Robot visual processing method based on attention mechanism

Abstract

The invention discloses a robot visual processing method based on an attention mechanism. The method includes the following steps that image preprocessing is conducted, wherein basic processing is conducted on an image and comprises color spatial switching, edge extracting, image conversion and image thresholding; feature extracting is conducted, wherein five kinds of feature information of the skin color, the color, the texture, the movement and the space coordinates of the preprocessed image are extracted; arbitration decision is conducted, wherein the extracted information is selectively distributed to an upper-layer function application subsystem needing the feature information according to a certain arbitration decision strategy; function application is conducted, wherein corresponding operation is conducted on the feature information which is submitted after arbitration decision to achieve function application, in other words, a direct implementation layer of visual application of a robot comprises five parts of human face detecting, color recognizing, movement detecting and tracking, gesture interaction and the attention mechanism. The robot visual processing method can provide more complete visual information of the human face, the skin color, the gesture and the like for the robot, and the movement detection capability and the tracking and planning capability are achieved.

Description

technical field

[0001] The invention relates to a robot vision system, in particular to a robot vision processing method based on an attention mechanism. Background technique

[0002] 1. Research on foreign robot vision systems

[0003] In 1993, a robot head called Kismet was developed under the leadership of Cynthia Breazeal, a roboticist at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology. Kismet has vision and hearing functions. Kismet is a baby robot inspired by the way babies and caregivers communicate. Each eye of the Kismet head is equipped with a 5.5mm CCD color camera, and a parallel network composed of eight 50MHz DSPTMS321C40 for image processing and two Motorola 68332-based microcontrollers for the motive device. Kismet has similar abilities and behaviors to babies, such as imitating the way of feedback between children and parents to express emotions and the way babies learn to communicate with others by themselves.

[0004] ...

Images