An apparatus includes an input interface and a processor. The input interface may be configured to (i) receive a sequence of video frames of a targeted view of an environment and (ii) collect data samples from a gravity sensor (G-sensor) and a gyroscopic sensor. The processor may be configured to (i) detect axes transitions using the data samples from the gyroscopic sensor, (ii) perform, in real-time, electronic image stabilization, (iii) generate a computed horizon level based on the data samples from the G-sensor and the data samples from the gyroscopic sensor, (iv) perform, in real-time, a rotational offset compensation on stabilized captured image data of the sequence of video frames to maintain alignment of a respective horizon in each frame of the sequence of video frames with the computed horizon level, and (v) generate video analytics for the sequence of video frames using the compensated and stabilized captured image data.

In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.

The present invention relates to systems and methods of express tracking for patient flow management in a distributed environment. Particularly, aspects are directed to a computer implemented method that includes initiating a check-in process that includes prompting a user to scan an identifier, processing the identifier using a cascade machine-learning architecture comprising of a multi-task convolutional neural network model and a recurrent neural network model to obtain the classification of the identifier and member identification information, determining whether the user is known user based on the member identification information, when the user is a known user, verifying user data saved in the computing system associated with the identifier, once the user data is verified, determining whether the user has a scheduled appointment; and when the user has a scheduled appointment, checking the user in for the scheduled appointment.

A control device for a mobile object including one or more imaging devices, the control device includes an image acquisition unit configured to acquire an image of an external environment of the mobile object from the one or more imaging devices, a correction unit configured to perform distortion reduction processing for reducing distortion of an image for each of one or more regions included in an image acquired from the one or more imaging devices, and a recognition unit configured to recognize the external environment of the mobile object based on an image on which the distortion reduction processing has been performed. The correction unit is configured to determine the one or more regions to be a target of the distortion reduction processing in accordance with a predetermined rule according to a moving scene of the mobile object.

A control apparatus for a vehicle including an image capturing device periodically acquires an image of an external environment of the vehicle from the image capturing device and recognizes a target object in the external environment of the vehicle based on the acquired image. The apparatus controls setting of a predetermined region for the acquired image and performs distortion reduction processing for reducing distortion of the image for the set predetermined region. In a case where a particular target object that is recognized is included in the predetermined region, the apparatus changes the predetermined region such that a region other than the particular target object included in the predetermined region increases.

Embodiments relate to a companion animal identification method including acquiring a preview image for capturing a face of a target companion animal, checking if the face of the target companion animal is aligned according to a preset criterion, capturing the face of the target companion animal when it is determined that the face of the target companion animal is aligned, and identifying the target companion animal by extracting features from a face image of the target companion animal having an aligned face view, and an identification system for performing the same.

Disclosed are a cost-effective light source device that can eliminate highlights or hotspots and reduce halo phenomenon on resistor surface and a method for reading resistor value with computer vision, in which an image of a body of a resistor is extracted through irradiation by an annular light source and reflection by a replaceable diffuse reflection hood such as paper box, paper bowl, or paper cup inside pasted with white paper and extraction by an image extraction device, followed by a series of image processing operations conducted by a control unit to calculate a disposition angle of the resistor in an image. Luminous elements on opposite axial ends of the resistor are activated, according to the disposition angle, for illumination, while luminous elements on opposite lateral sides of the resistor are shut down so that a clear color resistor image can be obtained.

A projection system and a method for correcting projection image are provided. The projection system includes a projection target, a projection apparatus and an image capturing device. The projection target includes a reference pattern, and receives an image beam to display a projection image in collaboration with the image beam. The projection apparatus projects the image beam to the projection target. The image capturing device captures a captured image having the projection image, and outputs the captured image to the projection apparatus. The projection apparatus adjusts a projection parameter of the image beam according to the projection image in the captured image. Based on the adjusted projection parameter, the corrected projection image displayed by the image beam corresponds to the reference pattern.

A learning method is performed by a computers The method includes: receiving a first image that includes an object; generating a first rectangle in the first image, the first rectangle including therein a figure, that is set in advance to have a first inclination and that represents a gripping position of an object, and having a side parallel to a first direction; inputting the first image to a model, which outputs, from the input image, a rectangle parallel to the first direction and an inclination, to cause the model to output a second rectangle and a second inclination; and updating the model such that errors of the second rectangle and the second inclination with respect to the first rectangle and the first inclination respectively decrease.

An image processing apparatus including a CPU which is operable to function as units comprising a processing unit which sets, as a first area, an area that is not a peripheral edge area in a captured image acquired by an imaging unit, sets an area including the peripheral edge area as a second area, and performs predetermined processing on one of the first area and the second area, and a specification unit which specifies whether the first area is subjected to the predetermined processing or the second area is subjected to the predetermined processing, based on orientation information of the imaging unit when the captured image is acquired.