The article describes an approach which allows for the creation of immersive and virtual art gallery for users with reduced mobility. Indeed, this user community often lacks accessibility towards comfortably visiting art galleries or museums. For this reason, we propose to public and private art societies the creation of 3D Augmented Virtuality (AV) environments which facilitate the painting visualization through a visitor-customized mobile application. By this way, visitors with reduced mobility can explore galleries without needing to move. Moreover, galleries can easily load and share the entire content of paintings in such a virtual environment, enriching them its sharing ability of art work collections. Experimental results and evaluation show the potential of the proposed approach for creating digital museums and other virtual visiting environments with interconnected phone-based immersive application.

Second-hand shopping, primarily via online marketplaces, has rapidly increased during the last decade. Nowadays, consumers widely choose the Pick-Up Point (PUP) service to facilitate the delivery of products. Parcels related to this Customer-to-Customer (C2C) activity are dropped off in PUPs chosen by the sellers, shipped to PUPs selected by the buyers where they wait to be picked up. The increased impact of C2C parcels on PUPs requires an improved control of their load to reduce the risks of PUP overload, parcel rerouting, and resulting customer dissatisfaction.This paper presents a forecasting approach for the load of PUPs receiving C2C parcels. The daily number of parcels dropped off with a given PUP as target is described by a Markov-Switching Auto-Regressive (MSAR) model to account for the non-stationarity of the second-hand shopping activity. A PUP Management Company, using this forecasting approach, is able to propose customers only target PUPs that are likely not to be overloaded at time of delivery. The proposed approach is compared to load prediction techniques involving SARIMA, Holt-Winters, LSTM, Prophet, and TiDE models. For the considered PUP, the load is predicted from one up to seven days ahead with mean absolute errors ranging from 5.5 parcels (1 day ahead) to 8.8 parcels (7 days ahead) for a PUP with an average load of 25 parcels. Similar results are shown for other PUPs.

Cooperative intelligent transportation systems (cooperative ITS or C-ITS) rely on the communications and sharing of information between vehicles, road infrastructures and communication infrastructure to improve users’ safety, facilitate their trips and ensure the safety of road agents. This chapter presents the technological advances in the field of ITS in the context of the democratization of the communication between vehicle and infrastructure using ITS-G5. A new type of electronic toll collection service based on this type of communication is presented in this chapter. Its objective is to reduce maintenance costs, increase agents’ safety and improve traffic fluidity.

This SHREC 2025 track dedicated to protein surface shape retrieval involved 9 participating teams. We evaluated the performance in retrieval of 15 proposed methods on a large dataset of 11,555 protein surfaces with calculated electrostatic potential (a key molecular surface descriptor). The performance in retrieval of the proposed methods was evaluated through different metrics (Accuracy, Balanced accuracy, F1 score, Precision and Recall). The best retrieval performance was achieved by the proposed methods that used the electrostatic potential complementary to molecular surface shape. This observation was also valid for classes with limited data which highlights the importance of taking into account additional molecular surface descriptors.

This paper presents a software engineering archi-tecture, which permits the analysis and collection of semantic information from textual images using a mobile phone. The development of processes for information extraction and information enhancement is becoming widely investigated by the community, due to new services requiring AI-based functionalities. Moreover, there is a growing need for solutions that aid individuals with specific needs, such as visually impaired people, refugees, and visitors in understanding their surrounding environment. In particular, we present an architecture that can respond to these needs by automatically providing an intelligent description of surrounding texts. This can be effectively accomplished by integrating various services and technologies into a single entity, which can be utilized by personal smartphones.

The deployment of electric vehicles represents a promising solution to reduce air pollutant emissions and transport costs, especially in urban areas and short supply chains. This paper focuses on the Electric Vehicle Routing Problem in Short Food Supply Chains (EVRP-SFSCs), with the aim of reducing total energy consumption and ensuring efficient delivery of local produce. The study proposes an optimization and simulation approach, using a mixed integer linear program to minimize energy consumption while respecting various structural and operational constraints related to energy, capacity, and delivery requirements. In addition, the Simulation of Urban MObility software is used to simulate the optimized routes, considering dynamic traffic flow constraints and vehicle dynamics. The results highlight the importance of considering different dimensions and parameters for sustainable routing in SFSCs.

