Disclosed are a method, terminal and computer readable storage medium for image classification. The method includes: determining an image feature vector of an image based on a convolutional neural network, where the image comprises textual information; determining a text feature vector based on the textual information and an embedded network; determining an image-text feature vector by joining the image feature vector with the text feature vector; and determining a category of the image based on a result of a deep neural network, where the result is determined based on the image feature vector, the text feature vector and the image-text feature vector.

A farming machine includes one or more image sensors for capturing an image as the farming machine moves through the field. A control system accesses an image captured by the one or more sensors and identifies a distance value associated with each pixel of the image. The distance value corresponds to a distance between a point and an object that the pixel represents. The control system classifies pixels in the image as crop, plant, ground, etc. based on depth information in in the pixels. The control system generates a labelled point cloud using the labels and depth information, and identifies features about the crops, plants, ground, etc. in the point cloud. The control system generates treatment actions based on any of the depth information, visual information, point cloud, and feature values. The control system actuates a treatment mechanism based on the classified pixels.

In some implementations, a method is provided. The method includes obtaining an image depicting an environment where an autonomous driving vehicle (ADV) is located. The method also includes determining, using a first neural network, a plurality of line indicators based on the image. The plurality of line indicators represent one or more lanes in the environment. The method further includes determining, using a second neural network, a vanishing point within the image based on the plurality of line segments. The second neural network is communicatively coupled to the first neural network. The plurality of line indicators is determined simultaneously with the vanishing point. The method further includes calibrating one or more sensors based of the autonomous driving vehicle based on the vanishing point.

In a method for performing adaptive content classification of a video content item, frames of a video content item are analyzed at a sampling rate for a type of content, wherein the sampling rate dictates a frequency at which frames of the video content item are analyzed. Responsive to identifying content within at least one frame indicative of the type of content, the sampling rate of the frames is increased. Responsive to not identifying content within at least one frame indicative of the type of content, the sampling rate of the frames is decreased. It is determined whether the video content item includes the type of content based on the analyzing the frames.

A method includes: capturing one or more images of an unorganized collection of items inside a first machine; determining one or more item types of the unorganized collection of items from the one or more images, comprising: dividing a respective image in the one or more images into a respective plurality of sub-regions; performing feature detection on the respective plurality of sub-regions to obtain a respective plurality of regional feature vectors, wherein a regional feature vector for a sub-region indicates characteristics for a plurality of predefined local item features for the sub-region; generating an integrated feature vector by combining the respective plurality of regional feature vectors; and applying a plurality of binary classifiers to the integrated feature vector; and selecting a machine setting for the first machine based on the determined one or more clothes type in the unorganized collection of items.

In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.

A system and method for determining device attributes using a classifier hierarchy. The method includes: sequentially applying a plurality of sub-models of a hierarchy to a plurality of features extracted from device activity data, wherein the sequential application ends with applying a last sub-model of the plurality of sub-models, wherein each sub-model includes a plurality of classifiers, wherein each sub-model outputs a class when applied to at least a portion of the plurality of features, wherein each class is a classifier output representing a device attribute, wherein applying the plurality of sub-models further comprises iteratively determining a next sub-model to apply based on the class output by a most recently applied sub-model and the hierarchy; and determining a device attribute based on the class output by the last sub-model.

In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.

A method for a data analysis system includes measuring, by a sensor terminal of the data analysis system, sensor data; receiving, by a teacher data input terminal of the data analysis system, teacher data input into the teacher data input terminal; and generating, a server by the data analysis system, a classifier according to learning through the sensor data and the teacher data. The sensor terminal transmits the sensor data to the server, receives the classifier generated by the server, analyzes the sensor data according to the classifier, and transmits an analysis result of the analyzing the sensor data to the server. The teacher data input terminal transmits the teacher data to the server. The server generates the classifier, analyzes the sensor data according to the classifier, transmits the classifier to the sensor terminal, and receives the analysis result from the sensor terminal.

A road obstacle detection device which uses a pre-learned first identifier to associate a semantic label with each pixel of an image, uses a pre-learned second identifier to estimate a statistical distribution of a semantic label of a predetermined region of interest of the image from a statistical distribution of a semantic label of a peripheral region that surrounds the region of interest, and uses the statistical distribution of the semantic label associated with the region of interest and the statistical distribution of the semantic label estimated for the region of interest to estimate a likelihood that an object is a road obstacle.