Electronic product performing multiple detections using image frames of same optical sensor
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cleaning robots require multiple sensors to perform obstacle avoidance, positioning, and object recognition, leading to high computation loading, power consumption, and low recognition correctness.
Innovation Solution
A mobile robot utilizing a single optical sensor with different light sources activated at various times to capture image frames, enabling obstacle avoidance, visual simultaneous localization and mapping (VSLAM), and object recognition, while reducing computation and power consumption by identifying regions of interest and using a learning model for object type recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensors are used to perform obstacle avoidance, positioning, and object recognition, then detection functions are improved, but device complexity and cost increase
Solution Approach 1:
The patent applies multi-functionality by enabling a single optical sensor to perform multiple detection functions (obstacle avoidance, positioning, object recognition) by capturing image frames under different lighting conditions. The sensor alternates between capturing frames with laser illumination for obstacle detection and frames with ambient or LED illumination for positioning and recognition, eliminating the need for separate specialized sensors.
Solution Approach 2:
The patent merges multiple detection functions into a single optical sensor system. By combining obstacle avoidance, positioning, and object recognition capabilities into one sensor that operates under different lighting conditions, the system reduces component count while maintaining comprehensive detection functionality.
2Reliability
If multiple sensors and processing functions are implemented, then detection capabilities are improved, but power consumption increases
Solution Approach 1:
The patent implements periodic action by alternating the optical sensor between different capture modes. The sensor periodically switches between capturing frames under laser illumination for obstacle avoidance and frames under ambient or LED illumination for positioning and object recognition. This time-division multiplexing approach allows a single sensor to perform multiple functions sequentially, reducing overall power consumption compared to running multiple sensors simultaneously.
Solution Approach 2:
By making the single optical sensor universal and capable of performing multiple detection functions through different lighting conditions, the system eliminates the need for multiple dedicated sensors that would consume more power simultaneously. The sensor adapts its capture mode based on the required function, optimizing energy usage.
3Measurement precision
If multiple sensors are used for different detection functions, then detection accuracy is improved, but computation loading increases
Solution Approach 1:
The patent makes a single optical sensor universal by processing its captured frames for multiple detection purposes. The same sensor data is utilized for obstacle avoidance, positioning, and object recognition through different processing algorithms applied to frames captured under different lighting conditions, reducing computational overhead compared to processing data from multiple separate sensors.
Solution Approach 2:
The patent merges multiple detection processing tasks into a unified computational framework that processes images from a single optical sensor. By combining obstacle detection, positioning, and object recognition processing into one system that operates on shared sensor data, the overall computational loading is reduced compared to independent processing pipelines for multiple sensors.
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 allows for multiple detecting functions with a single sensor, reducing computational and power requirements while improving recognition accuracy by leveraging different light sources for range estimation, VSLAM, and object identification.
Implementation Method 1
a laser diode is emitting light
Implementation Method 2
a light emitting diode is emitting light
Implementation Method 3
the optical sensor corresponding to lighting of different light sources
Data Source
AI summary
There is provided an electronic product that performs the obstacle avoidance, positioning and object recognition according to image frames captured by the same optical sensor. The electronic product 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.