Multi-Camera Collision Detection allowing for Object Occlusions
Multi-Camera Collision Detection allowing for Object Occlusions
复制标题
多摄像头碰撞检测允许物体遮挡
DOI：
--
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
D. Henrich
中科院分区：
文献类型：
--
作者：
Thorsten Gecks;D. Henrich
翻译后摘要：提出了一种基于多摄像机的碰撞检测系统。我们描述了全局碰撞信息的计算为整个监视工作空间的基础上，从摄像机图像中提取的局部碰撞信息。如果存在已知的遮挡（例如，通过机器人），该系统能够通过融合多个相机图像来恢复物体碰撞信息。所提出的算法是一个原型的安全系统的一部分，实现人机合作。人类需要与机器人进行可靠和安全的互动，以提高机器人在工作中甚至在家里的接受程度和信任程度。我们的研究旨在提供人类和机器人之间的安全交互，以防止对人类造成严重伤害以及与环境障碍物发生（代价高昂）碰撞。为了保障机器人的操作，安全系统需要检测动态障碍物（如人类），并确定适当的措施以避免与检测到的障碍物发生碰撞（即，路径规划），同时仍然能够接触物体以执行有用的功能，例如拾取和放置操作或引导运动[2]。为了实现这一目标，获取环境的当前状态是必要的。相机是执行此任务的方便传感器，因为它们在分辨率和更新速率等各种标准方面广泛可用且具有成本效益。与其他传感器硬件的比较可以在[5]中找到。
Abstract: A multi-camera-based collision detection system is presented. We describe the computation of global collision information for the entire surveilled workspace based on local collision information extracted from camera images. If there are known occlusions (e.g., by the robot), the system is able to recover object collision information by fusing multiple camera images. The algorithm presented is part of the safety system of a prototype realizing human-robot-cooperation. Introduction Humans need reliable and safe interaction with robots in order to increase the level of acceptance and trust of the robotic partner at work or even at home. Our research aims to provide secure interaction between humans and robots to prevent severe injuries to humans and (costly) collisions with environment obstacles.To safeguard robot operation, a secure system needs to detect dynamic obstacles such as humans and determine appropriate measures to avoid collisions with the obstacles detected (i.e., path planning), all while still being capable of contacting objects to carry out useful capabilities, such as pick-and-place operations or guided motions [2]. To achieve this goal, the acquisition of the current state of the environment is necessary. Cameras are convenient sensors for this task, as they are widely available and cost-efficient with respect to various criteria such as resolution and update rate. A comparison with other sensor hardware can be found in [5].
为安全的人/机器人共存合作建模直观行为
DOI：
10.1109/robot.2006.1642304
发表时间：
2006
期刊：
Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.
影响因子：
--
作者：
Henrich D;Kuhn S.
通讯作者：
Kuhn S.