The integration of the global navigation satellite system (GNSS), odometer, and inertial navigation system (INS) holds significant potentials for achieving high-precision vehicle localization. However, GNSS is vulnerable to obstructions and jamming, and the odometer is unreliable in harsh road conditions. These factors can lead to cumulative positioning errors in GNSS-denied environments. To address these issues, a novel multi-source information fusion based vehicle localization method that integrates an onboard binocular camera, an INS, and smart road studs—Internet of Things (IoT) devices extensively used for road safety and data collection in intelligent transportation systems— is introduced. We construct a position measurement model directly in the camera coordinate system through an enhanced You Only Look Once 8th version (YOLOv8) algorithm for smart road stud detection, combined with binocular vision measurement and position transformations. Additionally, we propose a method to enhance vehicle localization accuracy by integrating vehicle speed without relying on additional hardware speed sensors. The vehicle’s speed is estimated from the image sequences captured by the onboard camera using a deep neural network (DNN), named Speed-Net. The final navigation results are produced by fusing the smart road stud aided positioning information, the estimated vehicle speed, and INS data through an error-state extended Kalman filter (ESEKF). Real-world experiments demonstrate the effectiveness of the proposed Smart road stud (SRS)/Velocity/INS integrated vehicle localization method.

Weakly supervised learning has emerged as a powerful paradigm for image segmentation, providing a practical solution to reduce the dependence on costly, pixel-level annotated datasets. By leveraging partial annotations, such as image-level tags, this approach significantly reduces the labeling burden while maintaining competitive performance. However, weakly supervised methods inherently face challenges, including overlapping activation regions and insufficient localization due to sparse and noisy signals from image-level tags, often leading to suboptimal segmentation performance. These issues are further exacerbated in industrial defect localization, where datasets present unique complexities, including low-contrast object boundaries, inconsistent shapes, interclass similarities, and substantial intraclass variations. To address these limitations, we introduce a novel saliency-guided transformer attention with contrastive learning framework. The proposed framework leverages Transformer attention to generate localization maps and enhances the learning of challenging foreground and background information through saliency-guided cues. In addition, a pixel-level contrastive learning module is employed to refine feature map representations by bringing positive pairs closer together and pushing negative pairs apart, effectively addressing challenges, such as overlapping activations and ambiguous boundaries. Through extensive experiments and ablation studies, the proposed method demonstrates superior performance compared to state-of-the-art approaches across three defect segmentation datasets. We also evaluated the generalization of our approach on the PASCAL VOC segmentation and MVTec anomaly detection datasets.

Traditional methods for tracking maneuvering targets, such as connected and automated vehicles, face significant challenges in complex driving environments due to the need for constant adjustments to the state transition model to match the target’s motion. These adjustments often result in decision-making delays and competition between models. Furthermore, the widely adopted first-order Markov assumption frequently fails to capture time-dependent motion patterns, leading to information loss. Although the Interacting Multiple Model (IMM) algorithm mitigates some of these issues by employing multiple motion models, it still struggles with accurately identifying motion patterns, delays in maneuver detection and reduced tracking accuracy. To address these problems, we propose a novel approach that combines deep neural networks with traditional IMM tracking methods. Leveraging the strength of deep learning in classification tasks, we introduce an attention mechanism to enhance motion model recognition. This leads to the development of an enhanced version of IMM, termed Attention-IMM. We evaluate our method on the widely-used LAST dataset and real word automated vehicles data. The results demonstrate that Attention-IMM achieves superior performance in both tracking accuracy and the timeliness and accuracy of model decision-making, offering a robust and efficient solution for maneuvering target tracking.

Sensor fusion plays an increasingly important role in real-time traffic perception using roadside sensing devices because the use of single type of sensors often fail to deliver satisfactory performance in certain harsh environment. This paper investigates asynchronous data fusion for real-time vehicle tracking with inaccurate and randomly delayed measurements from millimeter-wave (MMW) radars and magnetic sensors in tunnel environment. We first propose a multisensor data association algorithm to assign the measurements of MMW radar and magnetic sensors to a particular vehicle. A tracking algorithm is then designed to asynchronously update the current vehicle states with randomly delayed magnetic sensor measurements. The proposed algorithm is implemented in the Xianfengding Tunnel, Jiangxi Province, China. Experiments validate the proposed method's accuracy using real data. The method and collected data form the basis of a real-time digital twin system to support advanced traffic management. The fusion results and measurement dataset are available at https://github.com/futianxuan/data.

