Multi-Sensor Object Detection Circuitry With Low-Complexity Probability Fusion

Solution Overview

Problem

Existing object detection methods using multiple sensors require high processing complexity, leading to increased power consumption and costs, and often result in slow or deteriorated final detection due to the need for separate object detection for each sensor and subsequent data fusion, which can lose valuable information and reduce quality.

Innovation Solution

An object detection circuitry and method that combines first and second object probability data generated by comparing feature data from different sensors to their respective predetermined feature models, allowing for efficient fusion and detection of predefined objects while reducing complexity and maintaining reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If separate object detection is performed for each sensor followed by data fusion, then comprehensive object detection can be achieved, but processing complexity increases and detection speed decreases

Engineering Contradiction:

Improveobject detection reliabilityVSAvoidprocessing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges the object detection process by combining probability data from multiple sensors at the probability level rather than performing separate detections and fusing results. This is achieved by obtaining first and second probability data from different sensors, combining them to generate combined probability data, and detecting objects based on this combined data, thereby reducing processing complexity while maintaining detection reliability

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent performs preliminary probability data generation for each sensor before combining them. By obtaining probability data from multiple sensors in advance and combining these probability data to generate combined probability data, the system prepares all necessary information beforehand, reducing the complexity of real-time processing while ensuring comprehensive object detection

Inventive Principle:

Principle #10Preliminary action

2Reliability

If separate object detection is performed for each sensor followed by data fusion, then comprehensive object detection can be achieved, but detection speed decreases

Engineering Contradiction:

Improveobject detection reliabilityVSAvoiddetection speed

Core Design Contradiction:

ReliabilityVSSpeed

Solution Approach 1:

The patent merges the object detection process by combining probability data from multiple sensors at the probability level rather than performing separate detections and fusing results. This is achieved by obtaining first and second probability data from different sensors, combining them to generate combined probability data, and detecting objects based on this combined probability data, thereby reducing processing complexity while maintaining detection reliability

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent performs preliminary probability data generation for each sensor before combining them. By obtaining probability data from multiple sensors in advance and combining these probability data to generate combined probability data, the system prepares all necessary information beforehand, reducing the complexity of real-time processing while ensuring comprehensive object detection

Inventive Principle:

Principle #10Preliminary action

3Reliability

If separate object detection is performed for each sensor followed by data fusion, then comprehensive object detection can be achieved, but power consumption increases

Engineering Contradiction:

Improveobject detection reliabilityVSAvoidpower consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent merges the object detection process by combining probability data from multiple sensors at the probability level rather than performing separate detections and fusing results. This is achieved by obtaining first and second probability data from different sensors, combining them to generate combined probability data, and detecting objects based on this combined probability data, thereby reducing processing complexity while maintaining detection reliability

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent performs preliminary probability data generation for each sensor before combining them. By obtaining probability data from multiple sensors in advance and combining these probability data to generate combined probability data, the system prepares all necessary information beforehand, reducing the complexity of real-time processing while ensuring comprehensive object detection

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12380693B2Object detection circuitry and object detection method using combined probability data

Publication Date: 2025.08.05 SONY GROUP CORP

AI summary

The present disclosure generally pertains to an object detection circuitry configured to: obtain first feature data which are based on first sensing data of a first sensor; compare the first feature data to a first predetermined feature model being representative of a predefined object, wherein the first predetermined feature model is specific for the first sensor, thereby generating first object probability data; obtain second feature data which are based on second sensing data of a second sensor; compare the second feature data to a second predetermined feature model being representative of the predefined object, wherein the second predetermined feature model is specific for the second sensor, thereby generating second object probability data; and combine the first and the second object probability data, thereby generating combined probability data for detecting the predefined object.