Mobile Robot Vision Using Resized ROI and Dual-Bandpass Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional cleaning robots require multiple sensors for obstacle detection, positioning, and object recognition, leading to increased complexity and power consumption.

Innovation Solution

A mobile robot utilizing a single optical sensor with different light sources (laser diode and light emitting diode) to capture image frames for obstacle avoidance, visual simultaneous localization and mapping, and object recognition, reducing computation and power consumption by determining a region of interest and using a dual-bandpass filter for differential image processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple sensors are used for obstacle detection, positioning, and object recognition, then the robot's detecting functions are improved, but the device complexity and power consumption increase

Engineering Contradiction:
Improvedetecting functionsVSAvoidsensor quantity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies a single optical sensor to perform multiple detecting functions including obstacle detection, positioning, and object recognition by capturing different types of image frames (first image frame for obstacle detection, second image frame for positioning, third image frame for object recognition) under different lighting conditions, thereby eliminating the need for multiple separate sensors and reducing device complexity while maintaining versatile detecting capabilities

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If the size of the ROI is extended to integer times of predetermined size, then the recognition correctness is improved, but the computation loading increases

Engineering Contradiction:
Improverecognition correctnessVSAvoidcomputation loading
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extends the region of interest (ROI) to integer times of predetermined size when the original ROI size is not an integer multiple, incorporating adjacent pixel rows or columns to achieve the extended size. This partial extension approach ensures sufficient recognition correctness by maintaining the integer multiple relationship while avoiding unnecessary computation on excessively large regions, thus balancing recognition accuracy with computational efficiency

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution enables efficient obstacle detection, accurate positioning, and object recognition with reduced computational and power demands, enhancing the robot's functionality while optimizing resource usage.

Implementation Method 1

The mobile robot includes a linear light source, an optical sensor, a dual-bandpass filter and a processor. The dual-bandpass filter is arranged at a light incident path of the optical sensor.

Methodology Applied
Scientific EffectBandpass filter: Filter (optical)

Data Source

PatentUS20260043921A1Mobile robot generating resized region of interest in image frame and using dual-bandpass filter
Publication Date: 2026.02.12 PIXART IMAGING INC
  • US20260043921A1 patent drawing
  • US20260043921A1 patent drawing
  • US20260043921A1 patent drawing

AI summary

There is provided a mobile robot that performs the obstacle avoidance, positioning and object recognition according to image frames captured by the same optical sensor. The mobile robot includes an optical sensor, a light emitting diode, a laser diode and a processor. The processor identifies an obstacle and a distance thereof according to image frames captured by the optical sensor when the laser diode is emitting light. The processor further performs the positioning and object recognition according to image frames captured by the optical sensor when the light emitting diode is emitting light.