A method comprising receiving data associated with a business, the data comprising first values for first attributes; processing the data, in accordance with a common data attribute schema that indicates second attributes, to generate second values for at least some of the second attributes including a group of attributes, the second values including a group of attribute values for the group of attributes; identifying, using the common data attribute schema and from among pre-existing software codes, software code implementing an ML data processing pipeline configured to generate a group of feature values; processing the group of attribute values with the software code to obtain the group of feature values; and either providing the group of feature values as inputs to a machine learning (ML) model for generating corresponding ML model outputs, or using the group of feature values to train the ML model.

A system includes: a sequential image string input unit configured to input a sequential image string having sequentiality; a reference image selection unit configured to select one or more images from the sequential image string as reference images; a variation calculation unit configured to select an adjacent reference image adjacent to the reference image from the sequential image string and calculate a variation between the reference image and the adjacent reference image; an image information regression unit configured to calculate class confidence by regression processing with the reference image as an input; a difference image information regression unit configured to calculate class confidence by regression processing with the variation as an input; a confidence integration unit configured to integrate class confidence calculated by the image information regression unit and class confidence calculated by the difference image information regression unit; and an output unit configured to output the integrated class confidence.

A system includes: a sequential image string input unit configured to input a sequential image string having sequentiality; a reference image selection unit configured to select one or more images from the sequential image string as reference images; a variation calculation unit configured to select an adjacent reference image adjacent to the reference image from the sequential image string and calculate a variation between the reference image and the adjacent reference image; an image information regression unit configured to calculate class confidence by regression processing with the reference image as an input; a difference image information regression unit configured to calculate class confidence by regression processing with the variation as an input; a confidence integration unit configured to integrate class confidence calculated by the image information regression unit and class confidence calculated by the difference image information regression unit; and an output unit configured to output the integrated class confidence.

The present disclosure relates to a method of performing, by an image processing circuit, an inference operation comprising: capturing first and second images using first and second values respectively of an image capture parameter; generating, for a first region of the first and second images, first and second estimates respectively of an image quality metric, wherein the image quality metric is dependent on the value of the image capture parameter; calculating first and second distances between the first and second estimates respectively and first and second target levels respectively; and supplying a result of the inference operation performed on the first region of either the first or second image selected based on the first and second distances.

A computer-implemented method of estimating a 6D pose and shape of one or more objects from a 2D image, comprises the steps of: detecting, within the 2D image, one or more 2D regions of interest, each 2D region of interest containing a corresponding object among the one of more objects; cropping out a corresponding pixel value array, coordinate tensor , and feature map for each 2D region of interest; concatenating the corresponding pixel value array, coordinate tensor, and feature map for each 2D region of interest; and inferring, for each 2D region of interest, a 4D quaternion describing a rotation of the corresponding object in the 3D rotation group, a 2D centroid, which is a projection of a 3D translation of the corresponding object onto a plane of the 2D image given a camera matrix associated to the 2D, image, a distance from a viewpoint of the 2D image to the corresponding object a size and a class-specific latent shape vector of the corresponding object.

A computer-implemented method of estimating a 6D pose and shape of one or more objects from a 2D image, comprises the steps of: detecting, within the 2D image, one or more 2D regions of interest, each 2D region of interest containing a corresponding object among the one of more objects; cropping out a corresponding pixel value array, coordinate tensor , and feature map for each 2D region of interest; concatenating the corresponding pixel value array, coordinate tensor, and feature map for each 2D region of interest; and inferring, for each 2D region of interest, a 4D quaternion describing a rotation of the corresponding object in the 3D rotation group, a 2D centroid, which is a projection of a 3D translation of the corresponding object onto a plane of the 2D image given a camera matrix associated to the 2D, image, a distance from a viewpoint of the 2D image to the corresponding object a size and a class-specific latent shape vector of the corresponding object.

In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications.

According to at least one embodiment, the present disclosure provides an apparatus for single-stage three-dimensional (3D) multi-object detection by using a LiDAR sensor to detect 3D multiple objects, comprising: a data input module configured to receive raw point cloud data from the LiDAR sensor; a BEV image generating module configured to generate bird's eye view (BEV) images from the raw point cloud data; a learning module configured to perform a deep learning algorithm-based learning task to extract a fine-grained feature image from the BEV images; and a localization module configured to perform a regression operation and a localization operation to find 3D candidate boxes and classes corresponding to the 3D candidate boxes for detecting 3D objects from the fine-grained feature image.

According to at least one embodiment, the present disclosure provides an apparatus for single-stage three-dimensional (3D) multi-object detection by using a LiDAR sensor to detect 3D multiple objects, comprising: a data input module configured to receive raw point cloud data from the LiDAR sensor; a BEV image generating module configured to generate bird's eye view (BEV) images from the raw point cloud data; a learning module configured to perform a deep learning algorithm-based learning task to extract a fine-grained feature image from the BEV images; and a localization module configured to perform a regression operation and a localization operation to find 3D candidate boxes and classes corresponding to the 3D candidate boxes for detecting 3D objects from the fine-grained feature image.

The disclosure relates to an object recognizer training method and device. There may be provided a method for training an object recognizer comprising obtaining an image by capturing an object by a first sensor and a second sensor, obtaining first object recognition information by inputting an image captured by the first sensor to a first sensor-based object recognizer and obtaining second object recognition information by inputting an image captured by the second sensor to a second sensor-based object recognizer, detecting an object recognition error in the second sensor-based object recognizer, if the object recognition error is detected, obtaining a predicted value of the second object recognition information corresponding to the first object recognition information based on reference data created before, and training the second sensor-based object recognizer using the predicted value of the second object recognition information.