Abstract: A crowd type classification system of an aspect of the present invention includes: a staying crowd detection unit that detects a local region indicating a crowd in staying from a plurality of local regions determined in an image acquired by an image acquisition device; a crowd direction estimation unit that estimates a direction of the crowd for an image of a part corresponding to the detected local region, and appends the direction of the crowd to the local region; and a crowd type classification unit that classifies a type of the crowd including a plurality of staying persons for the local region to which the direction is appended by using a relative vector indicating a relative positional relationship between two local regions and directions of crowds in the two local regions, and outputs the type and positions of the crowds.
Abstract: The present invention addresses the problem of preventing products from being carried outside a store without complete a checkout process in a checkout system in which a product, a shopping basket in which the product is accommodated, or a shopping cart in which the product is accommodated is disposed in a checkout device when performing a checkout process. In order to solve the problem, a product registration device (10) registers the product. The checkout device (20) performs the checkout process for the product registered by the product registration device (10). An output unit (320) outputs information indicating that a target object (30) (in the example shown in the drawing, a shopping cart (32) in which a product is accommodated) has moved from the checkout device (20) on the basis of the presence or absence of movement of the target object (30) from the checkout device (20), and the state of the checkout process.
Abstract: The slide bar display control device according to the present invention includes, a display means which indicates a first slide bar including a first slider and a first bar, an input means which can select an arbitrary part of the first slide bar shown on the display means based on touch operation, and a control means which controls the display means and the input means, wherein, when the control means detects that a first operation has been performed in a state that the first slider shown on the display means is being touched in the input means, the display means indicates a second slide bar including a second slider and a second bar, and wherein the second slider is a slider different in a variation amount of a set value per unit moving distance from the first slider.
Abstract: Provided is to appropriately allocate resources among the versions in the system, the resource setting control device includes: determination unit that extracts a load pattern of a service request in a specific period of time from a) a request history, including information of a group, the requested version, and a resource usage during execution of the service, and b) the request history in operation information storage, and updates the reference pattern when detecting that change from the reference pattern is beyond a specific range; and change unit that determines, for each of the versions, a resource request amount, based on a peak value of the resource usage in the specific period of time and a number of server devices providing the version, when detecting the load pattern change, and outputs the determined resource request amount.
Abstract: A rendering apparatus includes: a fragmentation unit configured to divide a three-dimensional model into a plurality of fragments; a calculation unit configured to calculate first radiance for each of the plurality of fragments, the first radiance being radiance in a direction from each of the plurality of fragments to every other of the plurality of fragments; and a rendering unit configured to calculate second radiance for each fragment visible from a viewpoint among the plurality of fragments based on the first radiance, the second radiance being radiance in a direction from the fragment to the viewpoint, project each fragment visible having the second radiance on a rendering screen relevant to the viewpoint, and generate a rendered image.
Abstract: An in-store monitoring device includes a memory storing instructions, and at least a processor reading the instructions to perform: acquiring an image in which one or more shoppers are captured; detecting, from the image, one or more shoppers present in a predetermined area; generating, for each of the shoppers, information on number of goods obtained by the shoppers; and calculating a sum of numbers of goods obtained by the detected shoppers.
Abstract: A guidance assistance apparatus includes: a memory that stores a set of instructions; and at least one processor configured to execute the set of instructions to: acquire a guidance route through which a guided person is to be guided from routes from a start-point position to an end-point position; calculate, based on information relating to the routes, an influence level on the guided person in a case in which the guided person deviates from the acquired guidance route, with respect to each of branch places at which the guidance route branches into a route different from the guidance route; and output the calculated influence level.
Abstract: A forwarding element includes a control engine and a forwarding table. The control engine includes a command template that includes a stateful interaction instruction. The forwarding table includes a rule entry that defines a match description and an action instruction. The forwarding element is configured to: receive a packet; determine packet attributes based on the packet; compare the packet attributes to the match description to determine whether there is a rule match, execute the action instruction in response to determining there is the rule match, which includes causing a trigger signal to be sent to the control engine, the trigger signal corresponding to the command template, and perform a stateful interaction on the packet according to the stateful interaction instruction in response to receiving the trigger signal.
Abstract: A program analysis method according to an exemplary aspect of the present disclosure includes: generating an analysis-target abstract code that is data representing a mathematical model into which an inspection-target execution code is transformed; and determining whether or not the inspection-target execution code is a fraudulent program by executing at least processing of determining whether or not the analysis-target abstract code includes a known factor code that is data representing a mathematical model into which a known execution code is transformed, and processing of determining whether or not a state at an end of execution of the inspection-target execution code is included in success state information indicating a state in which an attack by a fraudulent program is successful.
Abstract: The present invention is directed to a system and method for restricting data, or portions thereof, to specific display devices when accessed by a user. Furthermore, the system and method of the invention are directed, in part, to evaluating in real time, the access level of a device and restricting the availability of sensitive information on the device according to the access level as determined by device location and hardware configuration.
