Surveillance system employing plurality of unmanned aerial vehicles

Patent metadata

Field	Value
Publication number	US-12225327-B2
Application number	US-202318139683-A
Country	US
Kind code	B2
Filing date	Apr 26, 2023
Priority date	May 16, 2022
Publication date	Feb 11, 2025
Grant date	Feb 11, 2025

Abstract

Provided is a surveillance system employing a plurality of unmanned aerial vehicles (UAVs), the surveillance system showing improved surveillance performance while optimizing common energy consumption for computing of all the UAVs and also providing a stable visual monitoring service using autonomous mobility of the plurality of UAVs regardless of movement of an object to be monitored and action uncertainty of an adjacent UAV.

First claim

What is claimed is:

1. A surveillance system employing a plurality of unmanned aerial vehicles (UAVs) each of which communicates with a UAV management device through a wireless communication network and includes a camera module, a sensor module, a communication module, a memory module, a movement module, a movement control module, a processor, a battery, and a power management module, wherein the plurality of UAVs include agent UAVs and a leader agent UAV which wirelessly communicates with the agent UAVs,
wherein the agent UAVs calculate first state data including absolute location information, relative location information, energy information required for flight and surveillance, and surveillance information using information input from the camera modules and the sensor modules, transmit the first state data to the leader agent UAV, generate first movement action data and resolution adjustment data for a first surveillance image by inputting the first state data to a first neural network algorithm, and then fly according to the generated first movement action data and adjust surveillance ranges according to the resolution adjustment data for the first surveillance image,
wherein the leader agent UAV calculates second state data including absolute location information, relative location information, energy information required for flight and surveillance, and surveillance information using information input from the camera module and the sensor module, generates second movement action data and resolution adjustment data for a second surveillance image by inputting the second state data and the first state data received from the agent UAVs to a second neural network algorithm, and then flies according to the generated second movement action data and adjusts a surveillance range according to the resolution adjustment data for the second surveillance image, and
wherein the leader agent UAV calculates an average of a plurality of pieces of state data each input from the agent UAVs when the number of agent UAVs is two or more, and inputs the second state data and the calculated average of the plurality of pieces of state data to the second neural network algorithm.

2. The surveillance system of claim 1 , wherein the surveillance information included in the first state data includes a first image resolution and identification information of a first object to be monitored within the surveillance ranges of the agent UAVs, and
wherein the surveillance information included in the second state data includes a second image resolution and identification information of a second object to be monitored within the surveillance range of the leader agent UAV.

3. The surveillance system of claim 1 , wherein the plurality of UAVs further include a non-agent UAV which does not communicate with other UAVs, and
wherein surveillance images each captured by the leader agent UAV, the agent UAVs, and the non-agent UAV are transmitted to the UAV management device.

4. The surveillance system of claim 3 , wherein, when the number of agent UAVs is two or more, an agent UAV closest to the non-agent UAV flies around the non-agent UAV.

5. A surveillance system employing a plurality of unmanned aerial vehicles (UAVs) each of which communicates with a UAV management device through a wireless communication network and includes a camera module, a sensor module, a communication module, a memory module, a movement module, a movement control module, a processor, a battery, and a power management module, wherein the plurality of UAVs include agent UAVs and a leader agent UAV which wirelessly communicates with the agent UAVs,
wherein the agent UAVs calculate first state data including absolute location information, relative location information, energy information required for flight and surveillance, and surveillance information using information input from the camera modules and the sensor modules, transmit the first state data to the leader agent UAV, generate first movement action data and resolution adjustment data for a first surveillance image by inputting the first state data to a first neural network algorithm, and then fly according to the generated first movement action data and adjust surveillance ranges according to the resolution adjustment data for the first surveillance image,
wherein the leader agent UAV calculates second state data including absolute location information, relative location information, energy information required for flight and surveillance, and surveillance information using information input from the camera module and the sensor module, generates second movement action data and resolution adjustment data for a second surveillance image by inputting the second state data and the first state data received from the agent UAVs to a second neural network algorithm, and then flies according to the generated second movement action data and adjusts a surveillance range according to the resolution adjustment data for the second surveillance image,
wherein the plurality of UAVs further include a non-agent UAV which does not communicate with other UAVs,
wherein surveillance images each captured by the leader agent UAV, the agent UAVs, and the non-agent UAV are transmitted to the UAV management device, and
wherein, when the number of agent UAVs is two or more, an agent UAV closest to the non-agent UAV flies around the non-agent UAV.

6. The surveillance system of claim 5 , wherein the leader agent UAV calculates an average of a plurality of pieces of state data each input from the agent UAVs when the number of agent UAVs is two or more, and inputs the second state data and the calculated average of the plurality of pieces of state data to the second neural network algorithm.

7. The surveillance system of claim 5 , wherein the surveillance information included in the first state data includes a first image resolution and identification information of a first object to be monitored within the surveillance ranges of the agent UAVs, and
wherein the surveillance information included in the second state data includes a second image resolution and identification information of a second object to be monitored within the surveillance range of the leader agent UAV.

Assignees

• Univ Korea Res & Bus Found
• Ajou Univ Industry—Academic Cooperation Foundation
• Univ Ajou Ind Academic Coop Found

Inventors

• Kim Joongheon
• Jung Soyi
• Kim Jae-Hyun
• Yun Won Joon
• Park Soohyun

Classifications

• B64U10/00 Primary

  Type of UAV · CPC title

• B64U2101/20

  for use as communications relays, e.g. high-altitude platforms · CPC title

• B64U2101/31

  for surveillance · CPC title

• H04N23/662

  by using camera arrangements where one camera controls another camera to affect the control of camera image capture, e.g. placing the camera in a desirable condition to capture a desired image · CPC title

• H04N23/815

  for controlling the resolution by using a single image · CPC title