Abstract: A method, apparatus, and system with tracking are disclosed. The apparatus is configured to acquire a feature map of a template image, a color histogram of a foreground of the template image that has an object, and a color histogram of a background of the template image other than the foreground, acquire a feature score map, and a bounding box map corresponding to the feature score map, based on the feature map of the template image and a feature map of a search image, acquire a color score map based on the color histogram of the foreground, the color histogram of the background, and a color value of the search image, acquire a final score map, and a bounding box map corresponding to the final score map, based on the feature score map, the color score map, and the bounding box map, and output the corresponding bounding box.

Abstract: An image sensor includes: a motion detection circuit configured to detect a motion in image frames; and a micro control unit (MCU) configured to adjust at least a portion of a target frame among the image frames based on whether the motion is detected, and detect whether a target object is present based on the adjusted portion of the target frame.

Abstract: An apparatus and method for processing an image are provided. The apparatus includes: one or more processors; memory storing instructions configured to, when executed by the one or more processors, cause the one or more processors to: detect objects in the image; determine region of interest (ROI) scores of the respective detected objects; determine whether to display icons for the respective objects based on the respective ROI scores; display an image processing user interface including at least a portion of the image and the icons; and receive an input selecting an icon from among the icons displayed with the user interface, and in response perform image processing based on the selected icon.

Abstract: A processor-implemented method includes: obtaining a video feature of a video comprising a plurality of video frames; determining a target object representation of the video based on the video feature using a neural network; and generating a panorama segmentation result of the video based on the target object representation.

Abstract: An object classification method and apparatus are disclosed. The object classification method includes receiving an input image, storing first feature data extracted by a first feature extraction layer of a neural network configured to extract features of the input image, receiving second feature data from a second feature extraction layer which is an upper layer of the first feature extraction layer, generating merged feature data by merging the first feature data and the second feature data, and classifying an object in the input image based on the merged feature data.

Abstract: The present invention relates to an image collection sensor device, an unmanned counting edge computing system and method using the same, and more particularly, to an image collection sensor device capable of providing a high-precision unmanned counting service using a low-power wireless image collection sensor device operated by a battery by analyzing unmanned counting result data that counts the number of persons included in image data, determining image sensor parameters of the image data, and adjusting a collection cycle and collection image quality of image sensor data according to environmental changes in a sensing area.

Abstract: An apparatus includes one or more processors configured to generate a plurality of feature maps having respective different resolutions based on an input image; and update, for each of the plurality of transformer layers, respective position estimation information comprising first position information of a respective bounding box corresponding to one object query and second position information of respective key points corresponding to the one object query, wherein each of the plurality of transformer layers includes a self-attention model configured to generate respective intermediate data by performing self-attention on respective content information on a feature of the input image; and a cross-attention model configured to generate respective output data by performing cross-attention on respective one or more feature maps among the plurality of feature maps and the respective generated intermediate data.

Abstract: A method of generating a hyperlapse video includes: comparing a first reference point of a first image and a corresponding second reference point of a second image; based on the comparing, displaying a first user interface for matching the first reference point and second reference point; and determining whether to perform automatic shooting for the hyperlapse video based on whether the first reference point and the second reference point match.

Abstract: An object tracking apparatus is provided. The object tracking apparatus includes a processor configured to detect, from a first image frame, an amodal region including a first visible region in which a target object is visible and an occlusion region in which the target object is occluded, determine, based on the detected amodal region of the first image frame, that at least a partial region of a second image frame is a search region of the second image frame, the second image frame being temporally adjacent to the first image frame, and track the target object in the second image frame based on the determined search region.

Abstract: A processor-implemented liveness test method includes detecting a face region in a query image, the query image including a test object for a liveness test, determining a liveness test condition to be applied to the test object among at least one liveness test condition for at least one registered user registered in a registration database, determining at least one test region in the query image based on the detected face region and the determined liveness test condition, obtaining feature data of the test object from image data of the determined at least one test region using a neural network-based feature extractor, and determining a result of the liveness test based on the obtained feature data and registered feature data registered in the registration database and corresponding to the determined liveness test condition.

