Biblio

Intelligenta transportation is an important part of urban development. The core of realizing intelligent transportation is to master the urban road condition. This system processes the video of dashcam based on the Panoptic Segmentation network and adds a tracking module based on the comparison of front and rear frames and KM algorithm. The system mainly includes the following parts: embedded device, Panoptic Feature Pyramid Network, cloud server and Web site.

Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the dynamics of subject-object interactions. We propose a novel model which can explicitly reason about the geometric relations between constituent objects and an agent performing an action. To train our model, we collect dense object box annotations on the Something-Something dataset. We propose a novel compositional action recognition task where the training combinations of verbs and nouns do not overlap with the test set. The novel aspects of our model are applicable to activities with prominent object interaction dynamics and to objects which can be tracked using state-of-the-art approaches; for activities without clearly defined spatial object-agent interactions, we rely on baseline scene-level spatio-temporal representations. We show the effectiveness of our approach not only on the proposed compositional action recognition task but also in a few-shot compositional setting which requires the model to generalize across both object appearance and action category.