Abstract: There is provided a control device including a display control unit configured to cause display of a display unit to shift between a first display mode in which a first kind of image having a predetermined relation with an electric-to-electric (EE) image acquired by an imaging unit and a second kind of image different from the first kind of image are displayed and a second display mode in which the first kind of image is not displayed and the second kind of image is displayed, and a power control unit configured to control power supply to the imaging unit in the shift between the first and second display modes.

Abstract: Described is a system for adapting a deep convolutional neural network (CNN). A deep CNN is first trained on an annotated source image domain. The deep CNN is adapted to a new target image domain without requiring new annotations by determining domain agnostic features that map from the annotated source image domain and a target image domain to a joint latent space, and using the domain agnostic features to map the joint latent space to annotations for the target image domain.

Abstract: An embodiment of the present invention provides a picture processing method in an embedded system. The picture processing method includes: performing a bit setting operation on an input/output register corresponding to a communication GPIO port of a camera module in the embedded system, so as to improve a picture collection speed of the camera module; compressing a collected picture using a preset picture compression algorithm and transmitting the compressed picture to a picture preprocessing unit in the embedded system; and filtering out, by the picture preprocessing unit, a picture background using a preset filtering algorithm to obtain picture features of a target object in the picture. With the picture processing method, requirements for an occupied memory resource are balanced while a picture collection speed and a picture data processing speed are increased.

Abstract: System, methods, devices, and instructions are described for fast boot of a processor as part of camera operation. In some embodiments, in response to a camera input, a digital signal processor (DSP) of a device is booted using a first set of instructions. Capture of image sensor data is initiated using the first set of instructions at the DSP. The DSP then receives a second set of instructions and the DSP is programmed using the second set of instructions after at least a first frame of the image sensor data is stored in a memory of the device. The first frame of the image sensor data is processed using the DSP as programmed by the second set of instructions. In some embodiments, the first set of instructions includes only instructions for setting camera sensor values, and the second set of instructions includes instructions for processing raw sensor data into formatted image files.

Abstract: Positions of an image capture device may be used to determine a position-based time-lapse video frame factor. Apparent motion between pairs of images may be used to determine a visual-based time-lapse video frame rate factor. A time-lapse video frame rate for a time-lapse video may be determined based on the position-based time-lapse video frame factor and the visual-based time-lapse video frame rate factor.

Abstract: An object recognition method of a refrigerator is disclosed. The disclosed object recognition method of a refrigerator comprises the steps of: obtaining a captured image of a storage compartment of a refrigerator; checking the change in the imaging direction of an image capturing device which has captured the image of the storage compartment, when a change in the captured image is confirmed compared to a previously stored image; and performing an object recognition operation of the captured image when the imaging direction is maintained.

Abstract: In accordance with an embodiment, a method of detecting moving objects via a moving camera includes receiving a sequence of images from the moving camera; determining optical flow data from the sequence of images; decomposing the optical flow data into global motion related motion vectors and local object related motion vectors; calculating global motion parameters from the global motion related motion vectors; calculating moto-compensated vectors from the local object related motion vectors and the calculated global motion parameters; compensating the local object related motion vectors using the calculated global motion parameters; and clustering the compensated local object related motion vectors to generate a list of detected moving objects.

Abstract: According to an aspect of an embodiment, operations may comprise obtaining a first point cloud that includes a first point. The operations also comprises obtaining a second point cloud that is a copy of the first point cloud and that includes a second point that is a copy of the first point. The operations also comprises moving the second point cloud with respect to the first point cloud according to a first vector. The operations also comprises identifying a closest point of the first point cloud that is closest to the second point of the second point cloud. The operations also comprises determining a second vector between the closest point and the second point. The operations also comprises determining a measure of usefulness of the first point based on the first vector and the second vector. The operations also comprises indicating the measure of usefulness of the first point.

Abstract: An object detection system includes a first detection device configured to control a first camera to acquire a first image of a container and detect an object in the container based on the first image, and a second detection device configured to control a second camera to acquire a second image of the container. The second image is a more detailed or accurate image than the first image for detecting the object in the container based on the second image. The first detection device is further configured to train a learning model for detecting the object in the container based on the first image using detection results from the second detection device as an indication of the correct result, and then use the trained learning model for detecting the object in the container based on the first image.

Abstract: A method for using images that represent time-series data to forecast future images depicting future values as pixelated information is provided. The method includes: receiving a first set of time-series data; converting the received first set of time-series data into a first image; and using the first image to forecast a future image depicting future values as pixelated information that corresponds to a future time interval Training sets of time-series data are used to generate historical data that provides input to a machine learning algorithm, which provides, as an output, a composite image that depicts the future values as pixelated information that reflects associated uncertainties in the value predictions.

