Siqi Liu

Peiliang Li, Siqi Liu, Shaojie Shen

We propose a 3D object detection system with multi-sensor refinement in the context of autonomous driving. In our framework, the monocular camera serves as the fundamental sensor for 2D object proposal and initial 3D bounding box prediction. While the stereo cameras and LiDAR are treated as adaptive plug-in sensors to refine the 3D box localization performance. For each observed element in the raw measurement domain (e.g., pixels for stereo, 3D points for LiDAR), we model the local geometry as an instance vector representation, which indicates the 3D coordinate of each element respecting to the object frame. Using this unified geometric representation, the 3D object location can be unified refined by the stereo photometric alignment or point cloud alignment. We demonstrate superior 3D detection and localization performance compared to state-of-the-art monocular, stereo methods and competitive performance compared with the baseline LiDAR method on the KITTI object benchmark.

Boliang Lin

Freight train services in a railway network system are generally divided into two categories: one is the unscheduled train, whose operating frequency fluctuates with origin-destination (OD) demands; the other is the scheduled train, which is running based on regular timetable just like the passenger trains. The timetable will be released to the public if determined and it would not be influenced by OD demands. Typically, the total capacity of scheduled trains can usually satisfy the predicted demands of express cargos in average. However, the demands are changing in practice. Therefore, how to distribute the shipments between different stations to unscheduled and scheduled train services has become an important research field in railway transportation. This paper focuses on the coordinated optimization of the rail express cargos distribution in two service networks. On the premise of fully utilizing the capacity of scheduled service network first, we established a Car-to-Train (CTT) assignment model to assign rail express cargos to scheduled and unscheduled trains scientifically. The objective function is to maximize the net income of transporting the rail express cargos. The constraints include the capacity restriction on the service arcs, flow balance constraints, logical relationship constraint between two groups of decision variables and the due date constraint. The last constraint is to ensure that the total transportation time of a shipment would not be longer than its predefined due date. Finally, we discuss the linearization techniques to simplify the model proposed in this paper, which make it possible for obtaining global optimal solution by using the commercial software.