摘要
记者从发明者提供的背景信息中获得了以下引文：“为了安全操作，自动驾驶车辆在规划穿过环境的路径时，应考虑OBJ ECT-例如车辆、人、树木、动物、建筑物、标志和杆。为此，可以使用物体检测器实时准确地检测图像中描述的物体(例如，使用安装在自动驾驶车辆上的一个或多个传感器捕获的图像)。然而，传统的方法可能不具有期望的精度，因此可能MI SS，或者产生错误的或延迟的目标检测，这可能导致不正确的PAT HS甚至碰撞。
Abstract
Reporters obtained the following quote from the background information supplied by the inventors: “To operate safely, autonomous vehicles should account for obj ects-such as vehicles, people, trees, animals, buildings, signs, and poles-when planning paths through the environment. To do so, an object detector may be used to accurately detect objects depicted in an image(s) in real-time (e.g., images captured using one or more sensors mounted on the autonomous vehicle). However, conventional approaches may not have a desired accuracy and as a result, may mi ss, or generate false or delayed object detections that may lead to improper pat hs and even collisions.
NETL
NSTL