In recent years, traffic flow prediction has played a crucial role in the management of intelligent transportation systems. However, traditional prediction methods are often limited by static spatial modeling, making it difficult to accurately capture the dynamic and complex relationships between time and space, thereby affecting prediction accuracy. This paper proposes an innovative traffic flow prediction network, SFADNet, which categorizes traffic flow into multiple traffic patterns based on temporal and spatial feature matrices. For each pattern, we construct an independent adaptive spatio-temporal fusion graph based on a cross-attention mechanism, employing residual graph convolution modules and time series modules to better capture dynamic spatio-temporal relationships under different fine-grained traffic patterns. Extensive experimental results demonstrate that SFADNet outperforms current state-of-the-art baselines across four large-scale datasets.

In the fields of traffic flow prediction and other intelligent forecasting applications, the technology of multivariate time series forecasting using graph neural networks (GNNs) is receiving growing attention. Although various GNN models based on dynamic graph structures have introduced promising approaches, they still face challenges in adequately capturing spatio-temporal information for traffic forecasting. To address this issue, this paper proposes a novel dynamic spatio-temporal attention-based GNN model using ordinary differential equations (ODEs), termed the dynamic graph ordinary differential equation (DGODE) model. Building upon the prior graph ordinary differential equation (GODE) framework, DGODE employs ODEs to mitigate the over-smoothing problem in GNNs and further incorporates dynamic graph structures to enhance the graph information extraction capabilities of GODE. These enhancements enable DGODE to optimize the integration of ODEs within GNNs, alleviate overfitting, and deepen the mining of spatio-temporal dependencies. The related experimental results demonstrate that, compared with existing baseline models, the proposed DGODE model achieves superior performance in traffic flow prediction with a reduced prediction error rate.

In an industrial environment, measuring and reconstructing metal objects using computer vision methods can be affected by surface highlight reflections, leading to inaccurate results. In this article, we propose a novel network with broad applicability for removing highlight reflections based on dynamic highlight masks, which is suitable for industrial metal highlight images where a baseline image with no highlight reflections is not available. First, we use a pretrained model to learn the highlight features of the metal surface, and then construct an adaptive dynamic highlight soft mask that allows texture features in highlight regions to be preserved while removing highlights. Second, we adjust the shape and shift of convolution operations using an adaptive highlight mask to better match the metal surface structure and avoid unnatural transitions at the edges of highlights in partially convolutional networks. We conducted quantitative evaluations on synthetic and real-world highlight datasets to demonstrate the effectiveness of our method. Compared with the state-of-the-art methods, our method shows improvements of over 0.4 in terms of correlation and Bhattacharyya distance of the histogram curves for synthesized highlight datasets. In terms of nonhighlight region invariance of real industrial highlight datasets, our method shows improvements of over 8, 0.1, and 23 points in terms of peak signal-to-noise ratio, structural similarity, and mean squared error, respectively.

Traffic flow prediction methods commonly rely on historical traffic data, such as traffic volume and speed, but may not be suitable for high-capacity expressways or during peak traffic hours. Furthermore, downstream flow can have significant impacts on traffic flow. To address these challenges, our study proposes a novel traffic flow prediction model, V-STF, which integrates visual methods to quantify macroscopic traffic flow indicators, as well as density features in temporal and flow feedback in spatio features. The contribution of our proposed model lies in its ability to improve prediction accuracy during non-periodic peak hours, by taking into account the impact of congested road conditions on traffic flow. Our experiments using the STREETS dataset demonstrate that V-STF outperforms state-of-the-art methods, especially in predicting sudden changes in traffic flow, resulting in more accurate predictions.

A semantic understanding of road traffic can help people understand road traffic flow situations and emergencies more accurately and provide a more accurate basis for anomaly detection and traffic prediction. At present, the overview of computer vision in traffic mainly focuses on the static detection of vehicles and pedestrians. There are few in-depth studies on the semantic understanding of road traffic using visual methods. This paper aims to review recent approaches to the semantic understanding of road traffic using vision sensors to bridge this gap. First, this paper classifies all kinds of traffic monitoring analysis methods from the two perspectives of macro traffic flow and micro road behavior. Next, the techniques for each class of methods are reviewed and discussed in detail. Finally, we analyze the existing traffic monitoring challenges and corresponding solutions.

The transportation detection of long-distance small objects has low accuracy. In this work, we propose DMF, which is based on disparity depths. We map different disparity regions to 2D candidate regions according to the distance to solve the small-object detection problem. This method clusters disparity maps of different depths. The projected image is extracted with image features in the mapping region. On the one hand, it uses a multicluster method to unsample 2D mapping regions. On the other hand, the feature fusion of different scales is performed on each cluster region. The experimental results on two datasets show that DMF can improve the detection accuracy of small objects.

The stereo vision could obtain the 3-D coordinate of the detected object by computing the disparity of the corresponding image points. However, on account of the time complexity and the low robustness of the image matching algorithm, it is seldom used in large-scale scene. This paper puts forward a new vehicle detection method, which simplifies the massive Fourier transformation in the image matching process. The method converts the 2-D Fourier transformation to 1-D with the dimensionality reduction of reused Fourier transformation. Meanwhile, 1-D Fourier transformation of the fast image matching model is also derived. The coarse-to-fine pyramid search strategy is used according to the gradient information of each depth map adaptively. The adjacent area of the same depth is obtained with a larger matching weight which improves the matching accuracy and robustness. The model can be used in the fitting and projection transformation of road plane after background extraction. Thus reduce the complexity of vehicle segmentation and enhance the robustness of vehicle detection. The experimental results show the method can effectively achieve the large-scale and real-time detection. It is adaptive to various illumination changes and impervious to shadow and occlusion.