公开(公告)号：US12142261B2

公开(公告)日：2024-11-12

申请号：US17203269

申请日：2021-03-16

Applicant: INTELLIVISION TECHNOLOGIES CORP.

Inventor： Krishna Khadloya ,  Chandan Gope ,  Vaidhi Nathan

IPC: G10L15/16 ,  G06F9/54 ,  G06N3/045 ,  G06N3/08 ,  G06N20/10 ,  G06N20/20 ,  G10L25/18 ,  G10L25/21

Abstract: Artificial intelligence-based processing can be used to classify audio information received from an audio input unit. In an example, audio information can be received from a microphone configured to monitor an environment. A processor circuit can identify identifying one or more features of the audio information received from the microphone and use a first applied machine learning algorithm to analyze the one or more features and determine whether the audio information includes an indication of an abnormal event in the environment. In an example, the processor circuit can use a different second applied machine learning algorithm, such as a neural network-based deep learning algorithm, to analyze the same one or more features and classify the audio information as including an indication of a particular event type in the environment.

公开(公告)号：US11601620B2

公开(公告)日：2023-03-07

申请号：US17196783

申请日：2021-03-09

Applicant: IntelliVision Technologies Corp.

Inventor： Vaidhi Nathan ,  Krishna Khadloya ,  Prakash Narayan ,  Albert Kay

IPC: H04N7/18 ,  G06N3/08 ,  H04L67/1036 ,  H04L67/1097 ,  G06V20/10

Abstract: The invention is based, in part, on a system and method designed to be able to easily and automatically scale up to millions of cameras and users. To do this, this discourse teaches use of modern cloud computing technology, including automated service provisioning, automated virtual machine migration services, RESTful API, and various firewall traversing methods to facilitate the scaling process. Moreover, the system and method described herein teaches scalable cloud solutions providing for higher though-put camera provisioning and event recognition. The network may segregate the retrieval server from the storage server, and by doing so, minimizing the load on any one server and improving network efficiency and scalability.

公开(公告)号：US20150022666A1

公开(公告)日：2015-01-22

申请号：US14337962

申请日：2014-07-22

Applicant: Intellivision Technologies Corp.

Inventor： Albert Kay ,  Prakash Narayan ,  Vaidhi Nathan

IPC: H04L29/08 ,  H04N5/232 ,  H04L29/06 ,  H04N7/18

CPC classification number: H04L67/025 ,  H04L63/029 ,  H04L65/4084 ,  H04L65/608 ,  H04L67/1097 ,  H04L67/12 ,  H04L67/42 ,  H04L69/40 ,  H04N5/23206 ,  H04N5/23225 ,  H04N7/181

Abstract: Methods of monitoring real-world environments using a plurality of processor controlled Internet video cameras, scalable cloud computing technology, and various Internet connected smartphones and tablet computers. The system is designed to use cloud computing technology, including automated service provisioning, automated virtual machine migration services, RESTful API, and various firewall traversing methods to scale to up to millions of cameras and beyond. The integrity of the system is maintained by requiring that the various video cameras continually send “heartbeat” camera status messages to the cloud servers. The video cameras can optionally also be configured to automatically detect various events occurring in their local environments, report these events to clients, and stream event video data either directly or indirectly to the clients, or alternatively save the video data in various scalable third party cloud storage systems such as the Amazon S3 service. Time expiring tokens and encryption keys help ensure system security.

Abstract translation: 使用多个处理器控制的因特网摄像机，可扩展的云计算技术以及各种因特网连接的智能电话和平板计算机监视现实环境的方法。 该系统旨在使用云计算技术，包括自动化服务配置，自动化虚拟机迁移服务，RESTful API和各种防火墙穿越方法，以扩展到数百万台摄像机及以上。 通过要求各种摄像机连续向云服务器发送“心跳”摄像机状态消息来维持系统的完整性。 视频摄像机还可以被配置为自动检测在其本地环境中发生的各种事件，将这些事件报告给客户端，以及将事件视频数据直接或间接地传送到客户端，或者将视频数据保存在各种可扩展的第三方云 存储系统，如Amazon S3服务。 时间到期令牌和加密密钥有助于确保系统安全。