Robot Vision Model Based on Multi-Neural Network Fusion

摘要

In the practical application of robot vision, neural networks are widely used to recognize working targets, but the reliability will decrease due to the influence of environmental factors such as illumination, background, camera orientation and so on. To solve this problem of robot vision, this paper establishes two back-propagation neural networks corresponding to the color and shape and a convolution neural network corresponding to the texture respectively to recognize the identical target in the robot's field of view, and then fuses the recognition results of three neural networks with the D-S evidence theory to get a better judgment. The experimental results show that the proposed model in this paper can improve the reliability of robot vision by the fusion of multi-neural network of color, shape and texture, and it can be used in automatic control systems such as feeding, assembly, sorting and tracking of industrial robots.