US 11,727,673 B1
Visual analysis method for cable element identification
Xizhao Luo, Suzhou (CN); Tingchen Wang, Suzhou (CN); and Xiaoxiao Wang, Yihuai (CN)
Assigned to SOOCHOW UNIVERSITY, Suzhou (CN)
Appl. No. 18/18,857
Filed by SOOCHOW UNIVERSITY, Suzhou (CN)
PCT Filed Aug. 31, 2022, PCT No. PCT/CN2022/116051
§ 371(c)(1), (2) Date Jan. 30, 2023,
.
Claims priority of application No. 202210649558.7 (CN), filed on Jun. 9, 2022.
Int. Cl. G06T 7/00 (2017.01); G06V 10/774 (2022.01); G06V 20/70 (2022.01); G06V 10/776 (2022.01); G06V 10/764 (2022.01)
CPC G06V 10/774 (2022.01) [G06T 7/0004 (2013.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 20/70 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30108 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A visual analysis method for cable element identification, comprising:
step S1: constructing and labeling a picture data set: collecting a predetermined number of pictures with a predetermined format, and screening and preprocessing the pictures to obtain the picture data set; according to screen attributes of the pictures, performing label remarking on the pictures in the picture data set, and classifying the pictures into different subsets subordinate to the picture data set;
step S2: preparing a training data set: selecting the pictures contained in the corresponding subsets from the picture data set, and combining the selected pictures to form the training data set; splitting the training data set to obtain a plurality of training data related files;
step S3: training a model: training a preset identification and analysis model according to the training data related files; and
step S4: identifying a cable element: inputting a target picture into the completely trained preset identification and analysis model, identifying the target picture, and determining cable element information existing in the target picture; and labeling the target picture according to the cable element information.