Loading patent…
AssigneesDeutsche Telekom AG, The Board of Trustees of the Leland Stanford Junior University
InventorsCheng-Hsin Hsu, Kyu-Han Kim, Jatinder Pal Singh, David M. Chen, Sam Tsai, Bernd Girod
Estimating the term…
A method of tracking an inventory of objects via a mobile communications device includes acquiring an image of one or more of the objects via the mobile communications device, which also collects a location of the mobile communications device while acquiring the image of the one or more of the objects. The location and image are transferred from the mobile communications device to a remote server via a wireless network, such that the one or more of the objects are identified at the server based on the image, and the location and identity of the one or more objects are stored on a database associated with the server.
A computer-implemented method for image processing and object recognition, the method comprising:
A non-transitory computer-readable medium, part of a remote image processing server, having processor-executable instructions stored thereon for image processing and object recognition, the processor-executable instructions, when executed by a processor, causing the following steps to be performed:
A remote image processing server, the server comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
Logistics, e.g. warehousing, loading or distribution; Inventory or stock management: inventory or stock management, e.g. order filling,…
Inventory or stock management, e.g. order filling, procurement or balancing against orders: by inventory control or reporting using inventory…
Inventory fulfillment: by distributed inventory management
Information and communication technology [ict] specially adapted for administrative, commercial, financial, managerial
About 5 years 3 months of term left · ends 7 Feb 2032 (estimated)
The invention pertains to location-aware asset management, and more particularly pertains to an asset management system integrating visual search tools and location inference techniques.
It is important to accurately manage assets to reduce loss and more efficiently deploy the assets when and/or where needed. However, accurately managing a large set of assets is a difficult, time-consuming task, both for individuals and institutions. Asset inventories may be maintained by manual updates or deployments of barcode or radio-frequency identification (RFID) technologies. However, such manual updates will be costly in terms of human labor and the results may sometimes be erroneous.
Barcode or RFID systems, while offering a potential alternative, tend to be expensive and may only be affordable to large institutions. Further, such systems require physically attaching a tag to each asset.
Other features of the invention will be appreciated from the attached description and associated figures of which:
FIG. 1 is a screen shot illustration within a system implementing an asset management method according to an embodiment described herein;
FIG. 2 is a schematic diagram illustrating the building and updating of asset inventory according to an embodiment of the invention;
The principles described herein employ an asset management system consisting of a mobile device with a camera and network connection, and a remotely located server. The mobile device captures images of assets and sends query information to the server. The server performs segmentation and recognition of the objects within the query image, and infers the location of the object using query sensor data. The location and identity of the assets are then saved within an asset database.
An example of books on shelves is used herein as an example to demonstrate the practicality of the described asset management system. In particular, a spine segmentation algorithm is used in addition to the application of robust feature-based image matching to recognize each segmented spine, and to thus accurately estimate each spine's pose in the query photo. Sensor readings from the smartphone and image matching help localize each recognized book spine first within a room and then within a bookshelf.
In an embodiment, the described system employs commodity smartphones and personal computers, and thus is low-cost and easy to deploy. As used herein, the term “smartphone” refers to a mobile electronic computing device usable to place cellular calls and that is equipped with a camera, e.g., an auto-focus camera, motion and orientation sensors, and network access, e.g., high-speed network access. The camera may also be referred to as an image acquisition unit, and may include dedicated code or software for image processing. Each such smartphone includes a wireless communications unit for interfacing to one or more wireless networks. Acquired images may be stored on a memory of the smartphone and/or transferred via the wireless communications unit to a remote entity.