Systems, methods, and non-transitory computer readable media can perform operations comprising generating a first type of pose and a second type of pose based on visual geometry localization; determining a mode for planning a planning path for a vehicle based on at least one of the first type of pose and the second type of pose; and generating the planning path for the vehicle based on the mode.

Systems, computer program products, and methods are described herein for character recognition in a digital image processing environment. The present invention is configured to electronically retrieve one or more documents from a document repository, wherein the one or more documents are in an image format; initiate one or more image super resolution algorithms on the one or more documents; generate, based on at least the one or more image super resolution algorithms, one or more high-resolution images associated with each of the one or more documents; initiate one or more image bottleneck ensembles (IBE) algorithms on the one or more high-resolution images; extract, using the one or more IBE algorithms, one or more features associated with the one or more high resolution images; and store the one or more features extracted from the one or more high resolution images in a feature repository

Systems, computer program products, and methods are described herein for character recognition in a digital image processing environment. The present invention is configured to electronically retrieve one or more documents from a document repository, wherein the one or more documents are in an image format; initiate one or more image super resolution algorithms on the one or more documents; generate, based on at least the one or more image super resolution algorithms, one or more high-resolution images associated with each of the one or more documents; initiate one or more image bottleneck ensembles (IBE) algorithms on the one or more high-resolution images; extract, using the one or more IBE algorithms, one or more features associated with the one or more high resolution images; and store the one or more features extracted from the one or more high resolution images in a feature repository.

In various examples, a single camera is used to capture two images of a scene from different locations. A trained neural network, taking the two images as inputs, outputs a scene structure map that indicates a ratio of height and depth values for pixel locations associated with the images. This ratio may indicate the presence of an object above a surface (e.g., road surface) within the scene. Object detection then can be performed on non-zero values or regions within the scene structure map.

In various examples, a single camera is used to capture two images of a scene from different locations. A trained neural network, taking the two images as inputs, outputs a scene structure map that indicates a ratio of height and depth values for pixel locations associated with the images. This ratio may indicate the presence of an object above a surface (e.g., road surface) within the scene. Object detection then can be performed on non-zero values or regions within the scene structure map.

Systems, computer program products, and methods are described herein for character recognition in a digital image processing environment. The present invention is configured to electronically retrieve one or more documents from a document repository, wherein the one or more documents are in an image format; initiate one or more image super resolution algorithms on the one or more documents; generate, based on at least the one or more image super resolution algorithms, one or more high-resolution images associated with each of the one or more documents; initiate one or more image bottleneck ensembles (IBE) algorithms on the one or more high-resolution images; extract, using the one or more IBE algorithms, one or more features associated with the one or more high resolution images; and store the one or more features extracted from the one or more high resolution images in a feature repository.

Apparatus configured to assist a user in correctly positioning the apparatus on a drug delivery device, the apparatus comprising: attachment means for attaching the apparatus to the drug delivery device; an imaging arrangement for capturing at least one image of a portion of a delivery device; a processor for processing the captured at least one image to determine a position of the apparatus relative to the drug delivery device and to determine a manner in which the apparatus should be moved in order to correctly position the apparatus on the drug delivery device; and a display for displaying an indication of the manner in which the apparatus should be moved in order to correctly position the apparatus on the drug delivery device.

In various examples, a single camera is used to capture two images of a scene from different locations. A trained neural network, taking the two images as inputs, outputs a scene structure map that indicates a ratio of height and depth values for pixel locations associated with the images. This ratio may indicate the presence of an object above a surface (e.g., road surface) within the scene. Object detection then can be performed on non-zero values or regions within the scene structure map.

Apparatus configured to assist a user in correctly positioning the apparatus on a drug delivery device, the apparatus comprising: attachment means for attaching the apparatus to the drug delivery device; an imaging arrangement for capturing at least one image of a portion of a delivery device; a processor for processing the captured at least one image to determine a position of the apparatus relative to the drug delivery device and to determine a manner in which the apparatus should be moved in order to correctly position the apparatus on the drug delivery device; and a display for displaying an indication of the manner in which the apparatus should be moved in order to correctly position the apparatus on the drug delivery device.

A computer-implemented method for vehicle registration number recognition, the method comprising obtaining a vehicle registration number to be recognised and a plurality of authorised vehicle registration numbers, and comparing the vehicle registration number to be recognised with the plurality of authorised vehicle registration numbers, wherein comparing comprises: identifying the number of characters in common between the vehicle registration number to be recognised and each of the plurality of authorised vehicle registration numbers; determining whether the number of characters in common between the vehicle registration number to be recognised and each authorised vehicle registration number is above a pre-determined threshold but less than all characters; and in the event that the number of characters in common between the vehicle registration number to be recognised and at least one authorised vehicle registration number is above the pre-determined threshold, sending a signal that the vehicle registration number is recognised.