Pedestrian Detection for Autonomous Cars: Occlusion Handling by Classifying Body Parts
Pedestrian Detection for Autonomous Cars: Occlusion Handling by Classifying Body Parts
复制标题
DOI：
10.1109/smc42975.2020.9282839
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
M. Islam;Abdullah Al Redwan Newaz;B. Gokaraju;A. Karimoddini
中科院分区：
文献类型：
--
作者：
M. Islam;Abdullah Al Redwan Newaz;B. Gokaraju;A. Karimoddini
在这项工作中，我们解决了使用深度神经网络检测行人身体部位的问题。特别是，我们认为在自动驾驶设置中的遮挡行人检测问题。虽然最先进的深度神经模型在检测全身行人方面表现相当出色，但对于被遮挡的行人来说，它们的表现并不令人满意。引入一种新的训练策略沿着融合机制，我们通过利用身体部位信息来处理被遮挡的行人，从而提高了SSD-Mobilenet和Faster R-CNN的性能。我们通过使用公共数据集和我们的数据集训练这两个深度神经网络来评估我们的方法。两个开发的模型的性能进行了比较，无论是在检测精度和运行时效率。
In this work, we address the problem of detecting body parts of pedestrians using deep neural networks. In particular, we consider the occluded pedestrian detection problem in autonomous driving settings. While state-of-the-art deep neural models perform reasonably well for detecting full-body pedestrians, their performances are not satisfactory for occluded pedestrians. Introducing a new training strategy along with a fusion mechanism, we enhance the performance of the SSD-Mobilenet and the Faster R-CNN by utilizing body parts information to handle occluded pedestrians. We evaluate our method by training these two deep neural networks using a public dataset as well as our dataset. The performance of the two developed models is compared both in terms of detection accuracy and runtime efficiency.