A projection method is provided. The method includes acquiring an image of a real scene using the camera. A target object is identified from the image of the real scene, and a target area is determined according to the target object. In response to a projection command, a projection content of a virtual scene is acquired. The projection content or a part of the projection content is projected outside the target area using a projection device.

Embodiments of this application disclose a method for determining camera pose information of a camera of a mobile terminal. The method includes: obtaining a first image, a second image, and a template image, the first image being a previous frame of image of the second image, the first image and the second image being images including a respective instance of the template image captured by the mobile terminal using the camera at a corresponding spatial position; determining a first homography between the template image and the second image; determining a second homography between the first image and the second image; and performing complementary filtering processing on the first homography and the second homography, to obtain camera pose information of the camera, wherein the camera pose information of the camera represents a spatial position of the mobile terminal when the mobile terminal captures the second image using the camera.

A method for determining a disease state prediction, relating to a potential disease or medical condition of a subject, includes accessing a set of subject images, the subject images capturing a part of a subject's body, and accessing a set of clinical factors from the subject. The clinical factors are collected by a device or a medical practitioner substantially contemporaneously with the capture of the subject images. The subject images are inputted into an image model to generate disease metrics for disease prediction for the subject. The disease metrics generated by the image model and the clinical factors are inputted into a classifier to determine the disease state prediction, and the disease state prediction is returned.

In accordance with various embodiments, a method (100) for the computer-aided recognition of a transport container (402) being empty can comprise: determining (101) one or more than one segment of image data of the transport container (402) using depth information assigned to the image data; assigning (103) the image data to one from a plurality of classes, of which a first class represents the transport container (402) being empty, and a second class represents the transport container (402) being non-empty, wherein the one or more than one segment is not taken into account in the assigning; outputting (105) a signal which represents the filtered image data being assigned to the second class.

Embodiments of this application provide example target detection methods and apparatuses. One target detection method includes obtaining an image by using a photographing apparatus. A region of interest can be marked in the image based on a parameter of the photographing apparatus and a preset traveling path. The image can be detected by using a target detection algorithm to obtain a category to which a target object in the image belongs, a first location region of the target object in the image, and a confidence of the category. The confidence of the category can be modified, based on a relative location relationship between the first location region and the region of interest, to obtain a first confidence.

Systems and methods for classifying at least a portion of an image as being textured or textureless are presented. The system receives an image generated by an image capture device, wherein the image represents one or more objects in a field of view of the image capture device. The system generates one or more bitmaps based on at least one image portion of the image. The one or more bitmaps describe whether one or more features for feature detection are present in the at least one image portion, or describe whether one or more visual features for feature detection are present in the at least one image portion, or describe whether there is variation in intensity across the at least one image portion. The system determines whether to classify the at least one image portion as textured or textureless based on the one or more bitmaps.

Techniques and apparatuses are described that implement face authentication anti-spoofing using ultrasound. In particular, a face-authentication system uses ultrasound to distinguish between a real human face and a presentation attack that uses instruments to present a version of a human face. The face-authentication system includes or communicates with an ultrasonic sensor, which can detect a presentation attack and notify the face-authentication system. In general, the ultrasonic sensor analyzes characteristics of a presented object and determines whether the object represents a human face or a presentation attack instrument. In this way, the ultrasonic sensor can prevent unauthorized actors from using the presentation attack to gain access to a user's account or information.

An apparatus comprising an interface, a light projector and a processor. The interface may be configured to receive pixel data. The light projector may be configured to generate a structured light pattern. The processor may be configured to process the pixel data arranged as video frames and generate disparity and depth maps. The processor may comprise convolutional neural network hardware that may arrange reference images into a tensor, perform logical operations on one of the video frames in a depth direction of the tensor to generate a tensor of feature maps of the video frames, use a convolution to reduce an amount of calculations performed in the depth direction of the tensor of feature maps, perform convolution filtering on the tensor of the feature maps, determine an index map location, and search lookup data based on the index map location to determine the disparity and depth maps.

An apparatus for analyzing multimodal data includes an image processor configured to generate an activation embedding vector based on an index of an activation map obtained from image data through a convolutional neutral network, a text processor configured to receive text data to generate a text embedding vector, a vector concatenator configured to concatenate the activation embedding vector and the text embedding vector to each other to generate a concatenated embedding vector, and an encoder configured to generate a multimodal representation vector in consideration of an influence between elements constituting the concatenated embedding vector based on self-attention.

Reducing false detections in template-based classification of identity documents. In an embodiment, an iterative procedure is used to generate one or more hypotheses for the location of a document in image data and a type of document in the image data based on a plurality of predefined models representing a plurality of types of documents. The one or more hypotheses are filtered by rejecting any hypothesis that is not well-conditioned according to one or more criteria. When a best hypothesis that satisfies a threshold remains after filtering the one or more hypotheses, the document in the image data is analyzed, and, when no hypothesis that satisfies the threshold remains after filtering the one or more hypotheses, the image data is rejected.