Object Recognition

JP2024541065APending Publication Date: 2024-11-06COMMONWEALTH SCI & IND RES ORG
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024526811
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-11-04
Filing Date
2022-11-04
Publication Date
2024-11-06

AI Technical Summary

Technical Problem

Existing object recognition systems face challenges in achieving robustness and generality, as specific models are effective for individual objects but lack versatility, while generalized models perform poorly and are often limited to a single sensing modality, necessitating multiple models for different sensing types.

Method used

An object recognition system comprising tags with object models and sensing systems with sensing device models, using shape encoding layers to enable robust, sensor-independent recognition of multiple objects by transmitting object-specific models periodically or on demand, allowing the system to focus on relevant models and reduce computational and storage needs.

Benefits of technology

The system achieves rapid, accurate, and efficient recognition of multiple objects by using object-specific models, reducing unnecessary data transmission and computation, and enabling cross-modal recognition through a common shape encoding layer.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024541065000001_ABST
    Figure 2024541065000001_ABST
Patent Text Reader

Abstract

The present invention provides an object recognition system for recognizing objects in an environment, the system comprising tags, each tag associated with an individual object and including a tag memory for storing an object model, which is a computational model indicating a relationship between the individual objects and a shape coding layer; a sensing system including a sensing device for sensing the environment, a sensing system memory for storing a sensing device model, which is a computational model indicating a relationship between sensor data captured using the sensing device and the shape coding layer, and a sensing system processor for receiving the object model from a transceiver, retrieving the sensing device model from the sensing system memory, obtaining sensor data from the sensing device indicative of the environment, and analyzing the sensor data using the sensing device model and the object model, thereby recognizing objects in the environment.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Image processing system

    JP2008052549A

  • Image processor and program

    JP2009037419A

  • MULTI-VIEW DEEP NEURAL NETWORK FOR LiDAR PERCEPTION

    JP2021089723A

  • Method and device for classifying objects

    US20210174133A1