CPC G06T 7/0004 (2013.01) [G06V 10/26 (2022.01); G06V 10/40 (2022.01); G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G06V 10/806 (2022.01); G06V 20/50 (2022.01); G06T 2207/10048 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30108 (2013.01); G06V 2201/06 (2022.01)] | 20 Claims |
1. A detection method for a spinning workshop, comprising:
performing image collection on a process control device of a spinning box in the spinning workshop to obtain an image to be processed;
extracting a first image feature from the image to be processed; and
processing the first image feature based on a decoder network to obtain a fault detection result for the process control device;
wherein the decoder network comprises a plurality of decoder modules connected in series in sequence;
wherein each decoder module comprises a decoder layer and an adaptive classification head; and the adaptive classification head is configured to perform classified prediction on an output feature of the decoder layer to obtain a first fault classification result, and update the first fault classification result based on a preset classification calibration matrix to obtain a second fault classification result output by the decoder module; and
wherein the fault detection result output by the decoder network comprises a second fault classification result output by a last-layer decoder module of the decoder network, and a fault position output by the last-layer decoder module;
wherein for each decoder module after a first decoder module in the decoder network, an output feature of a previous decoder module of the decoder module is taken as an input feature of the decoder module.
|