Adaptive real-time detection and inspection network (ARDEN)

摘要

An adaptive real-time detection and inspection network that employs deep learning to detect and recognize objects in a stream of pixilated two-dimensional digital images. The network provides an image from an image source as an image frame in pixels to a CNN having an input layer and an output layer, and the CNN identifies and classifies objects in the image. In addition, the network provides metadata about the image source and its location, and provides the object classification data and metadata to the RNN that identifies the motion and relative speed of the classified objects in the image. The network combines object classification data from CNN and motion data from RNN, and correlates the combined data to define a bounding box around each classified object and an indicator of the relative speed and direction of movement of the classified object. And they can be displayed on a display device.