The development of Short Food Supply Chains (SFSCs) using a fleet of electric vehicles is one way of reducing the carbon footprint. In this study, we looked at optimizing electric vehicle routes in order to minimize energy consumption under constraints of vehicle capacity (trucks), client demand and battery capacity. The Simulation of Urban MObility tool is used to simulate road traffic and estimate the energy consumed by vehicles. In our study, we proposed a solution based on a constrained clustering approach.

Gesture recognition is a tool to enable novel interactions with different techniques and applications, like Mixed Reality and Virtual Reality environments. With all the recent advancements in gesture recognition from skeletal data, it is still unclear how well state-of-the-art techniques perform in a scenario using precise motions with two hands. This paper presents the results of the SHREC 2024 contest organized to evaluate methods for their recognition of highly similar hand motions using the skeletal spatial coordinate data of both hands. The task is the recognition of 7 motion classes given their spatial coordinates in a frame-by-frame motion. The skeletal data has been captured using a Vicon system and pre-processed into a coordinate system using Blender and Vicon Shogun Post. We created a small, novel dataset with a high variety of durations in frames. This paper shows the results of the contest, showing the techniques created by the 5 research groups on this challenging task and comparing them to our baseline method.

Pick-Up Points (PUPs) represent an alternative delivery option for online purchases. Parcels are delivered at a reduced cost to PUPs and wait until being picked up by customers or returned to the original warehouse if their sojourn time is over. When the chosen PUP is overloaded, the parcel may be refused and delivered to the next available PUP on the carrier tour. This paper presents and compares forecasting approaches for the load of a PUP to help PUP management companies balance delivery flows and reduce PUP overload. The parcel life-cycle has been taken into account in the forecasting process via models of the flow of parcel orders, the parcel delivery delays, and the pick-up process. Model-driven and data-driven approaches are compared in terms of load-prediction accuracy. For the considered example, the best approach (which makes use of the relationship of the load with the delivery and pick-up processes) is able to predict the load up to 4 days ahead with mean absolute errors ranging from 3.16 parcels (1 day ahead) to 8.51 parcels (4 days ahead) for a PUP with an average load of 45 parcels.

The growth of e-commerce has resulted in a surge in parcel deliveries, increasing transportation costs and pollution issues. Alternatives to home delivery have emerged, such as the delivery to so-called parcel pick-up points (PUPs), which eliminates delivery failure due to customers not being at home. Nevertheless, parcels reaching overloaded PUPs may need to be redirected to alternative PUPs, sometimes far from the chosen ones, which may generate customer dissatisfaction. Consequently, predicting the PUP load is critical for a PUP management company to infer the availability of PUPs for future orders and better balance parcel flows between PUPs. This paper proposes a new approach to forecasting the PUP load evolution using a Markov jump process that models the parcel life cycle. The latest known status of each parcel is considered to estimate its contribution to the future load of its target PUP. This approach can account for the variability of activity, the various parcel preparation delays by sellers, and the diversity of parcel carriers that may result in different delivery delays. Here, results are provided for predicting the load associated with parcels ordered from online retailers by customers (Business-to-Customer, B2C). The proposed approach is generic and can also be applied to other parcel flows to PUPs, such as second-hand products (Customer-to-Customer, C2C) sent via a PUP network.

