Yue Shigang, Rind F Claire
School of Biology and Psychology, University of Newcastle upon Tyne, Newcastle upon Tyne NE1 7RU, UK.
IEEE Trans Neural Netw. 2006 May;17(3):705-16. doi: 10.1109/TNN.2006.873286.
The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the images of an approaching object such as a predator. Its computational model can cope with unpredictable environments without using specific object recognition algorithms. In this paper, an LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance the expanded edges of colliding objects via grouped excitation for collision detection with complex backgrounds. The isolated excitation caused by background detail will be filtered out by the new mechanism. Offline tests demonstrated the advantages of the presented LGMD-based neural network in complex backgrounds. Real time robotics experiments using the LGMD-based neural network as the only sensory system showed that the system worked reliably in a wide range of conditions; in particular, the robot was able to navigate in arenas with structured surrounds and complex backgrounds.
小叶巨运动检测器（LGMD）是蝗虫大脑中一个已被识别的神经元，它对诸如捕食者等接近物体的图像反应最为强烈。其计算模型无需使用特定的目标识别算法就能应对不可预测的环境。本文提出了一种基于LGMD的神经网络，该网络具有一种新的特征增强机制，通过分组激发来增强碰撞物体的扩展边缘，以便在复杂背景下进行碰撞检测。新机制将滤除由背景细节引起的孤立激发。离线测试证明了所提出的基于LGMD的神经网络在复杂背景下的优势。将基于LGMD的神经网络作为唯一传感系统进行的实时机器人实验表明，该系统在广泛的条件下都能可靠运行；特别是，机器人能够在具有结构化周边和复杂背景的场地中导航。
