A method for extracting a feature includes: acquiring a predicted object segmentation annotation image of a (T-1)-th frame in a video and a pixel-level feature map of a T-th frame in the video, T being a positive integer greater than 2; performing respectively feature mapping on the predicted object segmentation annotation image of the (T-1)-th frame and the pixel-level feature map of the T-th frame, to obtain a mapping feature map of the (T-1)-th frame and a mapping feature map of the T-th frame; and performing a convolution on the mapping feature map of the T-th frame using a convolution kernel of the mapping feature map of the (T-1)-th frame, to obtain a score map of the T-th frame.

A method for extracting a feature includes: acquiring a predicted object segmentation annotation image of a (T-1)-th frame in a video and a pixel-level feature map of a T-th frame in the video, T being a positive integer greater than 2; performing respectively feature mapping on the predicted object segmentation annotation image of the (T-1)-th frame and the pixel-level feature map of the T-th frame, to obtain a mapping feature map of the (T-1)-th frame and a mapping feature map of the T-th frame; and performing a convolution on the mapping feature map of the T-th frame using a convolution kernel of the mapping feature map of the (T-1)-th frame, to obtain a score map of the T-th frame.

Many embodiments can comprise a system. The system can comprise one or more processors and one or more storage devices. The one or more storage devices can be configured to store computing instructions that, when executed, cause the processor to receive a plurality of images of an object, the plurality of images comprising different views of the object from around the object; iteratively align one or more images within one or more subsets of the plurality of images until the object is aligned from image to image within the one or more subsets of the plurality of images; and selectively align respective images of the one or more subsets to each other to produce a surround image. Other embodiments are disclosed herein.

Many embodiments can comprise a system. The system can comprise one or more processors and one or more storage devices. The one or more storage devices can be configured to store computing instructions that, when executed, cause the processor to receive a plurality of images of an object, the plurality of images comprising different views of the object from around the object; iteratively align one or more images within one or more subsets of the plurality of images until the object is aligned from image to image within the one or more subsets of the plurality of images; and selectively align respective images of the one or more subsets to each other to produce a surround image. Other embodiments are disclosed herein.

A product defect detection method and apparatus, an electronic device, and a storage medium are provided. A method includes: acquiring a multi-channel image of a target product; inputting the multi-channel image to a defect detection model, wherein the defect detection model includes a plurality of convolutional branches, a merging module and a convolutional headbranch; performing feature extraction on each channel in the multi-channel image by using the plurality of convolutional branches, to obtain a plurality of first characteristic information; merging the plurality of first characteristic information by using the merging module, to obtain second characteristic information; performing feature extraction on the second characteristic information by using the convolutional headbranch, to obtain third characteristic information to be output by the defect detection model; and determining defect information of the target product based on the third characteristic information.

A product defect detection method and apparatus, an electronic device, and a storage medium are provided. A method includes: acquiring a multi-channel image of a target product; inputting the multi-channel image to a defect detection model, wherein the defect detection model includes a plurality of convolutional branches, a merging module and a convolutional headbranch; performing feature extraction on each channel in the multi-channel image by using the plurality of convolutional branches, to obtain a plurality of first characteristic information; merging the plurality of first characteristic information by using the merging module, to obtain second characteristic information; performing feature extraction on the second characteristic information by using the convolutional headbranch, to obtain third characteristic information to be output by the defect detection model; and determining defect information of the target product based on the third characteristic information.

This description relates to image feature extraction. In some examples, a system can include a keypoint detector and a feature list generator. The keypoint detector can be configured to upsample a keypoint score map to produce an upsampled keypoint score map. The keypoint score map can include feature scores indicative of a likelihood of at least one feature being present at keypoints in an image. The feature list generator can be configured to identify a subset of keypoints of the keypoints in the image using the feature scores of the up sampled keypoint score map, determine descriptors for the subset of keypoints based on a feature description map, and generate a keypoint descriptor map for the image based on the determined descriptors.

This description relates to image feature extraction. In some examples, a system can include a keypoint detector and a feature list generator. The keypoint detector can be configured to upsample a keypoint score map to produce an upsampled keypoint score map. The keypoint score map can include feature scores indicative of a likelihood of at least one feature being present at keypoints in an image. The feature list generator can be configured to identify a subset of keypoints of the keypoints in the image using the feature scores of the up sampled keypoint score map, determine descriptors for the subset of keypoints based on a feature description map, and generate a keypoint descriptor map for the image based on the determined descriptors.

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.

The present disclosure is directed to techniques for determining a perceptual importance map. The perceptual importance map indicates the relative importance to the human visual system of different portions of an image. The techniques include obtaining cost values for the blocks of an image, where cost values are values used in determining motion vectors. For each block, a confidence value is derived from the cost values. The confidence value indicates the confidence with which the motion vector is believed to be correct. A perceptual importance value is determined based on the confidence value via one or more modifications to the confidence value to better reflect importance to the human visual system. The generated perceptual importance values can be used for various purposes such as allocating bits for encoding, identifying regions of interest, or selectively rendering portions of an image with greater or lesser detail based on relative perceptual importance.