Cooperative Object Classification for Driving Applications
Cooperative Object Classification for Driving Applications
复制标题
DOI：
10.1109/ivs.2019.8813811
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Eduardo Arnold;Omar Y. Al-Jarrah;M. Dianati;Saber Fallah;David Oxtoby;A. Mouzakitis
中科院分区：
文献类型：
--
作者：
Eduardo Arnold;Omar Y. Al-Jarrah;M. Dianati;Saber Fallah;David Oxtoby;A. Mouzakitis
3D物体分类可以通过从不同角度呈现同一物体的视图，并将所有视图聚合以构建分类器来实现。虽然这种方法以前已经被提出用于一般物体分类，但大多数现有的工作并没有考虑视觉障碍。相比之下，本文通过生成特定于应用的数据集来考虑在障碍（例如遮挡和传感器噪声）下驾驶应用的3D物体分类问题。我们提出了一种合作对象分类方法，该方法利用从不同角度（agent）看到的同一对象的多幅图像来生成更准确的分类。我们考虑了模型的泛化能力及其对损伤的恢复能力。我们引入了一个与真实遮挡相似度更高的遮挡模型，并使用了简化的传感器噪声模型。实验结果表明，基于多视图的协同模型明显优于单视图方法，并能有效缓解遮挡和传感器噪声的影响。
3D object classification can be realised by rendering views of the same object from different angles and aggregating all the views to build a classifier. Although this approach has been previously proposed for general objects classification, most existing works did not consider visual impairments. In contrast, this paper considers the problem of 3D object classification for driving applications under impairments (e.g. occlusion and sensor noise) by generating an application-specific dataset. We present a cooperative object classification method where multiple images of the same object seen from different perspectives (agents) are exploited to generate more accurate classification. We consider model generalisation capability and its resilience to impairments. We introduce an occlusion model with higher resemblance to real-world occlusion and use a simplified sensor noise model. The experimental results show that the cooperative model, relying on multiple views, significantly outperforms single-view methods and is effective in mitigating the effects of occlusion and sensor noise.