Abstract:
An information processing system is provided. The information processing system comprises at least one processor configured to receive inputs of videos captured by a plurality of imaging apparatuses, detect a first person image appearing in a first video captured by a first imaging apparatus and a second person image appearing in a second video captured by a second imaging apparatus, associate a first person with a second person based on a first feature value of the first person and a second feature value of the second person, and provide an elapsed time from a first time point when the first person disappears from the first video to a second time point when the second person appears in the second video. The first feature value and the second feature value may include information based on histogram.
Abstract:
The first parameter generation unit 811 generates a first parameter, which is a parameter of a first recognizer, using first learning data including a combination of data to be recognized, a correct label of the data, and domain information indicating a collection environment of the data. The second parameter generation unit 812 generates a second parameter, which is a parameter of a second recognizer, using second learning data including a combination of data to be recognized that is collected in a predetermined collection environment, a correct label of the data, and target domain information indicating the predetermined collection environment, based on the first parameter. The third parameter generation unit 813 integrates the first parameter and the second parameter to generate a third parameter to be used for pattern recognition of input data by learning using the first learning data.
Abstract:
The present invention is a two-wheel vehicle riding person number determination system including an imaging means configured to image a two-wheel vehicle that is installed in a predetermined position and travels on a road, and a two-wheel vehicle riding person number determining means configured to process an image of the imaging means, extract a contour shape of an upper position of the two-wheel vehicle that travels on the road, detect humped shapes corresponding to heads of persons who ride on the two-wheel vehicle from the contour shape of the upper position of the two-wheel vehicle, and determine, on the basis of the humped shapes, whether or not the number of the persons who ride on the two-wheel vehicle is at least two persons or more.
Abstract:
An object tracking apparatus, method and computer-readable medium for detecting an object from output information of sensors, tracking the object on a basis of a plurality of detection results, generating tracking information of the object represented in a common coordinate system, outputting the tracking information, and detecting the object on a basis of the tracking information.
Abstract:
Provided is an image processing system, an image processing method, and a program for preferably detecting a mobile object. The image processing system includes: an image input unit for receiving an input for some image frames having different times in a plurality of image frames constituting a picture, which is of a pixel on which the mobile object appears or a pixel on which the mobile object does not appear, for selected arbitrary one or more pixels in an image frame at the time of processing; and a mobile object detection model constructing unit for learning a parameter for detecting the mobile object based on the input.
Abstract:
[Problem] To provide a motion condition estimation device, a motion condition estimation method and a motion condition estimation program capable of accurately estimating the motion condition of monitored subjects even in a crowded environment. [Solution] A motion condition estimation device according to the present invention is provided with a quantity estimating means 81 and a motion condition estimating means 82. The quantity estimating means 81 uses a plurality of chronologically consecutive images to estimate a quantity of monitored subjects for each local region in each image. The motion condition estimating means 82 estimates the motion condition of the monitored subjects from chronological changes in the quantities estimated in each local region.
Abstract:
[Problem] To provide a motion condition estimation device, a motion condition estimation method and a motion condition estimation program capable of accurately estimating the motion condition of monitored subjects even in a crowded environment. [Solution] A motion condition estimation device according to the present invention is provided with a quantity estimating means 81 and a motion condition estimating means 82. The quantity estimating means 81 uses a plurality of chronologically consecutive images to estimate a quantity of monitored subjects for each local region in each image. The motion condition estimating means 82 estimates the motion condition of the monitored subjects from chronological changes in the quantities estimated in each local region.
Abstract:
A similarity computation unit (130) derives a first probability P indicating that a first moving body appearing in the first video is the same as a second moving body appearing in the second video on the basis of similarity of feature value of the moving bodies. A non-appearance probability computation unit (140) derives a second probability Q indicating that the first moving body is not the same as the second moving body on the basis of an elapsed time after the first moving body exits from the first video. A person determination unit (150) determines whether the first moving body is the same as the second moving body by comparing the probability P and Q.
Abstract:
Provided is a technique for enhancing operability of a mobile apparatus. An information processing apparatus (2000) includes a first processing unit (2020), a second processing unit (2040), and a control unit (2060). The first processing unit (2020) generates information indicating an event detection position in accordance with a position on a surveillance image set in a first operation. The first operation is an operation with respect to the surveillance image displayed on a display screen. The second processing unit (2040) performs a display change process with respect to the surveillance image or a window including the surveillance image. The control unit (2060) causes any one of the first processing unit (2020) and the second processing unit (2040) to process the first operation on the basis of a second operation.
Abstract:
Provided are an information processing system, an information processing method, and a program capable of favorably estimating the association between persons appearing in pictures. This information processing system includes: a correspondence relationship estimation unit for determining a scale indicating a possibility that one or more persons appearing in pictures captured respectively at a first time by a plurality of video cameras, and one or more persons appearing in pictures captured respectively at a second time, which is later than the first time, by the plurality of video cameras, are respectively associated with each other, and estimating a correspondence relationship between the person appearing at the first time and the person appearing at the second time in consideration of all scales relating to at least one person appearing at one of the first time and the second time, and all persons appearing at the other time; and a person-to-be-tracked registration unit for receiving an input of correspondence information to the effect that at least a part of one or more persons captured at the first time corresponds, or does not correspond, with at least a part of one or more persons captured at the second time.