A device and a method for controlling a device using a real-time image are provided. The method includes: receiving an image captured by an image capturing device connected to a network to display the image in real-time; searching for the device that is connected to the network and is controllable; designating, within the image, a setting zone corresponding to the device; receiving a user input; and controlling the device selected according to the user input. A location of the setting zone within the image may be updated according to a change in the image. The user may receive immediate visual feedback on how the devices are being controlled. The user may control a device displayed on the screen on which the real-time indoor image is displayed without having to navigate through different sub-menus for different devices.

An apparatus and the like for controlling a mobile body that are capable of adjusting a detection result by a radar device in accordance with a three-dimensional shape for each region of a three-dimensional map generated from an image captured by an image-capturing device are provided. A mobile body control unit 105 is an apparatus for controlling the vehicle (mobile body) including an image-capturing device 101 and a millimeter wave radar device 102 (radar device). A three-dimensional map generation unit 203 generates a three-dimensional map around the vehicle from an image captured by the image-capturing device 101. A radar weight map estimation unit 204 (weight estimation unit) estimates the weight of the detection result by the millimeter wave radar device 102 for each region of the three-dimensional map from the three-dimensional shape for each region of the three-dimensional map. A weight adjustment unit 205 (adjustment unit) adjusts a detection result by the millimeter wave radar device 102 on the basis of a weight.

Provided is an object recognition method which includes obtaining a first visible-light image acquired by the first camera device and a second visible-light image acquired by the second camera device; performing exposure processing on the first visible-light image according to the luminance information of the bright area image of the first visible-light image and performing exposure processing on the second visible-light image according to the luminance information of the dark area images of the first visible-light image and/or the second visible-light image, where the dark area image is an area image having a luminance value less than or equal to the preset value; and performing target object detection on the first visible-light image obtained after exposure processing and the second visible-light image obtained after exposure processing and recognizing and verifying a target object according to the detection result.

The present disclosure relates to navigation and to systems and methods for using a dual sensor readout channel to allow for frequency detection. In one implementation, at least one processing device may receive a plurality of images acquired by a camera onboard a host vehicle, wherein the plurality of images are received via a first channel and via a second channel, and wherein the first channel is associated with a first frame capture rate, and the second channel is associated with a second frame capture rate different from the first frame capture rate. The processing device may use images received via the first channel to detect flickering and non-flickering light sources in an environment of the host vehicle; and provide, based on images received via the second channel, images for showing on one or more human-viewable displays.

An apparatus for recording license plates of vehicles travelling on a road having several adjacent lanes comprises a vehicle classification sensor configured to detect a predetermined shape characteristic of a vehicle or group of vehicles. The apparatus further comprises at least one camera mounted at an elevated point beside one of the lanes and having an angle of aperture covering at least one of said lanes, each lane covered by at least one camera. The vehicle classification sensor is configured to, upon detecting the predetermined shape characteristic on a lane, trigger the camera that covers the lane the predetermined shape characteristic is detected on to record an image of a license plate on the back of the vehicle or group's leading vehicle, respectively, for which the predetermined shape characteristic is detected. The triggered camera is of a lane either adjacent to or at least one lane apart from the lane.

Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

A character recognizing apparatus includes an acquiring unit, an identifying unit, and a character recognizing unit. The acquiring unit acquires a string image that is an image of a string generated in accordance with one of multiple string generation schemes. The identifying unit identifies a range specified for a result of character recognition in each of the multiple string generation schemes. The character recognizing unit performs first character recognition on the string image, and if a result of the first character recognition has a feature of a particular string generation scheme of the multiple string generation schemes, the character recognizing unit performs second character recognition on the string image within the range specified for a result of character recognition in the particular string generation scheme.

Systems that search databases of videos or images to identify similar products in a given video or image of a product are disclosed. The content of the given video is represented by a feature vector used to measure the given video's similarity to either a video or an image. When the system is deployed to recognize particular fashion items in videos, some such videos are taken in uncontrolled settings, and as a result, may have low resolution, poor contrast, minimal focus, motion blur, or low lighting. By recognizing and removing poor quality video frames from the image recognition pipeline, associating products across video frames to form tracklets of each product, and enriching the feature representation of each item for best retrieval result by fusing information from multiple video frames depicting the item, the system addresses the aforementioned shortcomings.

An object extraction method using an object extraction system that includes a pre-processing module, an edge module, and an optimization module, and the object extraction method includes: generating an edge depth map with respect to a 2D image by pre-processing a 2D image where a target object to be data-labeled may be included, by the pre-processing module; extracting a target edge with respect to the target object from 3D data where the target object may be included, by the edge module; and optimizing the generated target edge to a final edge to match the generated edge depth map, by the optimization module.

Described herein is a system and computer implemented method for finding similars for a selected clothing image amongst a set of clothing images in an electronic catalog in an online store serving online customers. An object detection model is applied to extract the clothing section within the clothing images to create a preprocessed image. A first machine learning model is applied on the preprocessed image(s) to convert the colors and textures of said preprocessed image into a first set of vector representations. A second machine learning model is applied on the preprocessed image(s) to convert the shapes of said preprocessed image into a second set of vector representations. Operations of mapping nearest vectors, matching attributes, sorting and ranking are performed, and thereafter similar images are displayed to the online customer.