Tracking system and method employing an artificial neural network for tracking tools in and nearby a transportation vehicle

Patent metadata

Field	Value
Publication number	US-2024177468-A1
Application number	US-202418435818-A
Country	US
Kind code	A1
Filing date	Feb 7, 2024
Priority date	Jan 29, 2021
Publication date	May 30, 2024
Grant date	—

Abstract

A tracking system and method for tracking tools in and nearby a transportation vehicle is provided. The tracking system comprises a vehicle-based detection unit for optically acquiring tool sets in the vehicle loading space from different angles and providing digital image data as well as corresponding range information. An electronic main controller unit is operatively coupled to a communication receiving unit and communicates with the vehicle-based detection unit and a cloud-based computer system of the tracking system. A mobile computing unit includes an optical camera and a LIDAR sensor device and wirelessly communicates with the electronic main controller unit and the cloud-based computer system. The tool detection and tracking is accomplished by combining an image-based detection employing an artificial neural network in the cloud-based computer system and a signal-based detection employing the short-range wireless network communication means.

First claim

1 . A method of tracking tools in and nearby a transportation vehicle ( 6 ) using a tracking system, the method comprising:
training (S 200 ) the at least one artificial neural network of the cloud-based computer system ( 12 ) using digital image data and corresponding range information provided by the mobile computing unit ( 9 ); communicating (S 4 , S 300 ) the weights of the at least one trained artificial neural network to the electronic main controller unit ( 7 ) of the tracking system; and periodically:
by activating (S 6 ) the vehicle-based detection unit ( 24 ), providing digital image data and corresponding range information regarding the vehicle loading space ( 23 ),
providing (S 500 ) a prediction output regarding identity and location of tool sets ( 4 ) of the plurality of tool sets ( 4 ), based on the provided digital image data and corresponding range information and the trained artificial neural network,
receiving signals transmitted by each short-range wireless network communication member ( 5 ) with the short-range wireless network communication receiving unit ( 22 ),
performing (S 600 ) a tracking and localization algorithm on the received signals to obtain an estimate for locations of identified tool sets ( 4 ) of the plurality of tool sets ( 4 ), and
applying (S 700 ) a recursive estimator algorithm for deriving a refined result for locations of identified tool sets ( 4 ) of the plurality of tool sets ( 4 ), using the prediction output derived on the basis of the trained artificial neural network and the estimate for locations of identified tool sets ( 4 ) as input data.

2 . The method as claimed in claim 1 , wherein training (S 200 ) of the at least one artificial neural network further comprises using (S 5 ) signals, provided by the mobile computing unit ( 9 ), that have been transmitted by and that are unique to each short-range wireless network communication member ( 5 ).

3 . The method as claimed in claim 1 , further comprising visualizing (S 10 ) the refined result for locations of identified tool sets ( 4 ) of the plurality of tool sets ( 4 ) on a display unit of the mobile computing unit ( 9 ).

4 . The method as claimed in claim 1 , further comprising storing (S 9 ) the derived refined results for locations of identified tool sets ( 4 ) of the plurality of tool sets ( 4 ) in the cloud-based computer system ( 12 ).

Assignees

• Ford Global Tech Llc

Inventors

• Aslandere Turgay Isik
• Grein Marcel

Classifications

• G06V10/809 Primary

  of classification results, e.g. where the classifiers operate on the same input data · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06V20/59

  inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions · CPC title

• H04W4/025

  using location based information parameters · CPC title

• H04W4/38

  for collecting sensor information · CPC title