The data incest problem causes inter-estimate correlation during data fusion processes, which yields inconsistent data fusion results. Especially in the multi-sensor multi-vehicle (MSMV) system, the data incest problem is serious due to multiple relative position estimations, which not only lead to pessimistic estimation but also cause additional computational overhead. In order to address the data incest problem, we propose a new data fusion method termed the interval split covariance intersection filter (ISCIF). The general consistency of the ISCIF is proven, serving as supplementary proof for the split covariance intersection filter (SCIF). Moreover, a decentralized MSMV localization system including absolute and relative positioning stages is designed. In the absolute positioning stage, each vehicle uses the ISCIF algorithm to update its own position based on absolute measurements. In the relative position stage, the interval constraint propagation (ICP) method is implemented to preprocess multiple relative position estimates and initially prepare input data for ISCIF. Then, the proposed ISCIF algorithm is employed to realize relative positioning. In addition, comparative simulations demonstrate that the proposed method can achieve both accurate and consistent results compared with the state-of-the-art methods.

The implementation of object detection in the maritime domain plays a crucial role in safeguarding maritime security, ensuring navigation safety, and upholding environmental protection. The escalating instances of unlawful maritime activities, including piracy and smuggling, underscore the pressing need for robust object detection systems capable of promptly identifying unauthorized vessels and preempting illicit intrusions. In this paper, we propose to consider the implementation of the attention mechanisms and the low-visibility enhancement network (LVENet) in addressing challenges and advancements related to object detection in the maritime domain. The intricacies of the maritime environment, encompassing its diverse and dynamic objects, vessel outlines, occlusions, and the constraints of annotated datasets, pose distinctive obstacles. Addressing these challenges, attention mechanisms emerge as a pivotal solution by honing in on critical image regions and adapting to the maritime environment’s ever-changing conditions. The evaluation of six cutting-edge models based on attention mechanism using maritime datasets SeaShips and Singapore Maritime Dataset (SMD), coupled with the integration of LVENet, highlights significant enhancements in mean average precision (mAP) scores. LVENet notably bolsters object detection in scenarios with reduced visibility in the maritime domain, contributing to an average mean precision increase of 2.1–5.0

In the cooperative multi-sensor multi-vehicle (MSMV) localization domain, the data incest problem yields inconsistent data fusion results, thereby reducing the accuracy of vehicle localization. In order to address this problem, we propose the interval split covariance intersection filter (ISCIF). At first, the proposed ISCIF method is applied to the absolute positioning step. Then, we combine the interval constraint propagation (ICP) method and the proposed ISCIF method to realize relative positioning. Additionally, in order to enhance the robustness of the MSMV localization system, a Kullback–Leibler divergence (KLD)-based fault detection and exclusion (FDE) method is implemented in our system. Three simulations were carried out: Simulation scenarios 1 and 2 aimed to assess the accuracy of the proposed ISCIF with various capabilities of absolute vehicle positioning, while simulation scenario 3 was designed to evaluate the localization performance when faults were present. The simulation results of scenarios 1 and 2 demonstrated that our proposed vehicle localization method reduced the root mean square error (RMSE) by 8.9% and 15.5%, respectively, compared to the conventional split covariance intersection filter (SCIF) method. The simulation results of scenario 3 indicated that the implemented FDE method could effectively reduce the RMSE of vehicles (by about 55%) when faults were present in the system.

Amid the rapid advancement of wireless network technologies, the forthcoming ubiquity of the Internet of Things (IoT) necessitates the development of sophisticated architectural frameworks and algorithms capable of handling the associated spectrum management complexities. This study proposes an innovative Mobile Broadband Internet of Things (MBIN) architecture, designed to facilitate efficient progression of the impending IoT revolution. The centerpiece of this architecture is a ground-breaking Advanced Cloud-Enabled Double Auction (ACEDA) algorithm. Deployed within the MBIN framework, this mechanism optimizes the sharing of spectrum resources, thereby enhancing the performance of the IoT structure. Theoretical grounding, algorithmic implementation, simulation results, and user satisfaction analysis are discussed in-depth to validate the efficacy of this approach.

