According to an embodiment, an image processing device includes one or more processors. The one or more processors are configured to: acquire an image; detect a first repeated pattern from the image; detect an object included in the first repeated pattern; and output the object as a second repeated pattern.

A method for safe transfer between manned and autonomous driving modes, the method may include detecting, based on first sensed information sensed during a first period, a situation related to an environment of the autonomous vehicle; searching for one or more matching concepts of a group of reference concepts, to which the situation belongs, each reference concept of the group represents a plurality of situations and has a reference concept safety level; wherein for each reference concept of at least a sub-group of the group of reference concepts the safety level of the reference concept is based on a tested success level of at only some of the plurality of scenarios represented by the reference concept; and determining, based on an outcome of the searching, whether the vehicle is capable to safely autonomously drive through the environment.

Method for counting the number of persons being at a predefined location before entering a transportation vehicle 1, wherein the method includes the steps of receiving images taken by one or more cameras 2a, 2b mounted at the transportation vehicle 1 and performing for each image processing steps of, wherein the method further comprises track boundary boxes BB of each detected person in all received images and count the number of persons.

Provided are an image processing apparatus and an operation method of the image processing apparatus. The image processing apparatus includes a memory storing one or more instructions, and a processor configured to execute the one or more instructions stored in the memory to, by using one or more convolution neural networks, extract target features by performing a convolution operation between features of target regions having same locations in a plurality of input images and a first kernel set, extract peripheral features by performing a convolution operation of features of peripheral regions located around the target regions in the plurality of input images and a second kernel set, and determine a feature of a region corresponding to the target regions in an output image, based on the target features and the peripheral features.

A computing system for detecting objects in an image can perform operations including generating an image pyramid that includes a first level corresponding with the image at a first resolution and a second level corresponding with the image at a second resolution. The operations can include tiling the first level and the second level by dividing the first level into a first plurality of tiles and the second level into a second plurality of tiles; inputting the first plurality of tiles and the second plurality of tiles into a machine-learned object detection model; receiving, as an output of the machine-learned object detection model, object detection data that includes bounding boxes respectively defined with respect to individual ones of the first plurality of tiles and the second plurality of tiles; and generating image object detection output by mapping the object detection data onto an image space of the image.

Provided is an information processing apparatus that includes a region estimating unit estimate candidate regions of object detection from an image, a topic estimating unit that estimates a topic of the image on the basis of text information accompanying the image, a region evaluating unit that evaluates the candidate regions estimated by the region estimating unit on the basis of relationships with the topic estimated by the topic estimating unit, and an image generating unit that generates an image on the basis of evaluation results acquired by the region evaluating unit. The topic estimating unit described above estimates the topic on the basis of words to which tags are added.

A region extraction method of the present disclosure is executed by an information processing device including an arithmetic circuit to extract a desired region corresponding a moving object from three-dimensional point cloud information. The method includes: by the arithmetic circuit, receiving three-dimensional point cloud information acquired by a three-dimensional point cloud acquisition device; receiving reference information that includes at least a part of a range of the three-dimensional point cloud information and is acquired under a condition different from the acquisition of the three-dimensional point cloud information; and comparing the three-dimensional point cloud information with the reference information, detecting the moving object, and extracting a region of the moving object from the three-dimensional point cloud information.

An electronic device using a spatio-temporal self-similarity (STSS) and a method of operating the electronic device are disclosed. The electronic device may generate an STSS tensor including a spatial self-similarity map and spatial cross-similarity maps for each position of a video feature map corresponding to an input video based on a temporal offset and a spatial offset. STSS feature vectors may be generated from the STSS tensor by decreasing a dimension of the spatial offset and maintaining a dimension of the temporal offset for each position of the STSS tensor. An STSS feature map may be generated by integrating the dimension of the temporal offset for each position of the STSS feature vectors. An inference on the input video may be based on a result of adding the STSS feature map to the video feature map.

The present disclosure relates to a data construction and learning system and method based on a method of splitting and arranging multiple images. The data construction and learning system based on a method of splitting and arranging multiple images includes an input unit configured to receive images captured by a plurality of cameras disposed in a vehicle, a memory in which a program for merging the images into a single image and estimating information on a road situation and an object has been stored, and a processor configured to execute the program. The processor merges and recognizes, as one situation, road situations and objects redundantly included in the images.

The embodiment of the disclosure provides a method, apparatus, device, and storage medium for object recognition. The method includes: determining a set of first candidate object regions based on image information of a media content; determining, based on text information associated with the media content, an object region from the set of first candidate object regions; and determining an object matching the object region based on a visual feature of the object region and a text feature, the text feature being determined based on the text information. Based on the manner, disclosure may recognize an object in the media content for multimodal information of the image information of the media content and text information associated with the media content, which may effectively improve the accuracy of the object recognition.