Surveillance system, information processing device, fall detection method, and non-transitory computer readable medium

Patent metadata

Field	Value
Publication number	US-12510671-B2
Application number	US-201917437659-A
Country	US
Kind code	B2
Filing date	Mar 19, 2019
Priority date	Mar 19, 2019
Publication date	Dec 30, 2025
Grant date	Dec 30, 2025

Abstract

Provided are a surveillance system, an information processing device, a fall detection method, and a non-transitory computer readable medium capable of improving the accuracy of detecting a person who has fallen down in a railroad crossing. A surveillance system according to the present disclosure includes a LiDAR sensor (10) that emits a plurality of laser beams with different ranges to a surveillance area, and outputs a detection signal indicating a detection status of an object by each of the laser beams, and an information processing device (20) that determines that the object has fallen down when the detection status by a laser beam with a shorter range than a predetermined range indicates that the object is detected and the number of laser beams detecting the object decreases.

First claim

What is claimed is:

1 . A surveillance system comprising:
a camera configured to capture an image of a surveillance area, a LiDAR sensor; and an information processing device; wherein the LiDAR sensor comprises; at least one memory storing instructions, and at least one processor configured to execute the instructions to; emit a plurality of laser beams with different ranges to the surveillance area, and output a detection signal indicating a detection status of an object by each of the laser beams; and wherein the information processing device comprises; at least one memory storing instructions, and at least one processor configured to execute the instructions to; determine that the object has fallen down when the detection status by a laser beam with a shorter range than a predetermined range indicates that the object is detected and the number of laser beams detecting the object decreases, recognize the object in a captured image captured using the camera, and determine that the object has fallen down when timing when the number of laser beams detecting the object decreases and timing when the object becomes not recognized in the captured image where the object has been recognized are within a predetermined range.

2 . The surveillance system according to claim 1 , wherein the at least one processor of the information processing device is further configured to execute the instructions to determine that the object has fallen down when the detection signal by the laser beam with the shortest range among the plurality of laser beams detects the object.

3 . The surveillance system according to claim 1 , wherein the at least one processor of the LiDAR sensor is further configured to execute the instructions to control an illumination direction of the plurality of laser beams so that the plurality of laser beams reach an earth's surface inside the surveillance area.

4 . The surveillance system according to claim 1 , wherein the at least one processor of the information processing device is further configured to execute the instructions to rotate the captured image where the object becomes not recognized, and determine that the object has fallen down when the object becomes recognized in the captured image by using the rotated captured image and a learning model having learned a standing state of a person.

5 . A fall detection method comprising:
receiving, from a LiDAR sensor having emitted a plurality of laser beams with different ranges to a surveillance area, a detection signal indicating a detection status of an object by each of the laser beams; recognizing the object in a captured image captured using a camera; and determining that the object has fallen down when the detection status by a laser beam with a shorter range than a predetermined range indicates that the object is detected and the number of laser beams detecting the object decreases and when timing when the number of laser beams detecting the object decreases and timing when the object becomes not recognized in the captured image where the object has been recognized are within a predetermined range.

6 . A non-transitory computer readable medium storing a program causing a computer to execute:
receiving, from a LiDAR sensor having emitted a plurality of laser beams with different ranges to a surveillance area, a detection signal indicating a detection status of an object by each of the laser beams; recognizing the object in a captured image captured using a camera; and determining that the object has fallen down when the detection status by a laser beam with a shorter range than a predetermined range indicates that the object is detected and the number of laser beams detecting the object decreases and when timing when the number of laser beams detecting the object decreases and timing when the object becomes not recognized in the captured image where the object has been recognized are within a predetermined range.

Assignees

• Nec Corp

Inventors

• Miyamoto Shinichi

Classifications

• B61L29/00

  Safety means for rail/road crossing traffic · CPC title

• B61L23/007

  Safety arrangements on railway crossings · CPC title

• G06V40/103

  Static body considered as a whole, e.g. static pedestrian or occupant recognition · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title