In the Multi-sensor multi-vehicle (MSMV) cooperative localization system, the data incest problem generates inter-estimate correlation, leading to over-convergence problems. For the purpose of solving the data incest problem, we propose a method named interval split covariance intersection filter (ISCIF). First, the consistency proof of ISCIF is provided. Then, ISCIF is applied to achieve vehicle cooperative localization, including both absolute and relative positioning stage. Moreover, in order to reduce the computational overhead and address pessimistic estimation problems caused by multiple relative position estimates in the MSMV cooperative localization system, the interval constraint propagation (ICP) method is employed for data preprocessing before relative positioning using ISCIF. Finally, two different simulation experiment scenarios are designed to validate localization accuracy. Simulation results demonstrate that our proposed method, compared to the traditional split covariance intersection filter (SCIF) method, reduces the root mean square error (RMSE) by 13% and 21% in two different experimental scenarios, respectively.

Vehicle localization plays a crucial role in ensuring the safe operation of autonomous vehicles and the development of intelligent transportation systems (ITS). However, there is insufficient effort to compare the performance and challenges of different vehicle localization algorithms. This paper aims to address this gap by analyzing the comprehensive performance of existing advanced vehicle localization techniques and discussing their challenges. Firstly, we analyze the self-localization methods based on active and passive sensors. The results show that, the light detection and ranging (LiDAR) and vision-based localization techniques can reach high accuracy. However, they have high computational complexity. Only using the inertial measurement unit (IMU), global positioning system (GPS), radar, and ultrasonic sensors may not realize localization result with high accuracy. Then, we discuss V2X-based cooperative localization methods, analyze the multi-sensor based localization techniques and compare the comprehensive performance among all methods. Although the artificial intelligence (AI) techniques can effectively enhance the efficiency of vision-based localization algorithms, the high computational complexity still should be considered. In addition, since the IMU, GPS, radar, and ultrasonic sensors have good performance in terms of the availability, reliability, scalability, and cost-effectiveness, they can be used as auxiliary sensors to achieve good comprehensive performance through data fusion techniques. Finally, we propose the challenges of different techniques and look forward to future work.

Regional dropout strategies have demonstrated to be very effective in improving both the performance and the generalization capability of deep learning models. However, when such strategies are performed in a totally random manner, the background noise and label mismatch problems arise. To tackle such problems, existing approaches typically focus on regions with the highest distinctiveness. Yet, there are two main drawbacks of existing approaches: (I) Many existing region-based augmentation methods can only use rectangular regions, resulting in the loss of object contour information; (II) Deterministic se-lection of the most discriminative regions leads to poor diversification in data augmentation. In fact, a trade-off is needed between diversification and concentration, which can decrease the undesirable noise.In this paper, we propose a novel object-centric contour-aware CutMix data augmentation strategy with arbitrary-shape and size superpixel supports, which is hereafter referred to as OcCaMix for short. It not only captures the most discriminative regions, but also effectively preserves the contour details of the objects. Moreover, it enables the search of natural object parts of different sizes. Extensive experiments on a large number of benchmark datasets show that OcCaMix significantly outperforms state-of-the-art CutMix based data augmentation methods in classification tasks. The source codes and trained models are available at https://github.com/DanielaPlusPlus/OcCaMix .(c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )

This paper provides an adaptive pruning approach to compress Multi-Head Self Attention (MHSA) models. The main aim is to suppress redundant attention heads, requiring high computational complexity, without substantially affecting performance. Through head pruning, we propose more flexible and efficient models for the object detection tasks. Specifically, we propose to enhance the architectures of the two state-of-the-art MHSA-based models: Bottleneck Transformers (BoTNet) and Attention Augmented Convolutional Networks (AACN). Our approach relies on the alternation between the escalation and the ablation of heads. We selected the less productive heads. We suggest to exploit two and four heads, rather than four and eight heads for BotNet and AACN models, respectively. Our experiments on ImageNet and Pascal VOC datasets prove that our light-weighted architectures are more efficient compared with the original heavy-weighted ones. We reach close performances and achieve faster convergence during training, which allows easier transfer and deployment.