Object Segmentation by Spraying Robot Based on Multi-Layer Perceptron

The vision system provides an important way for construction robots to obtain the type and spatial location information of object. characteristics environment, object, robot structure are jointly examined in this paper propose approach object segmentation by spraying based on multi-layer perceptron. Firstly, hand-eye experimental platform is built through establishing mathematical model calibrating parameters model. Secondly, effort made carry out research image preprocessing algorithms related experiments, compare effects different binocular stereo-matching actual engineering environment. Finally, experiment conducted identify applicability effect depth algorithm results prove that application perceptron can meet requirement solution accuracy suitable complex projects real life. This not only overcomes shortcomings existing recognition methods poor difficult be used widely, but also basic data subsequent three-dimensional reconstruction, thus making a significant contribution processing robots.