An image object classification method and system are disclosed. The method is executed by a processor coupled to a memory. The method includes: providing an image file including at least one image object, performing a process of extracting multiple binary-classified characteristics on the image object to obtain a plurality of first results independent of each other in categories, combining the plurality of first results in a manner of dimensionality reduction based on concatenation, performing a process of characteristics abstraction on the combined first results to obtain a second result, and performing a process of characteristics integration on the plurality of first results and the second result in a manner of dot product of matrices to obtain a classification result.

An image data processing method includes a first-type identity recognition performed on a target object in an image data stream. In response to the first recognition result indicating that the target object is a similar object in the similar object database, a similar identity document (ID) associated with the similar object is acquired. In addition, K pattern recognition services configured for the similar ID are also acquired. A second-type identity recognition is performed on the target object in the image data stream through the K pattern recognition services respectively to obtain K second recognition results. In response to the K second recognition results indicating that the target object is the similar object, the similar ID to the application client to cause the application client to execute an application service based on the similar ID.

The present disclosure describes systems, robots, and methods for organizing and selecting classifiers of a library of classifiers. The classifiers of the library of classifiers can be organized in a relational model, such as a hierarchy or probability model. Instead of storing, activating, or executing the entire library of classifiers at once by a robot system, computational resource demand is reduced by executing subset of classifiers to determine context, and the determined context is used as a basis for selection of another subset of classifiers. This process can be repeated, to iteratively refine context and select more specific subsets of classifiers. A selected subset of classifiers can eventually be specific to a task to be performed by the robot system, such that the robot system can take action based on output from executing such specific classifiers.

A server and a control method thereof are provided. The server includes a communicator configured to communicate with an external apparatus; and a processor configured to: receive an image from the external apparatus via the communicator, process the received image by applying a plurality of image analysis models of which an analysis type for the image is different from each other, to the received image, and generate analysis result information about the image respectively corresponding to a plurality of analysis types according to the processing of the received image. With this, more various types of image analysis information may be provided with respect to one image. At least a portion of the analysis of the image, the processing and the generation may be carried out using at least one of a machine learning, a nerve network or a deep learning algorithm as a rule based or artificial intelligence algorithm.

Low variance detection training is described herein. In an example, annotated data can be determined based on sensor data received from a sensor associated with a vehicle. The annotated data can comprise an annotated low variance region and/or an annotated high variance region. The sensor data can be input into a model, and the model can determine an output comprising a high variance output and a low variance output. In an example, a difference between the annotated data and the output can be determined and one or more parameters associated with the model can be altered based at least in part on the difference. The model can be transmitted to a vehicle configured to be controlled by another output of the model.

A target detection method and apparatus are provided. A first image of a target scenario collected by an image sensor is analyzed to obtain one or more first 2D detection boxes of the target scenario, and a three-dimensional point cloud of the target scenario collected by a laser sensor is analyzed to obtain one or more second 2D detection boxes of the target scenario in one or more views (for example, a BEV and/or a PV). Then, comprehensive analysis is performed on a matching degree and confidence of the one or more first 2D detection boxes, and a matching degree and confidence of the one or more second 2D detection boxes, to obtain a 2D detection box of a target. Finally, a 3D model of the target is obtained based on a three-dimensional point corresponding to the 2D detection box of the target.

An image attack detection method includes: acquiring an image-to-be-detected, and performing global classification recognition based on the image-to-be-detected to obtain a global classification recognition result; performing local image extraction randomly based on the image-to-be-detected to obtain a target number of local images, the target number being obtained by calculation according to a defensive rate of a reference image corresponding to the image-to-be-detected; performing local classification recognition based on the target number of local images respectively to obtain respective local classification recognition results, and fusing the respective local classification recognition results to obtain a target classification recognition result; and detecting a similarity between the target classification recognition result and the global recognition result, and determining the image-to-be-detected as an attack image when the target classification recognition result and the global classification recognition result are dissimilar.

Embodiments of the present invention are directed to a computer-implemented method for multiscale representation of input data. A non-limiting example of the computer-implemented method includes a processor receiving an original input. The processor downsamples the original input into a downscaled input. The processor runs a first convolutional neural network (“CNN”) on the downscaled input. The processor runs a second CNN on the original input, where the second CNN has fewer layers than the first CNN. The processor merges the output of the first CNN with the output of the second CNN and provides a result following the merging of the outputs.

A method for assessing a hazard on flood sensitivity based on an ensemble learning includes collecting such data as topography, hydrometeorology, soil vegetation in a research region as feature data, and standardizing the feature data; extracting the historical inundation points and non-inundation points in the research basin according to historical water level data and remote sensing data; selecting an optimal feature subset by using Laplace scores. The method includes dividing sample points into a training set and a testing set and training the ensemble learning model; and calculating the hazard on the flood sensitivity for the whole basin by using the trained model to generate a grade distribution map of the hazard on the flood sensitivity in the basin. In the present disclosure, each of the feature data in the research region is taken as an input, the ensemble learning model improves accuracy for assessing the flood in the basin.

The present application provides an image processing method and an image processing system. The image processing method includes: obtaining a first image matrix; generating a first classified image matrix, wherein the first classified image matrix Includes a plurality of parts corresponding to a plurality of classification; obtaining a plurality of weightings, for a first image process, corresponding to the plurality of parts of the first classified image matrix, and generating a first weighting matrix accordingly; and performing the first image process upon the first image matrix according to the first weighting matrix to generate a first processed image matrix.