Western Digital Technologies, Inc.

Ramy Ayad

Shaomin Xiong

Toshiki Hirano

Pritam Das

Rajeev Nagabhirava

Matthew Davidson

Damien Kah

Systems and methods described herein provide for the use and storage of intermediate layer data within a neural network processing system. A first neural network, such as an object detection neural network may receive and process raw video image data to generate output utilized for metadata creation. Secondary neural networks may be configured to accept input data from one or more intermediate layers of the first neural network instead of the raw video image data. In this way, the initial data processed by the intermediate layers of the first neural network can be stored and utilized as a shortcut for processing additional features or attributes within the video image data. This alleviates the need to process video image data multiple times in different neural networks. The intermediate layer data can be stored in a different and often cheaper storage system and recalled faster and with fewer resources for future use.

Storage and processing of intermediate features in neural networks

Systems and methods for audio privacy in network video surveillance systems are described. A video camera may include an image sensor and a microphone to generate a video stream. Responsive to detecting a human speaking condition in the video stream, the audio data may be selectively modified to mask a human voice component of the audio data for storing and/or displaying the surveillance video stream.

Audio privacy protection for surveillance systems

Systems and methods for redundant storage among networked video cameras are described. Video data for a group of video cameras is received by a parity video camera. The parity video camera calculates parity across the peer video data, stores the parity data to one storage location and backup video data for the storage location to another storage location. In some examples, the storage locations are selected from among the non-volatile memory of the group of video cameras or another group of video cameras.

Parity-based redundant video storage among networked video cameras

Systems and methods for a low light surveillance system with dual video streams are described. A video camera may include an image sensor and an infrared blocking filter. Responsive to detecting low light conditions, the infrared blocking filter may be disabled and the full spectrum video data from the camera may be sent in one video stream that is processed for user display, such as rendering in gray scale, and another video stream that is used for analytics processing, such as event detection.

Growing community of inventors

East Brunswick, NJ, United States of America

Ramy Ayad