arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1510.03608cs.CV
收藏

用于行人检测的深度卷积神经网络

Deep convolutional neural networks for pedestrian detection

Politecnico di Milano(米兰理工大学)

Denis Tomè, Federico Monti, Luca Baroffio, Luca Bondi, Marco Tagliasacchi, Stefano Tubaro

摘要:

行人检测是一个热门的研究课题,因为它对许多应用至关重要,特别是在汽车,监控和机器人领域。尽管有了显著的改进,行人检测仍然是一个开放的挑战,需要越来越准确的算法。在过去的几年里,深度学习,特别是卷积神经网络,在图像分类、目标检测和分割等许多计算机视觉任务的准确性方面成为最先进的技术,通常远远超过以前的黄金标准。在本文中,我们提出了一种基于深度学习的行人检测系统,使通用卷积网络适应手头的任务。通过彻底分析和优化检测流水线的每一步,我们提出了一种优于传统方法的架构,实现了接近最先进方法的任务精度,同时需要较低的计算时间。最后,我们在NVIDIA Jetson TK1上测试了该系统,这是一个192核平台,预计将成为未来自动驾驶汽车的先驱计算大脑。

英文摘要:

Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. Despite the significant improvements, pedestrian detection is still an open challenge that calls for more and more accurate algorithms. In the last few years, deep learning and in particular convolutional neural networks emerged as the state of the art in terms of accuracy for a number of computer vision tasks such as image classification, object detection and segmentation, often outperforming the previous gold standards by a large margin. In this paper, we propose a pedestrian detection system based on deep learning, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline we propose an architecture that outperforms traditional methods, achieving a task accuracy close to that of state-of-the-art approaches, while requiring a low computational time. Finally, we tested the system on an NVIDIA Jetson TK1, a 192-core platform that is envisioned to be a forerunner computational brain of future self-driving cars.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