HDHao Du

Hao Du

*This is an algorithmically generated author record based on publicly available information.

Hao Du has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-Feature-Filtering-Based Road Curb Extraction from Unordered Point Clouds

    by Hong Lang, Yuan Peng, Zheng Zou, Shengxue Zhu, Yichuan Peng, Hao Du

    Road curb extraction is a critical component of road environment perception, being essential for calculating road geometry parameters and ensuring the safe navigation of autonomous vehicles. The existing research primarily focuses on extracting curbs from ordered point clouds, which are constrained by their structure of point cloud organization, making it difficult to apply them to unordered point cloud data and making them susceptible to interference from obstacles. To overcome these limitations, a multi-feature-filtering-based method for curb extraction from unordered point clouds is proposed. This method integrates several techniques, including the grid height difference, normal vectors, clustering, an alpha-shape algorithm based on point cloud density, and the MSAC (M-Estimate Sample Consensus) algorithm for multi-frame fitting. The multi-frame fitting approach addresses the limitations of traditional single-frame methods by fitting the curb contour every five frames, ensuring more accurate contour extraction while preserving local curb features. Based on our self-developed dataset and the Toronto dataset, these methods are integrated to create a robust filter capable of accurately identifying curbs in various complex scenarios. Optimal threshold values were determined through sensitivity analysis and applied to enhance curb extraction performance under diverse conditions. Experimental results demonstrate that the proposed method accurately and comprehensively extracts curb points in different road environments, proving its effectiveness and robustness. Specifically, the average curb segmentation precision, recall, and F1 score values across scenarios A, B (intersections), C (straight road), and scenarios D and E (curved roads and ghosting) are 0.9365, 0.782, and 0.8523, respectively.


  • Open Access

    A Heuristic Algorithm for Deploying Electric Taxi Charging Stations to Enhance Service Quality

    by Lingjie Li, Yu Zhang, Cheng Cheng, Hao Du, Shifu Liu

    With the growing maturity of electric vehicles technology and the increase in environmental awareness, electric vehicles have emerged as a feasible way to reduce carbon emissions due to transportation. In response, numerous cities have adopted electric vehicles into taxi and bus fleets to increase their use. As the use of electric taxis increases, the strategic deployment of charging stations becomes crucial to ensuring taxi operations. This study aims to optimize the deployment of electric taxi charging stations, with a focus on improving service quality. A heuristic algorithm, Improved K-means iterated with Queuing Theory (IKQT), is proposed. To validate the algorithm, over 11,000 GPS tracking trajectory data from Shanghai Qiangsheng taxis in April 2018 were analyzed. The results of the study demonstrate that the IKQT algorithm can significantly increase the utilization rate of charging stations, enabling them to serve more electric taxis during peak hours and thereby improving overall service quality. Specifically, the total waiting time for all charging services was reduced by approximately 6%, while the total number of unserved taxis across all charging stations decreased by roughly 19%. These improvements underscore the novelty and practical value of the IKQT in the deployment of electric taxi charging stations.


  • Open Access

    Effect of Rubber Aggregates on Early-Age Mechanical Properties and Deformation Behaviors of Cement Mortar

    by Gaowang Zhang, Hao Du, Junmin Li, Jie Yuan

    Rubberized cement-based materials are widely utilized because of their good ductility, impact resistance, and fatigue resistance. This research investigated the effect of the rubber aggregates content, particle size of rubber aggregates, and water–cement ratio on the early-age mechanical properties and deformation behaviors of mortar through laboratory tests, and strength reduction coefficient fitting models were established according to the testing results. The results show that the compressive strength growth rate of cement mortar is about 15% slower than that of flexural strength. The existence of rubber aggregates lowers the strength increase rate of mortar. The reduction coefficient of strength decreases with increasing rubber aggregates content and increases with the age of mortar. Increasing rubber aggregates content and decreasing particle size of rubber aggregate can lower the autogenous shrinkage in the initial stage, but the autogenous shrinkage of the later stage increases as the rubber aggregates content increases, with a turning point between 30 h and 50 h. After 3 days, the dry shrinkage of mortar accounts for about 70–80% of the total shrinkage, and it increases with higher rubber aggregate content, smaller particle size of rubber aggregates, and higher water–cement ratios.