18158950. SYSTEMS AND METHODS FOR PROCESSING IMAGES CAPTURED AT A PRODUCT STORAGE FACILITY simplified abstract (Walmart Apollo, LLC)

From WikiPatents
Revision as of 04:53, 26 July 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

SYSTEMS AND METHODS FOR PROCESSING IMAGES CAPTURED AT A PRODUCT STORAGE FACILITY

Organization Name

Walmart Apollo, LLC

Inventor(s)

Ishan Arora of Bangalore (IN)

Raghava Balusu of Achanta (IN)

Avi Raj of Buxar (IN)

Abhinav Pachauri of Kanpur (IN)

Han Zhang of Plano TX (US)

Mingquan Yuan of Flower Mound TX (US)

Avinash M. Jade of Bangalore (IN)

Lingfeng Zhang of Dallas TX (US)

Srinivas Muktevi of Bengaluru (IN)

Amit Jhunjhunwala of Bangalore (IN)

Siddhartha Chakraborty of KOLKATA (IN)

SYSTEMS AND METHODS FOR PROCESSING IMAGES CAPTURED AT A PRODUCT STORAGE FACILITY - A simplified explanation of the abstract

This abstract first appeared for US patent application 18158950 titled 'SYSTEMS AND METHODS FOR PROCESSING IMAGES CAPTURED AT A PRODUCT STORAGE FACILITY

The abstract describes a system for labeling objects in images captured at a product storage facility, utilizing a control circuit and a user interface. The control circuit selects unprocessed images, processes them iteratively, clusters them into groups, selects clustered images from each group, and outputs them. The user interface displays clustered images and allows users to label objects in each image to train a machine learning model.

  • System for labeling objects in images captured at a product storage facility
  • Utilizes a control circuit and a user interface
  • Control circuit selects, processes, clusters, and outputs images
  • User interface displays images and allows user input for labeling objects
  • Labeled dataset is used to train a machine learning model

Potential Applications: - Automated inventory management in warehouses - Quality control in manufacturing processes - Security monitoring in sensitive areas

Problems Solved: - Streamlining object labeling in images - Enhancing efficiency in image processing tasks - Improving accuracy in object recognition

Benefits: - Increased productivity in image analysis - Enhanced data organization and categorization - Facilitates the training of machine learning models

Commercial Applications: Title: Automated Object Labeling System for Image Analysis This technology can be applied in industries such as e-commerce, logistics, and surveillance for automated object labeling and image analysis tasks. It can improve operational efficiency and accuracy in various processes, leading to cost savings and enhanced decision-making capabilities.

Questions about Automated Object Labeling System for Image Analysis:

1. How does this technology improve the efficiency of image processing tasks? - The technology streamlines the process of labeling objects in images, reducing manual effort and increasing productivity.

2. What are the potential applications of this system beyond product storage facilities? - This system can be utilized in various industries for tasks such as quality control, security monitoring, and automated inventory management.


Original Abstract Submitted

In some embodiments, apparatuses and methods are provided herein useful to labeling objects in captured images. In some embodiments, there is provided a system for labeling objects in images captured at a product storage facility including a control circuit and a user interface. The control circuit is configured to select a set of unprocessed images; receive a selected configuration based on data resulting from iteratively processing the set of unprocessed images; cluster each unprocessed image into a corresponding group based on the selected configuration; select a plurality of clustered images from each of the plurality of groups; and output the plurality of clustered images from each group. The user interface is configured to: display each clustered image; and receive a user input labeling one or more objects shown in each clustered image resulting in a labeled dataset used to train a machine learning model.