Attention R-CNN for Accident Detection-猫眼课题宝

DOI：

10.1109/iv47402.2020.9304730

发表时间：

2020-10

期刊：

2020 IEEE Intelligent Vehicles Symposium (IV)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Trung-Nghia Le;Shintaro Ono;A. Sugimoto;Hiroshi Kawasaki

本文讨论了事故检测，我们不仅检测对象的类，但也认识到他们的特征属性。更具体地说，我们的目标是同时检测道路上的对象类边界框，并识别它们的状态，如安全，危险，或坠毁。为了实现这一目标，我们构建了一个新的数据集，并提出了一个基准的事故检测任务的基准方法。我们设计了一个名为Attention R-CNN的事故检测网络，它由两个流组成：一个用于通过类进行对象检测，一个用于特征属性计算。作为一个注意力机制捕捉场景中的上下文信息，我们将全局上下文从场景中利用到流中的对象检测。这种引入的注意机制使我们能够识别对象的特征属性。在新构建的数据集上进行的大量实验证明了我们所提出的网络的有效性。数据集和源代码在我们的项目页面上公开。1 https://sites.google.com/view/ltnghia/research/accident-detection

This paper addresses accident detection where we not only detect objects with classes, but also recognize their characteristic properties. More specifically, we aim at simultaneously detecting object class bounding boxes on roads and recognizing their status such as safe, dangerous, or crashed. To achieve this goal, we construct a new dataset and propose a baseline method for benchmarking the task of accident detection. We design an accident detection network, called Attention R-CNN, which consists of two streams: one is for object detection with classes and one for characteristic property computation. As an attention mechanism capturing contextual information in the scene, we integrate global contexts exploited from the scene into the stream for object detection. This introduced attention mechanism enables us to recognize object characteristic properties. Extensive experiments on the newly constructed dataset demonstrate the effectiveness of our proposed network. The dataset and source code are publicly available on our project page. 1 https://sites.google.com/view/ltnghia/research/accident-detection

Attention R-CNN for Accident Detection

文献摘要

相似文献