Patent · US Active

Pest detector to identify a type of pest using machine learning

US10524461B1 · kind B1 · utility

13Cited by
6References
20Claims
0Family size

Inventors

Key dates

Filing dateSep 25, 2018
Grant dateJan 7, 2020
Priority date
Expiry dateSep 25, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In some implementations, a detector may include one or more sensors, one or more external indicators, one or more processors, and one or more non-transitory computer readable media storing instructions that are executable by the one or more processors to perform various operations. The operations may include detecting, by a motion sensor, movement associated with the pest and capturing, by a sensor (e.g., an imaging sensor) of the detector, sensor data (e.g., a digital image) of the pest. The operations may include determining, by a machine learning algorithm, that the sensor data indicates a presence of a pest, and sending a notification message to a computing device. The notification message may include at least a portion of the sensor data. The operations may include visually indicating, using a pest indicator of the one or more external indicators, that the pest was detected.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.