An image processor and a method therein to provide a target image for evaluation with an object detector. The method comprises: obtaining a source image captured by a camera and depicting an object, and applying an inverse pixel transform to each target pixel of a target image to determine one or more source pixels located at a position in the source image corresponding to a position of each target pixel in the target image. The method further comprises assigning, to each target pixel, a target pixel value determined based on one or more source pixel values of the determined one or more source pixels located at the corresponding position, thereby is a size c in the target image of the depicted object of a specific object type normalized in at least one size dimension. Thereafter, the target image is fed to an object detector for evaluation.

The present invention provides an apparatus and method for image classification and segmentation based on a feature-guided network, a device, and a medium, and belongs to the technical field of deep learning. A feature-guided classification network and feature-guided segmentation network of the present invention include basic unit blocks. A local feature is enhanced and a global feature is extracted among the basic unit blocks. This resolves a problem that features are not fully utilized in existing image classification and image segmentation network models. In this way, a trained feature-guided classification network and feature-guided segmentation network have better effects and are more robust. The present invention selects the feature-guided classification network or the feature-guided segmentation network based on a requirement of an input image and outputs a corresponding category or segmented image, to resolve a problem that the existing classification or segmentation network model has an unsatisfactory classification or segmentation effect.

System and techniques for vehicle environment modeling with a camera are described herein. A device for modeling an environment comprises: a hardware sensor interface to obtain a sequence of unrectified images representative of a road environment, the sequence of unrectified images including a first unrectified image, a previous unrectified image, and a previous-previous unrectified image; and processing circuitry to: provide the first unrectified image, the previous unrectified image, and the previous-previous unrectified image to an artificial neural network (ANN) to produce a three-dimensional structure of a scene; determine a selected homography; and apply the selected homography to the three-dimensional structure of the scene to create a model of the road environment.

A method for product compliance includes receiving, at data processing hardware, a planogram defining a representative placement of a product on a display shelf and receiving at least one image from an imaging device having a field of view arranged to capture a top surface of the display shelf. The method also includes determining whether the product is disposed on the display shelf based on the at least one image. When the product is disposed on the display shelf, the method includes determining an actual placement of the product on the display shelf and comparing the actual placement of the product to the representative placement of the product defined by the planogram. The method further includes determining a planogram compliance based on the comparison of the actual placement of the product to the representative placement of the product and communicating the planogram compliance to a network.

In one exemplary embodiment in accordance with the disclosure, an image processing system is configured to use a distance authentication template to execute a detection procedure that detects at least one non-linear distortion in a subject image. The distance authentication template can be generated by mapping a set of spatial coordinates of three features in a distortion-free image to a set of pixel coordinates of the three features in the distortion-free image. Addressing a non-linear distortion in the subject image can include performing remedial actions to remedy the non-linear distortion, or taking into consideration the non-linear distortion when using the distance authentication template to identify one or more features in the subject image.

A method and apparatus for training a model, a method and apparatus for processing a video, a device and a storage medium are provided. An implementation of the method for training a model includes: analyzing a sample video, to determine a plurality of human body image frames in the sample video; determining human body-related parameters and camera-related parameters corresponding to each human body image frame; determining, based on the human body-related parameters, the camera-related parameters and an initial model, predicted image parameters of an image plane corresponding to the each human body image frame, the camera-related parameters and image parameters; and training the initial model based on original image parameters of the human body image frames in the sample video and the predicted image parameters of image planes corresponding to the human body image frames, to obtain a target model.

A method implemented with instructions executed by a processor includes receiving a digital image of an interior space. At least one detected object is identified within the digital image. Dimensions of the detected object are determined. Image segmentation is applied to the digital image to produce a segmented image. Edges are detected in the segmented image to produce a combined output image. Geometric transformation, field of view and depth correction are applied to the combined output image to correct for image distortion to produce a geometrically transformed digital image. Dimensions are applied to the geometrically transformed digital image at least partially based on the dimensions of the detected object to produce a dimensionalized floorplan.

A method for determining an optimized weighting of an encoder and decoder network; the method comprising: for each of a plurality of test weightings, performing the following steps with the encoder and decoder operating using the test weighting: (a) encoding, using the encoder, a reference image and a distorted image into a latent space to form an encoding; (b) decoding the encoding, using the decoder, to form a distortion map indicative of a difference between the reference image and a distorted image; (c) spatially transforming the distorted image by the distortion map to obtain an aligned image; (d) comparing the aligned image to the reference image to obtain a similarity metric; and (e) determining a loss function which is at least partially defined by the similarity metric; wherein the optimized weighting is determined to be the test weighting which has an optimized loss function.

A method, an electronic device, and a storage medium are disclosed. The method includes: acquiring a color sequence verification code; controlling a screen of an electronic device to sequentially generate colors based on a sequence of the colors included in the color sequence verification code; controlling a camera of the electronic device to collect an image of a face of a target object in each of the colors to acquire an image sequence; performing a face liveness verification on the target object to acquire a liveness score value; acquiring difference images corresponding respectively to the colors of the images of the image sequence based on the image sequence; performing a color verification based on the color sequence verification code and the difference images; and determining a face liveness detection result of the target object based on

A liveness detection method is provided. In the method, image features are extracted from an image of a user. Convolution processing is performed on the image features through an estimation network to obtain a predicted mean value and a predicted variance of the image features. Standardization processing is performed on the image features based on the predicted mean value, the predicted variance, and predetermined network parameters of the standardization processing to obtain standardized features. Whether the image of the user includes a living body image is determined according to a liveness classification probability of a classification performed on the image of the user based on the standardized features. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.