Abstract: The present disclosure provides a method and device for identifying a product purchased by a user and intelligent shelf system. The method includes acquiring a weight of products carried in a container, acquiring a first monitoring image acquired in a monitoring area corresponding to the container, identifying the first monitoring image, and obtaining an identification result, wherein the identification result comprises user identity information when it is determined that the weight of the products is reduced, acquiring a time when at least one product carried in the container is picked up, and determining information of at least one picked-up product, obtaining the user identity information corresponding to the at least one picked-up product, and associating the user identity information with the information of the at least one picked-up product.

Abstract: A person tracking method, comprising: acquiring N frames in units of time windows; acquiring, in time windows, tracking paths of a target person according to the N frames; and constructing continuous tracking paths by means of continuous time windows, so as to obtain the tracking results of the target person.

Abstract: The present disclosure provides a method, system, and terminal device for re-identifying a person in a closed place, relating to the field of video processing technologies. The method comprises: dividing a closed place into a plurality of regions comprising an entrance region, any of the regions comprising at least one camera for photographing; confirming a person first entering based on a trajectory tracking of the person in the entrance area, and assigning a unique identity number to the person, acquiring and recording feature information thereof and binding the identity number with the feature information; and when re-identification of a person in the closed place is performed, matching person's feature information captured by the camera of the region where the person is, with recorded feature information selecting the identity number bound with recorded feature information that best matches the feature information of the person as the identity number of the person.

Abstract: A video image segmentation method includes: obtaining an image segmentation model by performing machine learning based on a historical video image and a mask image of the historical video image; adjusting the image segmentation model based on an initial frame of an image to be segmented, a previous frame of a frame to be segmented and a mask image of the previous image; and performing segmentation on the image to be segmented using the image segmentation model after the adjusting.

Abstract: The disclosure relates to the technical field of data processing. Disclosed are a pedestrian flow funnel generation method and apparatus, a storage medium and an electronic device. The method can comprise: acquiring a current frame of image, and tracking and updating, according to a multi-target tracking algorithm, a head and shoulder area in a tracking sequence set in the current frame of image; acquiring, according to a head and shoulder recognition model, a head and shoulder area in the current frame of image, and updating, according to the head and shoulder area in the current frame of image, the tracking sequence set; analysing a motion track of each head and shoulder area in the tracking sequence set so as to count pedestrians, and when the current frame of image is the last frame of image, generating a pedestrian flow funnel based on a counting result of pedestrians.

Abstract: The present disclosure provides a method and device for identifying a product purchased by a user and intelligent shelf system. The method includes acquiring a weight of products carried in a container, acquiring a first monitoring image acquired in a monitoring area corresponding to the container, identifying the first monitoring image, and obtaining an identification result, wherein the identification result comprises user identity information when it is determined that the weight of the products is reduced, acquiring a time when at least one product carried in the container is picked up, and determining information of at least one picked-up product, obtaining the user identity information corresponding to the at least one picked-up product, and associating the user identity information with the information of the at least one picked-up product.

Abstract: The present disclosure provides a method, system, and terminal device for re-identifying a person in a closed place, relating to the field of video processing technologies. The method comprises: dividing a closed place into a plurality of regions comprising an entrance region, any of the regions comprising at least one camera for photographing; confirming a person first entering based on a trajectory tracking of the person in the entrance area, and assigning a unique identity number to the person, acquiring and recording feature information thereof and binding the identity number with the feature information; and when re-identification of a person in the closed place is performed, matching person's feature information captured by the camera of the region where the person is, with recorded feature information selecting the identity number bound with recorded feature information that best matches the feature information of the person as the identity number of the person.

Abstract: The disclosure relates to the technical field of data processing. Disclosed are a pedestrian flow funnel generation method and apparatus, a storage medium and an electronic device. The method can comprise: acquiring a current frame of image, and tracking and updating, according to a multi-target tracking algorithm, a head and shoulder area in a tracking sequence set in the current frame of image; acquiring, according to a head and shoulder recognition model, a head and shoulder area in the current frame of image, and updating, according to the head and shoulder area in the current frame of image, the tracking sequence set; analysing a motion track of each head and shoulder area in the tracking sequence set so as to count pedestrians, and when the current frame of image is the last frame of image, generating a pedestrian flow funnel based on a counting result of pedestrians.

Abstract: A person tracking method, comprising: acquiring N frames in units of time windows; acquiring, in time windows, tracking paths of a target person according to the N frames; and constructing continuous tracking paths by means of continuous time windows, so as to obtain the tracking results of the target person.

Abstract: A video image segmentation method includes: obtaining an image segmentation model by performing machine learning based on a historical video image and a mask image of the historical video image; adjusting the image segmentation model based on an initial frame of an image to be segmented, a previous frame of a frame to be segmented and a mask image of the previous image; and performing segmentation on the image to be segmented using the image segmentation model after the adjusting.