Abstract: A pluggable optical connector is configured to be insertable into and removable from an optical communication apparatus, and to be capable of communicating a modulation signal and a data signal with the optical communication apparatus. A wavelength-tunable light source is configured to output an output light and a local oscillation light. An optical transmission unit is configured to output an optical signal generated by modulating the output light in response to the modulation signal. An optical reception unit is configured to demodulate an optical signal received by using the local oscillation light to the data signal. Pluggable optical receptors are configured in such a manner that an optical fiber is insertable into and removable from the pluggable optical receptors, and configured to be capable of outputting the optical signal to the optical fiber and transferring the optical signal received thorough the optical fiber to the optical reception unit.
Abstract: An inference device comprises a weight storage part that stores weights, an input data storage part that stores input data, and a PE (Processing Element) that executes convolution computation in convolutional neural network using the weights and input data. The PE adds up weight elements to be multiplied with elements of the input data for each of variable values of the elements of the input data. The PE multiplies each of the variable values of the elements of the input data with each cumulative sum value of weights corresponding to the variable values of the elements of the input data. The PE adds up a plurality of multiplication results obtained by the multiplications.
Abstract: An advertisement guidance system includes: an advertisement database in which plural pieces of advertisement information are so stored that guidance information on each advertisement, feature information on the advertisement, and user target information are associated with one another; an extraction unit which extracts, from the advertisement database, advertisement information having user target information that matches an attribute of a user; an advertisement information storage unit which stores the advertisement information extracted by the extraction unit; a specification unit which specifies advertisement information having feature information on an advertisement contained in viewed content from the advertisement information stored in the advertisement information storage unit; and a display control unit which displays, on a display unit, guidance information on the advertisement included in the specified advertisement information.
Abstract: Provided is a pre-calculation device capable of keeping a secret against malicious behaviors of participants while keeping a processing load small. A Beaver triple generation processor generates a secret-shared Beaver triple formed of two secret-shared random numbers and a secret-shared value of a product of the two random numbers. A Beaver triple random inspection processor randomly selects a secret-shared Beaver triple, restores the Beaver triple through communication to and from other pre-calculation devices, and confirms that a product of first two elements is equal to a third element. The Beaver triple position stirring processor randomly replaces Beaver triples that have not been restored, to generate replaced secret-shared Beaver triples.
Abstract: An image processing device includes: a determination unit that determines whether a moving body driven by a driver is moving forward, based on acquired information, and determines that imaging timing is in a satisfactory state when it is determined that the moving body is moving forward.
Abstract: In order to efficiently receive spatial light without using a condensing lens, this light receiving device comprises: a first light guide body that has at least a first light receiving surface and a first light emission end and guides, in an oriented manner, signal light entering from the first light receiving surface to the first light emission end; a second light guide body that has at least a second light receiving surface and a second light emission end, the second light receiving surface being connected to the first light emission end, and that guides, in an oriented manner, signal light entering from the second light receiving surface to the second light emission end; and a light receiver that has a light receiving part connected to the second light emission end and that converts the signal light received by the light receiving part to an electrical signal.
Abstract: An image processing device 10 includes: a segmentation unit 21 that segments an input image 200 representing a result of observing an ocean surface region and a land surface region from overhead into ocean surface block images 211 and land surface block images 212, based on a segmentation criterion 210; a first determination unit 22 that determines a binarization criterion 220 for the ocean surface block images 211, based on a scattering model for electromagnetic waves in the ocean surface region; a second determination unit 23 that determines a binarization criterion 230 for the land surface block images 212, based on the binarization criterion 220 and a positional relationship between the ocean surface block images and the land surface block images; and a generation unit 25 that generates a land mask image 250 by performing binarization processing on the input image 200 based on the binarization criterion 220 and the binarization criterion 230.
Abstract: A radar image processing device includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: determine a search range based on a reference block and a layover direction, the reference block being set as an area of interest in a radar image generated from data obtained by an imaging radar, the layover direction being a direction in which layover occurs in the radar image and being estimated from an incident direction of an electromagnetic wave used for observation by the imaging radar; extract a similar block that is similar to the reference block and included in the search range by searching the search range; and perform filtering processing for reducing speckles generated in the radar image by using the reference block and the extracted similar block.
Abstract: This security evaluation system includes a first graph generation part that generates a first evaluation graph representing a connection relationship between resources as a target for security evaluation; a second graph generation part that generates a second evaluation graph representing a personal relationship between areas where the resources are located; and display part that displays the first evaluation graph and the second evaluation graph in association with each other.
Abstract: A store system (1) includes a store apparatus (10), an image capturing apparatus (30), and a display (40) that is also used as a placement surface of a product (P). The image capturing apparatus (30) generates an image in which the product (P) placed on a display surface of the display (40) is captured.