A method with distance estimation includes detecting a pedestrian region of a pedestrian comprised in a plurality of images received from a camera; determining a static point in the detected pedestrian region; and determining a distance between the pedestrian and the camera based on the static point in each of the images and a position of the camera corresponding to each of the images.

In one embodiment, a method includes a computer system accessing a curvilinear image captured using a camera lens, generating multiple rectilinear images from the curvilinear image based at least in part on one or more calibration parameters associated with the camera lens, identifying semantic information in one or more of the rectilinear images by processing each of the multiple rectilinear images using a machine-learning model configured to identify semantic information in rectilinear images, and identifying semantic information in the curvilinear image based on the identified semantic information in the one or more rectilinear images.

An image processing system includes a plurality of imaging units configured to capture optical images including a low-distortion region and a high-distortion region; a first image recognition unit configured to perform image recognition on at least a partial region out of image data obtained from the imaging unit and output a first image recognition result; a second image recognition unit configured to perform image recognition on image data in a wider region than the partial region out of the image data obtained from at least one of the imaging units and output a second image recognition result; and an integration processing unit configured to output an image recognition result integrated on the basis of the first image recognition result and the second image recognition result.

Apparatus and methods automate selection of patient interface(s). Image data captured by an image sensor may contain facial feature(s) of a user. The facial features may be captured in association with a predetermined reference feature of known dimension(s) such as with a user interface display that is generated with a sequence of icons that are activated for directing and tracking movement within the interface for desired image capture. The user's facial feature(s) and the reference feature may be detected in the captured image data. The image may be processed to measure an aspect of the detected facial feature(s) based on the reference feature. A patient interface size may be detected from standard patient interface sizes based on a comparison between the measured aspect of the facial feature(s) and a data record relating sizing information of the standard patient interface sizes and the measured aspect of the facial feature(s).

A computer-implemented method of detecting logos in a graphical rendering may comprise detecting, using a first and a second trained object detector, logos in the graphical rendering and outputting a first and a second list of detections and filtering, using at least a first and a second prior performance-based filter, the received first and second lists of detections into a first group of kept detections, a second group of discarded detections and a third group of detections. Detections in the third group of detections may be clustered in at least one cluster comprising detections that are of a same class and that are generally co-located within the electronic image. A cluster score may then be assigned to each cluster. A set of detections of logos in the graphical rendering may then be output, the set comprising the detections in the first group and a detection from each of the clusters whose assigned cluster score is greater than a respective threshold.

An identification method executed by a computer, the identification method includes receiving a face image; generating each of a plurality of first estimated values regarding an attribute of a face image by using a plurality of estimation models that generates a first estimated value regarding the attribute of the face image from the face image; generating a plurality of pieces of similarity information that indicates a similarity between feature information of the face image and a plurality of pieces of feature information respectively associated with the plurality of estimation models; and generating a second estimated value regarding the attribute of the face image, based on the plurality of first estimated values and the plurality of pieces of similarity information.

Methods and systems are described for generating dynamic conversational responses using two-tier machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The two-tier machine learning model may include a first tier that determines an intent cluster based on a feature input, and a second tier that determines a specific intent from the cluster.

Systems and methods for implementing a threat model that classifies contextual events as threats.

The present disclosure provides a detection device of a display panel. The detection device includes: an image receiver configured to receive a detection image of a display panel to be detected; a detector configured to input the detection image of the display panel to be detected into a detection model and generate a detection result by the detection model, the detection model is pre-constructed and configured to detect the display panel. The disclosure also provides a detection method of the display panel, an electronic device and a computer readable medium.

The disclosed technique detects a foreground region accurately even with a neural network. A first region detection unit detects, by a DNN, a predetermined foreground region in an inputted image. A weak region identification unit detects, by a DNN, a weak region having a possibility that misdetection or non-detection occurs during the region detection on the inputted image using a DNN that has the same detection target as that of the DNN of the first region detection unit. A second region detection unit detects, by a method other than a neural network, a foreground region that is a detection target same as that of the first region detection unit in the weak region detected by the weak region identification unit within the inputted image read from an input device. An integration unit integrates detection results by the first region detection unit and by the second region detection unit.