side of a connected vehicle in order to identify the environment type in which the vehicle is driving, without any need to implement specific sensors such as cameras or radars. We consider environment identification as a classification problem, and propose a new convolutional neural network (CNN) architecture to deal with it. The estimated CSI is used as the input feature to train the model. To perform the identification process, the model is targeted for implementation in an autonomous vehicle connected to a vehicular network (VN). The proposed model is extensively evaluated, showing that it can reliably recognize the surrounding environment with high accuracy ($96.48\%$). Our model is compared to related approaches and state-of-the-art classification architectures. The experiments show that our proposed model yields favorable performance compared to all other considered methods.

The detection and quantification of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) virus particles in ambient waters using a membrane-based in-gel loop-mediated isothermal amplification (mgLAMP) method can play an important role in large-scale environmental surveillance for early warning of potential outbreaks. However, counting particles or cells in fluorescence microscopy is an expensive, time-consuming, and tedious task that only highly trained technicians and researchers can perform. Although such objects are generally easy to identify, manually annotating cells is occasionally prone to fatigue errors and arbitrariness due to the operator’s interpretation of borderline cases. In this research, we proposed a method to detect and quantify multiscale and shape variant SARS-CoV-2 fluorescent cells generated using a portable (mgLAMP) system and captured using a smartphone camera. The proposed method is based on the YOLOv5 algorithm, which uses CSPnet as its backbone. CSPnet is a recently proposed convolutional neural network (CNN) that duplicates gradient information within the network using a combination of Dense nets and ResNet blocks, and bottleneck convolution layers to reduce computation while at the same time maintaining high accuracy. In addition, we apply the test time augmentation (TTA) algorithm in conjunction with YOLO’s one-stage multihead detection heads to detect all cells of varying sizes and shapes. We evaluated the model using a private dataset provided by the Linde + Robinson Laboratory, California Institute of Technology, United States. The model achieved a mAP@0.5 score of 90.3 in the YOLOv5-s6.