Abstract: A system and method for limiting access requests. In one system, a load balancer receives an access request, parses the access request into a UDP message, and transmits the UDP message to an aggregator; the aggregator accumulates the UDP message according to a predefined combination of data fields and a predefined duration so as to produce statistical data, and sends the statistical data to a summarizer in response to a request from the summarizer; the summarizer requests the statistical data from the aggregator according to a predefined request time interval, receives the statistical data from the aggregator, generates a blacklist for the access requests according to the received statistical data and a predefined rule, and sends the blacklist to the load balancer in response to a request from the load balancer. The load balancer determines a processing action on each of the received access requests according to the current blacklist.

Abstract: A system and method for limiting access requests. In one system, a load balancer receives an access request, parses the access request into a UDP message, and transmits the UDP message to an aggregator; the aggregator accumulates the UDP message according to a predefined combination of data fields and a predefined duration so as to produce statistical data, and sends the statistical data to a summarizer in response to a request from the summarizer; the summarizer requests the statistical data from the aggregator according to a predefined request time interval, receives the statistical data from the aggregator, generates a blacklist for the access requests according to the received statistical data and a predefined rule, and sends the blacklist to the load balancer in response to a request from the load balancer. The load balancer determines a processing action on each of the received access requests according to the current blacklist.

Abstract: In general, aspects of this disclosure are directed towards techniques for using a computing device to perform the functionality of a vehicle key, so that the computing device may be used to automatically unlock the doors of a vehicle and/or to activate a previously-deactivated keyless ignition system. The computing device may be associated with a vehicle, including sending an identifier associated with the computing device to the vehicle via short-range communication. The computing device may also send to the vehicle, via short-range communication, at least one unlock door signal including an access code verifiable by the vehicle, and wherein receipt of the at least one unlock door signal by the vehicle enables the vehicle to unlock one or more of its doors without further user intervention.

Abstract: A method, system and computer program product for managing pooled VPN proxy servers by a central server is provided. The method includes receiving information from a plurality of computers wherein the information received is used for registering, with a central server, the respective computer as a VPN proxy server. The method also includes receiving a request from a client device for a VPN proxy server and sending a list of registered VPN proxy servers to the client device.

Abstract: Propagating user feedback on shared posts is described, including receiving a user indication associated with repost content. The repost content is associated with post content. The post content includes at least one item provided on a website. The repost content includes at least one other item provided on another website or the website, and the at least one other item is associated with the at least one item. The repost content is determined to be associated with the post content. Post feedback data based on the user indication is identified. The post feedback data is associated with the post content, and the post feedback data represents previous user indication. The post feedback data is updated based on the user indication.

Abstract: In general, aspects of this disclosure are directed towards techniques for using a computing device to perform the functionality of a vehicle key, so that the computing device may be used to automatically unlock the doors of a vehicle and/or to activate a previously-deactivated keyless ignition system. The computing device may be associated with a vehicle, including sending an identifier associated with the computing device to the vehicle via short-range communication. The computing device may also send to the vehicle, via short-range communication, at least one unlock door signal including an access code verifiable by the vehicle, and wherein receipt of the at least one unlock door signal by the vehicle enables the vehicle to unlock one or more of its doors without further user intervention.

Abstract: A system and method is disclosed, which facilitates data replication in a multi-master Relational Database Management Systems (RDBMS). An in-memory attribute is stored at a server of a multi-master database system. The in-memory attribute is associated with an operation, a record, and a global unique identifier (GUID) assuring uniqueness across the database system. The in-memory attribute indicates disallowing at the server additional requested operations associated with the record. The operation associated with the in-memory attribute is performed at the server and logged in a global accessible log associated with the server and available to other servers of the database system. The in-memory attribute is removed from the server based on a global accessible log associated with at least one of the other servers.

Abstract: Methods and systems for improving caching accuracy utilizing snapshot technology are provided. One or more requests for data are received. When the requests for data return valid data, the valid data is stored within a cache. The response performance of a server device is monitored. When the response performance of the server device is above a predetermined threshold, one or more snapshot versions of a memory block are taken. The memory block may include the current state of the valid data at the time the snapshot version was taken. Upon receiving a warm-up cache signal for the cache, a snapshot version is used to populate the cache and sent to a client device.

Abstract: Embodiments of a method and apparatus for replicating a process performed on a first computer on a remote computer, particularly for the replication of a database maintained of each of the computers. An offset is added to time stamps for a sequence of commands so that a correction in a command or data associated with the command that is subsequently received before the command is executed can be implemented. The correction can result in removing the command from the sequence of commands to be performed, changing the data associated with the command or delaying execution of the command, for example.

Abstract: A method, non-transitory computer readable medium, and apparatus that establishes a connection between a mobile computing device and a second computing device. A notification of an initiating event is received from the second computing device. Physical movement of the mobile computing device is determined during a time period defined by the notification of the initiating event and a triggering event. An alert is output when determined physical movement is below a threshold value.