An object of the invention is to configure an object search device capable of expressing information on shapes and irregularities as features only by images, in a search for an object that is characteristic in shape or irregularity, and performing an accurate search.

The object search device includes: an image feature extraction unit that is configured with a first neural network, and is configured to input an image to extract an image feature; a three-dimensional data feature extraction unit that is configured with a second neural network, and is configured to input three-dimensional data to extract a three-dimensional data feature; a learning unit that is configured to extract an image feature and a three-dimensional data feature from an image and three-dimensional data of an object obtained from a same individual, respectively, and update an image feature extraction parameter so as to reduce a difference between the image feature and the three-dimensional data feature; and a search unit that is configured to extract image features of a query image and a gallery image of the object by the image feature extraction unit using the updated image feature extraction parameter, and calculate a similarity between the image features of both images to search for the object.

Disclosed are systems and methods for mapping multiple views to an identity. The systems and methods may include receiving a plurality of images that depict an object. Attributes associated with the object may be extracted from the plurality of images. An identity of the object may be determined based on processing the attributes.

A system includes a sensor and a client. The client receives a set of frames of top-view depth images generated by the sensor. The client identifies a frame of the received frames in which a first contour associated with a first object is merged with a second contour associated with a second object. The client determines, at a first depth in the identified frame, a merged-contour region which is associated with the merged contours. The client detects a third contour at a second depth that is less than the first depth and determines a first region associated with the third contour. The client detects a fourth contour at the second depth and determines a second region associated with the fourth contour. If criteria are satisfied, the client associates the first region with a position of the first object and associates the second region with a position of the second object.

Disclosed herein is an apparatus for the real-time monitoring of construction objects. The apparatus for the real-time monitoring of construction objects includes: a communication unit configured to receive image data acquired by photographing a construction site, and to transmit safety information to an external device; and a monitoring unit provided with a prediction model pre-trained using binary image sequences of construction objects at the construction site as training data, and configured to detect a plurality of construction objects from image frames included in image data received via the communication unit and convert the detected construction objects into binary images, to generate future frames by inputting the resulting binary images to the prediction model, and to derive proximity between the construction objects by comparing the generated future frames with the resulting binary images and generate the safety information.

In one embodiment, a video analysis service receives video data captured by one or more cameras at a particular location. The service applies a neural network-based model to portions of the video data, to identify objects within the video data. The service maps outputs of the neural network-based model to symbols using a conceptual space. The outputs of the model comprise the identified objects. The service applies a symbolic reasoning engine to the symbols, to generate an alert. The service sends the alert to a user interface in conjunction with the video data.

An infrared image sequence-based sleep quality evaluation system and method. The method comprises: obtaining a plurality of respiratory infrared image sequences to be evaluated, one respiratory infrared image sequence comprising a plurality of respiratory infrared image frames to be evaluated; performing sleep quality evaluation on each respiratory infrared image sequence in the plurality of respiratory infrared image sequences by means of a classifier to obtain a sleep quality evaluation result corresponding to each respiratory infrared image sequence; and counting the number of different sleep quality evaluation results according to the sleep quality evaluation results respectively corresponding to the plurality of respiratory infrared image sequences, and determining the sleep quality evaluation result with the largest number as a sleep quality evaluation result of a user. Contactless sleep monitoring can be carried out on a user, monitoring costs are reduced at the same time, and evaluation accuracy of sleep quality is improved.

A depth image of an object can be input to a deep neural network to determine a first four degree-of-freedom pose of the object. The first four degree-of-freedom pose and a three-dimensional model of the object can be input to a silhouette rendering program to determine a first two-dimensional silhouette of the object. A second two-dimensional silhouette of the object can be determined based on thresholding the depth image. A loss function can be determined based on comparing the first two-dimensional silhouette of the object to the second two-dimensional silhouette of the object. Deep neural network parameters can be optimized based on the loss function and the deep neural network can be output.

Provided are a disaster information processing apparatus, an operation method of a disaster information processing apparatus, an operation program of a disaster information processing apparatus, and a disaster information processing system capable of controlling an operation of a surveillance camera suitable for an environmental condition of a disaster-stricken area. An effective field of view range derivation unit derives and acquires an effective field of view range in a bird's-eye view image of an area captured by a surveillance camera, and a damage situation of the area being able to be grasped in the effective field of view range, and the effective field of view range changing depending on an environmental condition of the area. A control signal generation unit generates a control signal of the surveillance camera corresponding to the effective field of view range. An operation of the surveillance camera is controlled by the control signal.

A method and apparatus for monitoring a human or animal subject in a room using video imaging of the subject and analysis of the video image to detect and quantify movement of the subject and to derive an estimate of vital signs such as heart rate or breathing rate. The method includes techniques for de-correlating global intensity variations such as sunlight changes, compensating for noise, eliminating areas not of interest in the image, and quickly and automatically finding regions of interest for detecting subject movement and estimating vital signs. A logic machine is used for interpreting detected movement of the subject, and an artificial neural network is used to calculate a confidence measure for the vital signs estimates from signal quality indices. The confidence measure may be used with a normal density filter to output estimates of the vital signs.

A computer implemented method to detect compliance with safety requirements within a monitored environment. The method includes receiving at least one image of a monitored environment, analyzing the at least one image to detect one or more objects, analyzing the detected object and data corresponding to the monitored environment to determine that at least one characteristic of the object does not comply with a safety requirement, and generating a compliance record regarding the safety requirement.