Invention Grant
- Patent Title: Pruning filters for efficient convolutional neural networks for image recognition of environmental hazards
-
Application No.: US15979505Application Date: 2018-05-15
-
Publication No.: US10796169B2Publication Date: 2020-10-06
- Inventor: Asim Kadav , Igor Durdanovic , Hans Peter Graf
- Applicant: NEC Laboratories America, Inc.
- Applicant Address: JP
- Assignee: NEC Corporation
- Current Assignee: NEC Corporation
- Current Assignee Address: JP
- Agent Joseph Kolodka
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06K9/46 ; G06K9/62 ; G06K9/66 ; G06N3/04 ; G06N3/08 ; G06N5/04

Abstract:
Systems and methods for predicting changes to an environment, including a plurality of remote sensors, each remote sensor being configured to capture images of an environment. A processing device is included on each remote sensor, the processing device configured to recognize and predict a change to the environment using a pruned convolutional neural network (CNN) stored on the processing device, the pruned CNN being trained to recognize features in the environment by training a CNN with a dataset and removing filters from layers of the CNN that are below a significance threshold for image recognition to produce the pruned CNN. A transmitter is configured to transmit the recognized and predicted change to a notification device such that an operator is alerted to the change.
Public/Granted literature
Information query