Abstract: Disclosed is an information processing apparatus including processing circuitry that sets a behavior detection parameter corresponding to a behavior of a subject based on input information corresponding to characteristics of a subject in an image, and detects a behavior of the subject based on the set behavior detection parameter and a posture of the subject in the image. The present disclosure can be applied to, for example, a lecture capturing system.

Abstract: An example method may include applying an automated face detection program implemented on a computing device to a plurality of training digital images associated with a particular media content program to identify a sub-plurality of the training digital images, each containing a single face of a particular person associated with the particular media content program. An automated feature extraction program may be applied to the sub-plurality to generate a set of feature vectors associated with the particular person, each feature vector of the set corresponding to a different training digital image. An automated face recognition program may be applied to a runtime digital image associated with the particular media content program to recognize the particular person, together with respective geometric coordinates. The runtime digital image may be stored together with information identifying the particular person and the respective geometric coordinates of the particular person in the runtime digital image.

Abstract: An example method may include receiving, at a computing device, a digital image associated with a particular media content program, the digital image containing one or more faces of particular people associated with the particular media content program. A computer-implemented face recognition program together with a set of computational models associated with the particular media content program may be applied to the digital image to recognize one or more of the particular people in the digital image, together with respective geometric coordinates for each of the one or more detected faces. At least a subset of the set of the computational models may be associated with a respective one of the particular people. The digital image together may be stored in non-transitory computer-readable memory, together with information assigning respective identities of the recognized particular people, and associating with each respective assigned identity geometric coordinates in the digital image.

Abstract: A system and method for image processing are provided. A pre-processed image may be obtained. The pre-processed image may be decomposed into a low-frequency image and a high-frequency image. At least one grayscale transformation range may be determined based on the low-frequency image. At least one grayscale transformation parameter may be determined based on the at least one grayscale transformation range. The low-frequency image may be transformed based on the at least one grayscale transformation parameter to obtain a transformed low-frequency image. A transformed image may be generated by reconstructing the transformed low-frequency image and the high-frequency image.

Abstract: Systems and methods for operating an autonomous vehicle. The methods comprising: obtaining, by a computing device, loose-fit cuboids overlaid on 3D graphs so as to each encompass LiDAR data points associated with a given object; defining, by the computing device, an amodal cuboid based on the loose-fit cuboids; using, by the computing device, the amodal cuboid to train a machine learning algorithm to detect objects of a given class using sensor data generated by sensors of the autonomous vehicle or another vehicle; and causing, by the computing device, operations of the autonomous vehicle to be controlled using the machine learning algorithm.

Abstract: The present application describes a system and method for extending a range of an image detection and classification system that is associated with various image capture devices. The range of the image detection and classification system is extended using one or more of an optical zoom on an area of interest, a digital zoom on the area of interest and a crop operation on the area of interest.

Abstract: Certain embodiments involve flow-based color transfers from a source graphic to target graphic. For instance, a palette flow is computed that maps colors of a target color palette to colors of the source color palette (e.g., by minimizing an earth-mover distance with respect to the source and target color palettes). In some embodiments, such color palettes are extracted from vector graphics using path and shape data. To modify the target graphic, the target color from the target graphic is mapped, via the palette flow, to a modified target color using color information of the source color palette. A modification to the target graphic is performed (e.g., responsive to a preview function or recoloring command) by recoloring an object in the target color with the modified target color.

Abstract: An image processing apparatus comprising, a tracking unit configured to detect an object and track the object in images to be processed, the images being sequential with respect to time, a determining unit configured to determine a stay time for which the object stays, on the basis of a result of the tracking, and an associating unit configured to specify, on the basis of the result of the tracking, one predetermined location from one or more predetermined locations included in the images to be processed, and associate the specified one predetermined location with the stay time.

Abstract: Systems, apparatus, methods, and articles of manufacture for Artificial Intelligence (AI) driving analysis and incentives, by utilizing on-board image object analysis to classify driving events and provide driving-based awards.

Abstract: An indoor camera includes: an image capturing unit; a storage unit configured to store at least one detection area in association with stagnation times, the detection area that is a target area for detecting stagnation of a pet, and the stagnation times indicating the number of times when the pet enters the detection area and stagnates in the detection area; and a processor configured to detect a position of the pet and count the stagnation times of the pet in the detection area based on captured images. If determining, based on the captured images, that the pet stagnates in the detection area for a predetermined time period or longer, the processor increments and counts the stagnation times of the pet in the detection area and generates an action log including identification information of the detection area and information on the stagnation times.