In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At stage-1, our accelerated cluster proposal algorithm will generate refined cluster proposals by segmenting point clouds without ground, capable of generating less redundant proposals with higher recall in an extremely short time; stage-2 we will amplify and further process these proposals by a neural network to estimate semantic label for each point and meanwhile propose a novel data augmentation method to enhance the network's recognition capability for all categories especially for non-rigid objects. Evaluated on KITTI raw dataset, PASS3D stands out against the state-of-the-art on some results, making itself competent to 3D perception in autonomous driving system. Our source code will be open-sourced. A video demonstration is available at https://www.youtube.com/ watch?v=cukEqDuP_Qw.
In a large number of bidding supplier groups, it is difficult to accurately find suppliers with unreasonable bidding behavior. In order to solve the problem of precise positioning of massive abnormal bidding behavior groups of diverse and widely distributed suppliers, the authors design a detector framework of abnormal bidding behavior based on supplier portrait. This paper mainly focuses on three abnormal bidding behaviors which harmful to the tenderers—“affiliated operation,” “subcontracting behavior,” and “colluding behavior.” Based on the bidding behavior records of suppliers, this paper establishes supplier portraits in four dimensions. In order to solve the problem that the detection algorithm under the unlabeled data is difficult to verify, this research establishes a new evaluation framework based on the bid base price formula and benefit map database of the supplier. The experiment verifies that the framework can effectively detect most suppliers with abnormal bidding behavior and can significantly change the benchmark price after eliminating abnormal suppliers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.