Vehicle-to-vehicle interaction and collaboration can provide us with a large number of mobile traffic trajectories that can be used to analyze driving behavior. In this article, we propose a spatio-temporal cost combination based framework for taxi driving fraud detection. First, the point of interest where taxis interact and collaborate with collaborative Internet of Vehicles participants is identified, and a baseline trajectory model is built to determine the typical trajectory distribution. Second, a statistical model is used to calculate the travel distribution, travel time, and travel cost. At the same time, the taxi trajectory points are converted into evolving graphs to detect the abnormality of the local road segment. Then, we can analyze the causes of outlier trajectories combined with the perception of abnormal road environments. Finally, the trajectories of real taxis were used to evaluate outliers, which proves the effectiveness and efficiency of the method.

Predicting traffic accidents can help traffic management departments respond to sudden traffic situations promptly, improve drivers’ vigilance, and reduce losses caused by traffic accidents. However, the causality of traffic accidents is complex and difficult to analyze. Most existing traffic accident prediction methods do not consider the dynamic spatio-temporal correlation of traffic data, which leads to unsatisfactory prediction accuracy. To address this issue, we propose a multi-task learning framework (TAP) based on the Spatio-temporal Variational Graph Auto-Encoders (ST-VGAE) for traffic accident profiling. We firstly capture the dynamic spatio-temporal correlation of traffic conditions through a spatio-temporal graph convolutional encoder and embed it as a low-latitude vector. Then, we use a multi-task learning scheme to combine external factors to generate the traffic accident profiling. Furthermore, we propose a traffic accident profiling application framework based on edge computing. This method increases the speed of calculation by offloading the calculation of traffic accident profiling to edge nodes. Finally, the experimental results on real datasets demonstrate that TAP outperforms other state-of-the-art baselines.

Digital Twin (DT) provides a novel idea for Intelligent Transportation Systems (ITS), while Internet of Vehicles (IoV) provides numerous positioning data of vehicles. However, complex interactions between vehicles as well as offset and loss of measurements can lead to tracking errors of DT trajectories. In this paper, we propose a multi-vehicle trajectory tracking framework towards DT intersections (MVT2DTI). Firstly, the positioning data is unified to the same coordinate system and associated with the tracked trajectories via matching. Secondly, a spatial–temporal tracker (STT) utilizes long short-term memory network (LSTM) and graph attention network (GAT) to extract spatial–temporal features for state prediction. Then, the distance matrix is computed as a proposed tracking loss that feeds tracking errors back to the tracker. Through the iteration of association and prediction, the unlabeled coordinates are connected into the DT trajectories. Finally, four datasets are generated to validate the effectiveness and efficiency of the framework.

The low-dimensional manifold of image patches has been introduced as regularizer term, and shown effective in hyperspectral image inpainting. However, in this article, we find that using only the low-dimensional property of manifold may not always generate smooth results. In terms of this, we first present a higher order term to the low-dimensional manifold model, namely nonlocal second-order regularization (NSR), which provides better approximation to the real data distribution and manifests both the properties of low dimensionality and smoothness. Moreover, in order to balance the known and unknown sets, we further propose a weighted version of NSR, called WNSR. The generalized minimal residual algorithm is adopted to solve this unsymmetrical model, in which a semi-patch is applied for acceleration of the nearest neighbor search. Finally, we conduct intensive numerical experiments on five well-known datasets to verify the superiority of our method. The inpainting results show that our proposed (W)NSR significantly outperforms the state-of-the-art methods with respect to both visual and numerical quality.

Crowd counting is an important research topic in the field of computer vision. The multi-column convolution neural network (MCNN) has been used in this field and achieved competitive performance. However, when the crowd distribution is uneven, the accuracy of crowd counting based on the MCNN still needs to be improved. In order to adapt to uneven crowd distributions, crowd global density feature is taken into account in this paper. The global density features are extracted and added to the MCNN through the cascaded learning method. Because some detailed features during down-sampling process will be lost in the MCNN and it will affect the accuracy of the density map, an improved MCNN structure is proposed. In this paper, the max pooling is replaced by max-ave pooling to keep more detailed features and the deconvolutional layers are added to restore the lost details in down-sampling process. The experimental results in the UCF_CC_50 dataset and ShanghaiTech dataset show that the proposed method has higher accuracy and stability.