Smart road studs are widely used for road safety and traffic data collection. Their accurate and reliable detection, and integration into the perception and control modules of connected and autonomous vehicles (CAVs), enhances road boundary detection, vehicle localization, and driving safety. However, real-time, accurate and reliable detection of the small-sized smart road studs is challenging for fast moving CAVs, especially in harsh environments. To address the challenges, we first build a real-world smart road stud dataset, and then propose and validate a lightweight and efficient smart road stud detection model based on the you only look once 8th version (YOLOv8). We then introduce a novel downsampling module (DownS) combining the average pooling and the max pooling to reduce the number of parameters and minimize information loss during downsampling. Furthermore, we replace the loss function with Normalized Wasserstein Distance (NWD) loss to reduce sensitivity to location deviations in small target detection. Finally, we deploy a real-time smart road stud detection system on an experimental vehicle to validate the feasibility and effectiveness of the proposed algorithm. The experimental results demonstrate that the proposed algorithm significantly enhances the accuracy and efficiency of smart road stud detection, increasing the mean average precision by 9.58% and reducing the number of parameters by 13.71 %. Our dataset is available at: https://github.com/wky-xidian/smart-road-stud-dataset.

Sensor fusion plays an increasingly important role in real-time traffic perception using roadside sensing devices because the use of single type of sensors often fail to deliver satisfactory performance in certain harsh environment. This paper investigates asynchronous data fusion for lane-level vehicle tracking with randomly delayed measurements and inaccurate detections from millimeter wave (MMW) radars and magnetic sensors in tunnels, where vehicle tracking with single type of sensors can not meet the requirements of reliable and accurate lane-level tracking due to inaccurate radar detections at far distances, noisy radar detections in tunnel environment, and missed or false vehicle detections by magnetic sensors. A multisensor data association algorithm is first designed to assign the measurements of MMW radar and magnetic sensors to a particular vehicle. A multi-lane estimation model is then developed, which employs Bayesian weight mixture filtering to fuse MMW radar and magnetic sensor measurements and to estimate the lane in which a vehicle is located. Finally, the proposed algorithm is implemented in a real environment - the Xianfengding Tunnel located in Jiangxi Province, China. Experiments are conducted to validate the accuracy of the proposed method using real data. The proposed method and the collected data are further integrated to establish a real-time digital twin system aimed at supporting advanced traffic management. The fusion results and the real radar measurement dataset of the tunnel are made available athttps://github.com/futianxuan/data.

Smart road studs have been extensively deployed as road safety and data collection devices. Accurate and reliable detection of smart road studs and its further integration into the perception and control modules of connected and autonomous vehicles (CAVs) undoubtedly benefit road boundary detection, localization of CAVs and augument the safety of CAVs’ driving. This work investigates real-time, accurate and reliable detection of smart road studs, which is a challenging task for CAVs because existing methods fail to achieve accurate and real-time smart road stud detection, especially in harsh road environment. To address these challenges, we first build a real-world smart road stud dataset, and then propose and validate a lightweight and efficient smart road stud detection model based on the you only look once 8th version (YOLOv8), called SRS-YOLO. First, a Squeeze-and-Excitation (SE) attention module is used to improve the coarse-to-fine (C2F) module to differentiate the channel importance of feature maps and improve the detection accuracy of smart road studs. Second, a novel downsampling module (DownS) that integrates the average pooling and the max pooling is designed to reduce the number of parameters and minimize information loss during the downsampling process. Third, the loss function is replaced with the Normalized Wasserstein Distance (NWD) loss to alleviate the sensitivity to location deviations when computing the loss for small targets. The experimental results demonstrate that the proposed SRS-YOLO outperforms other state-of-the-art methods, and achieves a 87.92% mean average precision at a real-time speed of 78 frames/s. Our dataset is available at:https://github.com/wky-xidian/smart-road-stud-dataset.

