论文标题
以前视图中对象的多模式未来本地化和出现预测，并具有可及性
Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior
论文作者
论文摘要
在本文中，我们研究了预期未来动态的问题，尤其是在移动的车辆的情况下，尤其是其他车辆和行人的未来位置。我们应对两个基本的挑战：（1）由于以单个RGB摄像机的态度，由于以上为中心的视图而引起的部分可见性以及由于车辆的egomotion而引起的相当多的视野变化； （2）未来国家分布的多模式。与以前的许多作品相反，我们没有从地图中假设结构知识。我们宁愿从本图像的语义图中估算某些类别的对象的可及性，并使用计划的egomotion将其传播到未来。实验表明，先前的可达到性与多刺激性学习相结合，可以改善跟踪对象的未来位置的多模式预测，并首次出现新对象的出现。我们还向看不见的数据集展示了有希望的零射击传输。源代码可在$ \ href {https://github.com/lmb-freiburg/fln-epn-rpn} {\ text {this https url。}} $
In this paper, we investigate the problem of anticipating future dynamics, particularly the future location of other vehicles and pedestrians, in the view of a moving vehicle. We approach two fundamental challenges: (1) the partial visibility due to the egocentric view with a single RGB camera and considerable field-of-view change due to the egomotion of the vehicle; (2) the multimodality of the distribution of future states. In contrast to many previous works, we do not assume structural knowledge from maps. We rather estimate a reachability prior for certain classes of objects from the semantic map of the present image and propagate it into the future using the planned egomotion. Experiments show that the reachability prior combined with multi-hypotheses learning improves multimodal prediction of the future location of tracked objects and, for the first time, the emergence of new objects. We also demonstrate promising zero-shot transfer to unseen datasets. Source code is available at $\href{https://github.com/lmb-freiburg/FLN-EPN-RPN}{\text{this https URL.}}$
