论文标题
在嵌入式设备上进行健壮的实时行人检测
Robust Real-Time Pedestrian Detection on Embedded Devices
论文作者
论文摘要
在嵌入式设备上检测行人，例如机器人和无人机的板载，包括许多应用程序，包括道路交叉路口监控，安全性，人群监视和监视，仅举几例。但是，由于不断变化的摄像头观点和不同的对象外观以及对适合嵌入式系统的轻量级算法的需求，因此问题可能具有挑战性。本文提出了一个强大的框架，用于许多素材中的人行检测。该框架在不同的图像区域进行了精细和粗糙的检测，并利用时间和空间特性，以提高嵌入式板上的精度和实时性能。该框架使用Yolo-V3对象检测[1]作为其骨干检测器，并在NVIDIA JETSON TX2嵌入板上运行，但是也可以使用其他检测器和/或板。该框架的性能在两个已建立的数据集中及其在CVPR 2019嵌入了实时推理（ERTI）挑战中的第二名。
Detection of pedestrians on embedded devices, such as those on-board of robots and drones, has many applications including road intersection monitoring, security, crowd monitoring and surveillance, to name a few. However, the problem can be challenging due to continuously-changing camera viewpoint and varying object appearances as well as the need for lightweight algorithms suitable for embedded systems. This paper proposes a robust framework for pedestrian detection in many footages. The framework performs fine and coarse detections on different image regions and exploits temporal and spatial characteristics to attain enhanced accuracy and real time performance on embedded boards. The framework uses the Yolo-v3 object detection [1] as its backbone detector and runs on the Nvidia Jetson TX2 embedded board, however other detectors and/or boards can be used as well. The performance of the framework is demonstrated on two established datasets and its achievement of the second place in CVPR 2019 Embedded Real-Time Inference (ERTI) Challenge.