Traffic prediction is an essential function of intelligent transportation system for traffic control and autonomous driving. Most existing methods encode traffic spatial and temporal data separately, and then design a feature fusion module to correlate spatial and temporal features. However, spatial information is often static, and repetitive static spatial encoding leads to waste of resources, especially in large-scale traffic network prediction. In this paper, we propose a dynamic edge interaction encoding method for spatio-temporal features based on inverse Transformer (iTransformer) and Graph Transformer, named iTPGT-former. The dynamic edge interaction process is designed to embed dynamic temporal features into static edges via a convolutional embedding module. To enhance the Graph Transformer, a relative position encoding strategy based on the self-attentive score of the positive definite kernel (PDK) on graphs and a method for graph substructure encoding (GSE) via enumeration of paths are introduced. In the experimental and discussion session, the iTPGT-former is considered for accuracy, parameters, inference speed, and rich ablation experiments are provided based on six publicly available traffic datasets. The results show that iTPGT-former outperforms the baseline model in both traffic flow and traffic speed prediction. The maximum improvement is achieved in the METR-LA 60-min speed prediction task, with 15.2% reduction in Mean Absolute Percentage Error (MAPE). In addition, the inference of iTPGT-former is significantly faster than the GCN-based method. Our implementation of the iTPGT-former is available athttps://github.com/ouyangnann/iTPGTN-former.

In this paper, we study the deployment of Unmanned Aerial Vehicles (UAVs) to collect data from IoT devices, by finding the data collection tour of each UAV. To ensure the `freshness' of the collected data, a strict requirement is that the total time spent in the tour of each UAV, which consists of UAV flying time and data collection time, must be no greater than a given maximum data collection delay B, e.g., 20 minutes. In this paper, we consider a problem of using the minimum number of UAVs and finding their data collection tours, subject to the constraint that the total time spent in each tour is no greater than B. We study two variants of the problem, one is that a UAV needs to fly to the location of each IoT device to collect its data; the other variant is that a UAV is able to collect the data of the IoT device as long as their Euclidean distance is no greater than a given wireless transmission range. For the first variant of the problem, we propose a novel 4-approximation algorithm, which improves the best approximation ratio 4 4/7 so far. For the second variant, we design the first constant factor approximation algorithm. In addition, we evaluate the performance of the proposed algorithms via extensive experiments, and experimental results show that the average numbers of UAVs deployed by the proposed algorithms are from 11% to 19% less than those by existing algorithms.

Wireless energy transfer technology based on magnetic resonant coupling has been emerging as a promising technology for wireless sensor networks (WSNs) by providing controllable yet perpetual energy to sensors. In this article, we study the deployment of the minimum number of mobile charging vehicles to charge sensors in a large-scale WSN so that none of the sensors will run out of energy, for which we first advocate a flexible on-demand charging paradigm that decouples sensor energy charging scheduling from the design of sensing data routing protocols. We then formulate a novel optimization problem of scheduling mobile charging vehicles to charge life-critical sensors in the network with an objective to minimize the number of mobile charging vehicles deployed, subject to the energy capacity constraint on each mobile charging vehicle. As the problem is NP-hard, we instead propose an approximation algorithm with a provable performance guarantee if the energy consumption of each sensor during each charging tour is negligible. Otherwise, we devise a heuristic algorithm by modifying the proposed approximation algorithm. We finally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results demonstrate that the proposed algorithms are very promising, and the solutions obtained are fractional of the optimal ones. To the best of our knowledge, this is the first approximation algorithm with a nontrivial approximation ratio for a novel scheduling problem of multiple mobile charging vehicles for charging sensors.

In this paper we study data collection in an energy renewable sensor network for scenarios such as traffic monitoring on busy highways, where sensors are deployed along a predefined path (the highway) and a mobile sink travels along the path to collect data from one-hop sensors periodically. As sensors are powered by renewable energy sources, time-varying characteristics of ambient energy sources poses great challenges in the design of efficient routing protocols for data collection in such networks. In this paper we first formulate a novel data collection maximization problem by adopting multi-rate data transmissions and performing transmission time slot scheduling, and show that the problem is NP-hard. We then devise an offline algorithm with a provable approximation ratio for the problem by exploiting the combinatorial property of the problem, assuming that the harvested energy at each node is given and link communications in the network are reliable. We also extend the proposed algorithm by minor modifications to a general case of the problem where the harvested energy at each sensor is not known in advance and link communications are not reliable. We thirdly develop a fast, scalable online distributed algorithm for the problem in realistic sensor networks in which neither the global knowledge of the network topology nor sensor profiles such as sensor locations and their harvested energy profiles is given. Furthermore, we also consider a special case of the problem where each node has only a fixed transmission power, for which we propose an exact solution to the problem. We finally conduct extensive experiments by simulations to evaluate the performance of the proposed algorithms. Experimental results demonstrate that the proposed algorithms are efficient and the solutions obtained are fractional of the optimum.

