An image analysis apparatus includes a person information acquisition unit configured to analyze a captured image of a monitored space imaged by a camera so as to acquire information of a person imaged in the captured image, and a hidden state detection unit configured to detect occurrence of a hidden state in which a plurality of the persons are imaged to overlap in the captured image.

A method and an apparatus for controlling personal mobility device (PMD) depending on congestion includes identifying a target area according to an expected route of the PMD, acquiring a degree of congestion of the target area based on at least one of a type of objects, a movement of the objects, a distance between objects, the number of objects that is expected, and a speed limit of the target area, and controlling speed of the PMD according to the degree of congestion.

A human flow estimation system comprises: a sensor network comprising a plurality of sensors arranged in a to-be-estimated region for detecting the human flow; a model building module configured to build a human flow state model based on arrangement positions of the sensors, and build a sensor network model based on data of the sensors; and a human flow estimation module configured to estimate the human flow and provide a data weight of the estimated human flow based on the human flow state model and the sensor network model. The human flow estimation system further comprises a failure detection module configured to detect whether each sensor in the sensor network is abnormal, and the model building module is further configured to adjust the human flow state model and the sensor network model when an exception exists on the sensor.

Embodiments of the present disclosure disclose a method and apparatus for predicting a passenger flow. A specific implementation of the method includes: acquiring, based on a received prediction request for a passenger flow value of a target traffic route in a preset time period, route information of the target traffic route and a passenger flow sequence corresponding to a preset number of consecutive time periods before a current time; encoding the route information to generate encoded route information; and inputting the encoded route information and the passenger flow sequence into a pre-trained passenger flow prediction model to obtain a passenger flow prediction value of the target traffic route in the preset time period, the passenger flow prediction model being used to represent a corresponding relationship between both the encoded route information and the passenger flow sequence and the passenger flow prediction value of the target traffic route.

A first camera and a second camera are installed in a facility. An analyzing apparatus detects the same person from a first captured image generated by the first camera and a second captured image generated by the second camera. The analyzing apparatus computes a movement time which is required for the detected person to move between a captured area of the first camera and a captured area of the second camera. The analyzing apparatus determines an attributed of the person using at least one of the first captured image and the second captured image. The analyzing apparatus acquires a reference value corresponding to the determined attribute, compares the computed movement time with the acquired reference value, and outputs output information based on a result of the comparison.

A method for detecting object paths in a workplace, at a sensor block, includes responsive to detecting absence of motion, capturing an initial sequence of frames at a baseline frame rate at a camera and for each frame in the initial sequence of frames: detecting an initial constellation of objects; and transmitting a container representing the initial constellation of objects to a computer system. The method further includes, responsive to detecting motion: capturing a frame at the baseline frame rate at the camera; detecting a first constellation of objects, including a set of humans, in the frame; calculating a quantity of humans; transitioning the camera to a first frame rate; capturing a second sequence of frames at the first frame rate; detecting a second constellation of objects in the second sequence of frames; deriving a set of object paths; and transmitting the set of object paths to the computer system.

An image processing apparatus including a determination unit configured to determine, for each of a plurality of partial areas set in an input image, a priority for executing a first image analysis process, based on an image of the partial area and a corresponding image corresponding to the partial area, the corresponding image being in a past image analyzed before the input image, a selection unit configured to select at least one of partial areas from the plurality of partial areas, based on the determined priority, and a first analysis unit configured to execute the first image analysis process on each of the at least one of partial areas selected.

An annunciation method includes the steps of obtaining first position information as position information of a place where a first object is located, obtaining second position information as position information of a place where a second object is located, obtaining third position information as position information of a place where a third object is located, setting the first object and the second object as a first group when a distance between the first object and the second object calculated based on the first position information and the second position information is smaller than or equal to a first threshold value, obtaining fourth position information representing a position of the first group, and performing annunciation when a distance between the third object and the first group calculated based on the third position information and the fourth position information is smaller than a second threshold value.

Techniques are disclosed for providing a notification that a person is at a particular location. For example, a resident device may receive from a user device an image that shows a face of a first person, the image being captured by a first camera of the user device. The resident device may also receive, from another device having a second camera, a second image showing a portion of a face of a second person, the second camera having a viewable area showing a particular location. The resident device may determine a score indicating a level of similarity between a first set of characteristics associated with the face of the first person and a second set of characteristics associated with the face of a second person. The resident device may then provide to the user device a notification based on determining the score.

A counting system 100 of the present invention includes an image acquisition means 121 for acquiring a captured image obtained by capturing an imaging area that is a partial area of an object area, a detection means 122 for detecting a person existing in the imaging area from the captured image, a measurement means 123 for, on the basis of a detection result of the person, measuring a staying time that is a period of time in which the person stays in the imaging area, and a calculation means 124 for, on the basis of the detection result of the person and the staying time, calculating the number of persons existing in the object area.