11 May 2018 in IEEE Transactions on Intelligent Transportation Systems
Pavement surface distress conditions are critical inputs for quantifying roadway infrastructure serviceability. Numerous computer-aided automatic examination techniques have been deployed for pavement distress condition assessments, such as digital image processing methods. However, their effectiveness and applicability are impeded due to information losses in 2-D image combination processes or extremely high costs in 3-D geo-referenced data set. In this paper, a cost-effective Kinect-based approach is proposed for 3-D pavement surface reconstruction and cracking recognition. We propose a comprehensive computational solution for the detection and recognition of pavement distress feature identification. Various cracking measurements such as alligator cracking, traverse cracking, longitudinal cracking, and so on. are identified and recognized for their severity examinations based on associated geometrical features. The experimental results indicate that this method is effective in reducing data collection costs and extracting analytical information on pavement cracking measurements. The research findings confirm that the proposed approach provides a viable, applicable solution to an automatic pavement surface condition detection and evaluation. The proposed methodology is transferable for pavement surface reconstruction and distress condition detection based on the other 3-D cloud point data. It provides an alternative inexpensive complement to existing pavement examination methodologies.
17 April 2018 in IEEE Transactions on Intelligent Transportation Systems
Recent technology advances significantly push forward the development and the deployment of the concept of smart, such as smart community and smart city. Smart transportation is one of the core components in modern urbanization processes. Under this context, the connected autonomous vehicle (CAV) system presents a promising solution towards the enhanced traffic safety and mobility through state-of-the-art wireless communications and autonomous driving techniques. Being capable of collecting and transmitting real-time vehicle-specific, location-specific, and area-wide traffic information, it is believed that CAV-enabled transportation systems will revolutionize the existing understanding of network-wide traffic operations and reestablish traffic flow theory. This paper develops a new continuum dynamics model for the future CAV-enabled traffic system, realized by encapsulating mutually-coupled vehicle interactions using virtual internal and external forces. Leveraging Newton's second law of motion, our model naturally preserves the traffic volume and automatically handles both the longitudinal and lateral traffic operations due to its 2-D nature, which sets us apart from the existing macroscopic traffic flow models. Our model can also be rolled back to handle the conventional traffic of human drivers, and the experiment shows that the model describes real-world traffic behavior well. Therefore, we consider the proposed model a complement and generalization of the existing traffic theory. We also develop a smoothed particle hydrodynamics-based numerical simulation and an interactive traffic visualization framework. By posing user-specified external constraints, our system allows users to visually understand the impact of different traffic operations interactively.
11 July 2019 in IEEE Transactions on Intelligent Transportation Systems
In this paper, a deep learning (DL) framework was proposed to predict the taxi-passenger demand while the spatial, the temporal, and external dependencies were considered simultaneously. The proposed DL framework combined a modified density-based spatial clustering algorithm with noise (DBSCAN) and a conditional generative adversarial network (CGAN) model. More specifically, the modified DBSCAN model was applied to produce a number of sub-networks considering the spatial correlation of taxi pick-up events in the road network. And the CGAN model, fed with the historical taxi passenger demand and other conditional information, was capable to predict the taxi-passenger demands. The proposed CGAN model was made up with two long short-term memory (LSTM) neural networks, which are termed as the generative network G and the discriminative network D, respectively. Adversarial training process was conducted to the two LSTMs. In the numerical experiment, different model layouts were compared. It was found that different network layouts provided reasonable accuracy. With limited training data, more LSTM layers in the generator network resulted in not only higher accuracy, but also more difficulties in training. Comparisons were also conducted between the proposed prediction model and four typical approaches, including the moving average method, the autoregressive integrated moving method, the neural network model, and the LSTM neural network model. The comparison results showed that the proposed model outperformed all the other methods. And the repeated experiment indicated that the proposed CGAN model provided significant better predictions than the LSTM model did. Future research was recommended to include more datasets for testing the model and more information for improving predictive performance.
19 July 2024 in ACM Transactions on Graphics
We introduce vertex block descent, a block coordinate descent solution for the variational form of implicit Euler through vertex-level Gauss-Seidel iterations. It operates with local vertex position updates that achieve reductions in global variational energy with maximized parallelism. This forms a physics solver that can achieve numerical convergence with unconditional stability and exceptional computation performance. It can also fit in a given computation budget by simply limiting the iteration count while maintaining its stability and superior convergence rate. We present and evaluate our method in the context of elastic body dynamics, providing details of all essential components and showing that it outperforms alternative techniques. In addition, we discuss and show examples of how our method can be used for other simulation systems, including particle-based simulations and rigid bodies.