Abstract: Disclosed is a seamless complex positioning method using heterogeneous positioning techniques, the method including: performing, by a positioning control apparatus, satellite signal-based positioning in an area where a satellite signal is received; determining, by the apparatus, whether a first position of a mobile terminal determined using satellite signal-based positioning is close to a shaded area; determining, by the apparatus, a non-satellite signal-based positioning scheme supported in the shaded area when the first position is close to the shaded area; determining, by the apparatus, a second position of the mobile terminal while performing satellite signal-based positioning and positioning according to the non-satellite signal-based positioning scheme simultaneously when the first position is close to the shaded area; and stopping, by the apparatus, satellite signal-based positioning and performing only positioning according to the non-satellite signal-based positioning scheme when the second position

Abstract: Disclosed is a method and device for processing data, and the method includes generating a target augmentation task sequence by processing the target data with a trained first model that performs inference on the target data to generate the target data augmentation task sequence, generate augmented target data by performing data augmentation on the target data according to the target augmentation task sequence, and obtaining a prediction result corresponding to the target data by inputting the augmented target data to a trained second model and performing a corresponding processing on the augmented target data by the trained second model.

Abstract: A processor-implemented method includes generating a preprocessed infrared (IR) image by performing first preprocessing based on an IR image including an object; generating a preprocessed depth image by performing second preprocessing based on a depth image including the object; and determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image

Abstract: An apparatus and a method of controlling a camera is provided. The apparatus includes a receiver configured to receive an image from an image sensor and a processor configured to detect a target object from the image, perform a first zoom adjustment operation of the camera including the image sensor based on whether the target object is changed and perform a second zoom adjustment of the camera based on a center point of the target object and a center point of the camera.

Abstract: Disclosed is a target tracking method and apparatus. The target tracking apparatus includes a processor configured to obtain a first depth feature from a target region image and obtain a second depth feature from a search region image, obtain a global response diagram between the first depth feature and the second depth feature, acquire temporary bounding box information based on the global response diagram, updated the second depth feature based on the temporary bounding box information, obtain local feature blocks based on the first depth feature, obtain a local response diagram based on the local feature blocks and the updated second depth feature, and determine output bounding box information based on the local response diagram.

Abstract: A method and apparatus with object tracking is provided. The method includes generating a mixed filter by fusing a short-term filter with a long-term filter; and performing object tracking on a current frame image based on the mixed filter. The short-term filter is dependent on a prediction of the current frame image in a video sequence, and the long-term filter is a previously generated long-term filter or is generated by optimizing the previously generated long-term filter based on an object template feature pool.

Abstract: A processor-implemented method includes: generating a preprocessed infrared (IR) image by performing first preprocessing based on an IR image including an object; generating a preprocessed depth image by performing second preprocessing based on a depth image including the object; and determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image.

Abstract: Disclosed is a method and apparatus for testing a liveness, where the liveness test method includes receiving a color image and a photodiode (PD) image of an object from an image sensor comprising a pixel formed of a plurality of PDs, preprocessing the color image and the PD image, and determining a liveness of the object by inputting a result of preprocessing the color image and a result of preprocessing the PD image into a neural network.

Abstract: A processor-implemented method with object tracking includes: performing, using a first template, forward object tracking on first image frames in a first sequence group; determining a template candidate of a second template for second image frames in a second sequence group; performing backward object tracking on the first image frames using the template candidate; determining a confidence of the template candidate using a result of comparing a first tracking result determined by the forward object tracking performed on the first image frames and a second tracking result determined by the backward object tracking performed on the first image frames; determining the second template based on the confidence of the template candidate; and performing forward object tracking on the second image frames using the second template.

Abstract: A processor-implemented method of tracking a target object includes: extracting a feature from frames of an input image; selecting one a neural network model from among a plurality of neural network models that is provided in advance based on a feature value range, based on a feature value of a target object that is included in the feature of a previous frame among the frames; and generating a bounding box of the target object included in a current frame among the frames, based on the selected neural network model.