Energy is one of the most critical optimization objectives in wireless sensor networks. Compared with renewable energy harvesting technology, wireless energy transfer based on magnetic resonant coupling is able to provide more reliable energy supplies for sensors in wireless rechargeable sensor networks. The adoption of wireless mobile chargers (mobile vehicles) to replenish sensors' energy has attracted much attention recently by the research community. Most existing studies assume that the energy consumption rates of sensors in the entire network lifetime are fixed or given in advance, and no constraint is imposed on the mobile charger (e.g., its travel distance per tour). In this paper, we consider the dynamic sensing and transmission behaviors of sensors, by providing a novel charging paradigm and proposing efficient sensor charging algorithms. Specifically, we first formulate a charging throughput maximization problem. Since the problem is NP-hard, we then devise an offline approximation algorithm and online heuristics for it. We finally conduct extensive experimental simulations to evaluate the performance of the proposed algorithms. Experimental results demonstrate that the proposed algorithms are efficient.

In this paper, we study the use of multiple mobile charging vehicles to charge sensors in a large-scale wireless sensor network for a given monitoring period, where sensors can be charged by the vehicles with wireless power transfer. Since each sensor may experience multiple charges to avoid its energy expiration for the period, we first consider a charging problem of scheduling the multiple mobile vehicles to collaboratively charge sensors so that none of the sensors will run out of its energy and the sum of traveling distance (referred to as the service cost) of these vehicles can be minimized. Due to NP-hardness of the problem, we then propose a novel approximation algorithm for it, assuming that sensor energy consumption rates do not change over time. Otherwise, we devise a heuristic algorithm through minor modifications to the approximation algorithm. We finally evaluate the performance of the proposed algorithms via simulations. Experimental results show that the proposed algorithms are very promising, which can reduce upto 45% of the service cost in comparison with the service cost delivered by a greedy algorithm.

The emerging wireless energy transfer technology based on magnetic resonant coupling is a promising technology for wireless sensor networks as it can provide a controllable and perpetual energy source to sensors. In this paper we study the use of minimum number of wireless charging mobile vehicles to charge sensors in a sensor network so that none of the sensors runs out of its energy, subject to the energy capacity imposed on mobile vehicles, for which we first advocate an flexible on-demand wireless charging paradigm that decouples sensor energy charging scheduling from data routing protocols design. We then formulate an optimization problem of scheduling mobile vehicles to charge lifetime-critical sensors with an objective to minimize the number of mobile vehicles deployed, subject to the energy capacity constraint on each mobile vehicle. As the problem is NP-hard, we devise an approximation algorithm with a provable performance guarantee for it. We finally evaluate the performance of the proposed algorithm through experimental simulations. Experimental results demonstrate that the proposed algorithm is promising, and the solution obtained is fractional of the optimal.

With the advance of energy harvesting technology, more and more sensors now are powered by ambient energy. Energy harvesting sensor networks are a key step in paving the way for truly green systems that can operate `perpetually' and do not adversely impact on the environment. In this paper we consider quality data collection in an energy harvesting sensor network by exploring sink mobility. That is, we consider a mobile sink traveling along a to-be-found trajectory for data collection, subject to a specified tolerant delay constraint. We first formulate this optimization problem as a data quality maximization problem. Since the problem is NP-hard, we then devise a scalable heuristic solution. Also, a distributed implementation of the proposed algorithm is developed too. We finally conduct extensive experiments by simulation to evaluate the performance of the proposed algorithms. Experimental results demonstrate that the proposed algorithms are promising and very efficient.

In this paper, we study the use of a wireless charging vehicle (WCV) to replenish energy to sensors in a wireless sensor network so that none of the sensors will run out of its energy, where sensor batteries can be recharged. Specifically, we first propose a flexible on-demand sensor energy charging paradigm that decouples sensor energy replenishment and data collection into separate activities. We then formulate an optimization problem of wireless charging with an aim to maximize the ratio of the amount of energy consumed for charging sensors to the amount of energy consumed on traveling of the WCV as the WCV consumes its energy on both traveling and sensor charging. We also devise a novel algorithm for scheduling the tours of the WCV by jointly considering the residual lifetimes of sensors and the charging ratio of charging tours. We finally evaluate the performance of the proposed algorithm by conducting simulation. Experimental results show that the proposed algorithm is promising, and can improve the energy charging ratio of the WCV significantly.

