Object recognition for power equipment via human‐level concept learning

Inspection robots are popularized in substations due to the lack of personnel for operation and maintenance. However, these inspection remain at level perceptual intelligence, rather than cognition intelligence. To enable a robot automatically detect defects power equipment, object recognition is critical step because criteria infrared diagnosis vary with types equipment. Since this task not big-sample learning problem, prior knowledge needs be added improve existing methods. Here, an model based on human-level concept proposed, which utilizes relationship between The proposed method composed three parts: Mask RCNN, Bayesian Context Network learning. As backbone network, pixel-wise segmentation gives preliminary results. Then, graph Network, corrects results sequence by maximizing conditional probability given its neighbourhood. Experiments show that accuracy increases 9.7% compared making industrial application technology possible.