Abstract: The disclosure provides a structure diagnosis system and a structure diagnosis method. The structure diagnosis system includes: a lidar scanner scanning a structure to generate a point cloud data; an input interface receiving the point cloud data; and a processor receiving the point cloud data and generating a point cloud data set. The processor executes a surface degradation and geometry abnormal coupling diagnosis module to: marking a first point cloud range of a surface degradation area according to color space value of the point cloud data set; marking a second point cloud range of a geometry abnormal area according to coordinate value of the point cloud data set; when an abnormal area includes the first point cloud range and the second point cloud range at least partially overlapping each other, determining surface degradation or geometry abnormal occurring at the abnormal area and mark the abnormal area with a predetermined mode.

Abstract: A training device and a training method for a neural network model. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.

Abstract: An electronic device and a method for training a neural network model are provided. The method includes: obtaining a first neural network model and a first pseudo-labeled data; inputting the first pseudo-labeled data into the first neural network model to obtain a second pseudo-labeled data; determining whether a second pseudo-label corresponding to the second pseudo-labeled data matching a first pseudo-label corresponding to the first pseudo-labeled data; in response to the second pseudo-label matching the first pseudo-label, adding the second pseudo-labeled data to a pseudo-labeled dataset; and training the first neural network model according to the pseudo-labeled dataset.

Abstract: The disclosure provides a structure diagnosis system and a structure diagnosis method. The structure diagnosis system includes: a lidar scanner scanning a structure to generate a point cloud data; an input interface receiving the point cloud data; and a processor receiving the point cloud data and generating a point cloud data set. The processor executes a surface degradation and geometry abnormal coupling diagnosis module to: marking a first point cloud range of a surface degradation area according to color space value of the point cloud data set; marking a second point cloud range of a geometry abnormal area according to coordinate value of the point cloud data set; when an abnormal area includes the first point cloud range and the second point cloud range at least partially overlapping each other, determining surface degradation or geometry abnormal occurring at the abnormal area and mark the abnormal area with a predetermined mode.

Abstract: A training device and a training method for a neural network model are provided. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.

Abstract: A classification method includes the following steps. Firstly, a classification module including a deep neural network (DNN) is provided. Then, to-be-classified sample is obtained. Then, the DNN automatically extracts a feature response of the to-be-classified sample. Then, whether the feature response of the to-be-classified sample falls within a boundary scope of several training samples is determined; wherein the training samples are classified into several categories. Then, if the feature response of the to-be-classified sample falls within the boundary scope, the DNN determines that to-be-classified sample belongs to which one of the categories according to the training samples.

Abstract: A classification method includes the following steps. Firstly, a classification module including a deep neural network (DNN) is provided. Then, to-be-classified sample is obtained. Then, the DNN automatically extracts a feature response of the to-be-classified sample. Then, whether the feature response of the to-be-classified sample falls within a boundary scope of several training samples is determined; wherein the training samples are classified into several categories. Then, if the feature response of the to-be-classified sample falls within the boundary scope, the DNN determines that to-be-classified sample belongs to which one of the categories according to the training samples.

Abstract: An interactive object retrieval method is provided. The present method includes receiving a time-space searching condition and a query, and selecting a plurality of searching results from an object database in accordance with the time-space searching condition, a similarity between the query and each of a plurality of data records of a first category in the object database, and a time information and a location information corresponding to each of a plurality of data records of a second category in the object database. The method further includes receiving at least one user input corresponding to at least one of the searching results, and determining a display manner of the searching results on a user interface in accordance with the at least one user input and the similarity between the query and each searching result.

Abstract: An image detecting method and a system thereof are provided. The image detecting method includes the following steps. An original image is captured. A moving-object image of the original image is created. An edge-straight-line image of the original image is created, wherein the edge-straight-line image comprises a plurality of edge-straight-lines. Whether the original image has a mechanical moving-object image is detected according to the length, the parallelism and the gap of the part of the edge-straight-lines corresponding to the moving-object image.

Abstract: An interactive object retrieval method is provided. The present method includes receiving a time-space searching condition and a query, and selecting a plurality of searching results from an object database in accordance with the time-space searching condition, a similarity between the query and each of a plurality of data records of a first category in the object database, and a time information and a location information corresponding to each of a plurality of data records of a second category in the object database. The method further includes receiving at least one user input corresponding to at least one of the searching results, and determining a display manner of the searching results on a user interface in accordance with the at least one user input and the similarity between the query and each searching result.

Abstract: An image detecting method and a system thereof are provided. The image detecting method includes the following steps. An original image is captured. A moving-object image of the original image is created. An edge-straight-line image of the original image is created, wherein the edge-straight-line image comprises a plurality of edge-straight-lines. Whether the original image has a mechanical moving-object image is detected according to the length, the parallelism and the gap of the part of the edge-straight-lines corresponding to the moving-object image.