In this paper we study data collection in an energy harvesting sensor network for traffic monitoring and surveillance purpose on busy highways, where sensors are densely deployed along a pre-defined path and a mobile sink travels along the path to collect data from one-hop sensors periodically. As the sensors are powered by renewable energy sources, the time-varying characteristics of energy harvesting poses great challenges on the design of efficient routing protocols for data collection in such energy harvesting sensor networks. In this paper we first formulate a novel data collection maximization problem that deals with multi-rate transmission mechanism and transmission time slot scheduling among the sensors. We then show the NPhardness of the problem and devise an offline algorithm with a provable approximation ratio for the problem by exploiting the combinatorial property of the problem, assuming that the global knowledge of the network topology and the profile of each sensor are given. We also develop a fast, scalable online distributed solution for the problem without the global knowledge assumption, which is more suitable for real distributive sensor networks. In addition, we consider a special case of the problem for which a optimal polynomial solution is given. We finally conduct extensive experiments by simulations to evaluate the performance of the proposed algorithms. Experimental results demonstrate that the proposed algorithms are very efficient, and the solutions are fractional of the optimum.

In this paper we study data collection in an energy harvesting sensor network where sensors are deployed along a given path and a mobile sink travels along the path periodically for data collection. Such a typical application scenario is to employ a mobile vehicle for traffic surveillance of a given highway. As the sensors in this network are powered by renewable energy sources, the time-varying characteristics of energy harvesting poses great challenges on the design of efficient routing protocols for data collection in harvesting sensor networks. In this paper we first formulate a novel optimization problem as a network utility maximization problem, by incorporating multi-rate communication mechanism between sensors and the mobile sink and show the NP-hardness of the problem. We then devise a novel centralized algorithm for it, assuming that the global knowledge of the entire network is available. We also develop a distributed solution to the problem without the global knowledge assumption. We finally conduct extensive experiments by simulations to evaluate the performance of the proposed algorithms. The experimental results demonstrate that the proposed algorithms are promising and very efficient.

In this paper, we consider an energy harvesting sensor network where sensors are powered by reusable energy such as solar energy, wind energy, and so on, from their surroundings. We first formulate a novel monitoring quality maximization problem that aims to maximize the quality, rather than the quantity, of collected data, by incorporating spatial data correlation among sensors. An optimization framework consisting of dynamic rate weight assignment, fair data rate allocation, and flow routing for the problem is proposed. To fairly allocate sensors with optimal data rates and efficiently route sensing data to the sink, we then introduce a weighted, fair data rate allocation and flow routing problem, subject to energy budgets of sensors. Unlike the most existing work that formulated the similar problem as a linear programming (LP) and solved the LP, we develop fast approximation algorithms with provable approximation ratios through exploiting the combinatorial property of the problem. A distributed implementation of the proposed algorithm is also developed. The key ingredients in the design of algorithms include a dynamic rate weight assignment and a reduction technique to reduce the problem to a special maximum weighted concurrent flow problem, where all source nodes share the common destination. We finally conduct extensive experiments by simulation to evaluate the performance of the proposed algorithm. The experimental results demonstrate that the proposed algorithm is very promising, and the solution to the weighted, fair data rate allocation and flow routing problem is fractional of the optimum.

In this paper we consider data collection in an energy harvesting sensor network with a mobile sink, where a mobile sink travels along a trajectory for data collection subject to a specified tolerant delay constraint T. The problem is to find an optimal close trajectory for the mobile sink that consists of sojourn locations and the sojourn time at each location such that the network throughput is maximized, assuming that the mobile sink can only collect data from one-hop sensors, for which we first show that the problem is NP-hard. We then devise novel heuristic algorithms. We finally conduct extensive experiments to evaluate the performance of the proposed algorithms. We also investigate the impact of different parameters on the performance. The experimental results demonstrate that the proposed algorithms are efficient. To the best of our knowledge, this is the first kind of work of data collection for energy harvesting sensor networks with mobile sinks.