Hangzhou Hikvision Digital Technology Co., Ltd.

Renguang Feng

Peng Wang

Bin Guo

Xi Chen

Jiale Fang

An authentication method, system and a camera for person-identity document comparison are provided. The authentication method for person-identity document comparison includes: acquiring multiple face images; obtaining at least one target face image that meets a preset condition from the multiple face images (S); receiving an ID image obtained by an ID reading support device (S); comparing the ID image with each target face image to obtain a person-ID document similarity for each target face image respectively (S); and, if the number of target face images with person-ID document similarities higher than a preset similarity threshold reaches a first preset number, determining that the authentication is successful (S). The method achieves high real-time performance of person authentication through the person-ID document comparison.

People-credentials comparison authentication method, system and camera

Disclosed is a statistical method, apparatus and device for customer flow. The method includes: acquiring video data on which the statistics is to be made (S), identifying facial areas in the video data (S), matching the identified facial areas with pre-set facial information, wherein the pre-set facial information may be facial information of a person unrelated to the customer flow (for example, a staff, etc.); determining the number of successfully matched facial areas, to obtain the customer flow without unrelated persons (S). It can be seen that the method removes the interference from unrelated persons and improves the accuracy of customer flow statistics.

Customer flow statistical method, apparatus and device

Embodiments of the present application provide a method and apparatus for updating an online self-learning event detection model. The method includes: presenting, when at least one target alerting event generated by the current event detection model is detected, to a user the at least one target alerting event, so that the user provides an event result for each target alerting event based on the at least one presented target alerting event; obtaining the event result for each target alerting event provided by the user based on the at least one presented target alerting event; determining whether a target alerting event for which an event result has been provided by the user satisfies a predetermined update condition, and if so, training and obtaining a target event detection model based on at least one target alerting event for which an event result has been provided by the user and corresponding event result, and predetermined training samples; and replacing the current event detection model with the target event detection model. By means of the method and apparatus according to the present application, the current event detection model may be continually updated, and thus improving the accuracy of the online learning.

Growing community of inventors

Zhejiang, China

Renguang Feng