A learning method and a learning device for visual odometry based on an ORB feature of an image sequence are provided. The learning method includes: recording images, and constituting an original data set by means of the plurality of obtained images; performing ORB feature extraction on the images in the original data set to realize extraction of first key features; performing feature extraction and matching on continuous images in the original data set by means of a convolutional neural network, and extracting rich second key features from the sequential images; and inputting the first key features and the second key features extracted from the original data set into a multi-layer long-short-term memory network for training and learning, and generating and outputting estimation of a visual odometer. Rich first key features are extracted from an image sequence, and then a tracking algorithm is used for tracking the features in continuous frames.

The invention discloses an image detection method, apparatus, device and a medium. The method includes: determining one or more edge points in an input image and gradient directions thereof; generating an initial matrix with the same size as the input image, and assigning the same initial value to all matrix elements in the initial matrix; for each pixel point located in an accumulation region of each edge point, assigning a corresponding accumulation value to a matrix element in the initial matrix corresponding to the pixel point, to obtain an accumulation matrix; determining one or more circle-center positions in the input image based on the accumulation matrix; wherein, the accumulation region of each edge point includes a first direction line for accumulation along the gradient direction of the edge point and a second direction line for accumulation along the direction opposite to the gradient direction of the edge point.

Systems and techniques are described herein for performing optical flow estimation for one or more frames. For example, a process can include determining an optical flow prediction associated with a plurality of frames. The process can include determining a position of at least one feature associated with a first frame and determining, based on the position of the at least one feature in the first frame and the optical flow prediction, a position estimate of a search area for searching for the at least one feature in a second frame. The process can include determining, from within the search area, a position of the at least one feature in the second frame

System, methods, and other embodiments described herein relate to training a prediction system for improving depth perception in low-light. In one embodiment, a method includes computing, in a first training stage, losses associated with predicting a depth map for a synthetic image of a low-light scene, wherein the losses include a pose loss, a flow loss, and a supervised loss. The method also includes adjusting, according to the losses, a style model and a depth model. The method also includes training, in a second training stage, the depth model using a synthetic representation of a low-light image. The method also includes providing the depth model.

Apparatuses, systems, and techniques to calculate motion of one or more pixel in a region in an image. In at least one embodiment, motion is calculated based on motion of one or more pixels in a different region of said image that overlaps said region in which one or more algorithms are expressed in CUDA code, for example, for efficient execution on a GPU.

Apparatuses, systems, and techniques to calculate motion of one or more pixel in a region in an image. In at least one embodiment, motion is calculated based on motion of one or more pixels in a different region of said image that overlaps said region in which one or more algorithms are expressed in CUDA code, for example, for efficient execution on a GPU.

Example embodiments allow for fast, efficient motion-magnification of video streams by decomposing image frames of the video stream into local phase information at multiple spatial scales and/or orientations. The phase information for each image frame is then scaled to magnify local motion and the scaled phase information is transformed back into image frames to generate a motion-magnified video stream. Scaling of the phase information can include temporal filtering of the phase information across image frames, for example, to magnify motion at a particular frequency. In some embodiments, temporal filtering of phase information at a frequency of breathing, cardiovascular pulse, or some other process of interest allows for motion-magnification of motions within the video stream corresponding to the breathing or the other particular process of interest. The phase information can also be used to determine time-varying motion signals corresponding to motions of interest within the video stream.

Example embodiments allow for fast, efficient motion-magnification of video streams by decomposing image frames of the video stream into local phase information at multiple spatial scales and/or orientations. The phase information for each image frame is then scaled to magnify local motion and the scaled phase information is transformed back into image frames to generate a motion-magnified video stream. Scaling of the phase information can include temporal filtering of the phase information across image frames, for example, to magnify motion at a particular frequency. In some embodiments, temporal filtering of phase information at a frequency of breathing, cardiovascular pulse, or some other process of interest allows for motion-magnification of motions within the video stream corresponding to the breathing or the other particular process of interest. The phase information can also be used to determine time-varying motion signals corresponding to motions of interest within the video stream.

Each of a plurality of co-located inspection camera modules captures raw images of objects passing in front of the co-located inspection camera modules which form part of a quality assurance inspection system. The inspection camera modules have either a different image sensor or lens focal properties and generate different feeds of raw images. The co-located inspection camera modules can reside within a single standalone module and be selectively switched amongst to activate the corresponding feed of raw images. The activated feed of raw images is provided to a consuming application or process for quality assurance analysis.

Data is received that includes a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system. Thereafter, it is detected whether there is an object within each image. Based on this detection, images in which each object is detected that meet predefined object representation parameters are identified (on an object-by-object basis, etc.). The identified images are provided to a consuming application or process for quality assurance analysis. Related apparatus, systems, techniques and articles are also described.