2D IR Camera Depth Sensing for Portable Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional three-dimensional depth cameras are expensive and consume significant computational resources and power, making them unsuitable for portable devices like laptops, tablets, and smartphones.
Innovation Solution
A two-dimensional infrared (IR) camera is used to estimate depth by projecting IR light and measuring its intensity, allowing for three-dimensional depth sensing without the need for time-of-flight, structured light, or stereo camera approaches, enabling the derivation of a skeletal hand model based on IR parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional three-dimensional depth cameras are used, then depth sensing capability is achieved, but device cost and power consumption increase significantly
Solution Approach 1:
The patent replaces complex mechanical depth sensing systems (time-of-flight cameras, structured light systems, stereo cameras) with a simpler infrared intensity-based depth estimation system. Instead of using active illumination or multiple camera views, the system uses a single IR camera to capture intensity variations and estimate depth through computational methods, thereby reducing power consumption and device complexity while maintaining depth sensing capability
Solution Approach 2:
The patent changes the measurement parameter from direct depth measurement (using time-of-flight or structured light) to indirect depth estimation through infrared intensity analysis. By capturing IR intensity values and applying computational models to infer depth information, the system achieves depth sensing with lower power consumption and reduced hardware requirements
2Measurement precision
If conventional three-dimensional depth cameras are used, then depth sensing capability is achieved, but device cost increases
Solution Approach 1:
The patent employs inexpensive infrared cameras and standard processing hardware instead of expensive specialized depth sensing equipment. By using commercially available IR camera modules and implementing software-based depth estimation algorithms, the system achieves cost-effective depth sensing suitable for mass production in portable devices
Solution Approach 2:
The patent replaces expensive mechanical depth sensing hardware (time-of-flight sensors, structured light projectors, stereo camera assemblies) with a simpler infrared intensity analysis system. This substitution dramatically reduces bill of materials cost while maintaining acceptable depth estimation accuracy for gesture recognition applications
3Measurement precision
If conventional three-dimensional depth cameras are used, then depth sensing capability is achieved, but computational resource consumption increases
Solution Approach 1:
The patent replaces computationally intensive active depth sensing mechanisms (phase unwrapping in time-of-flight, pattern decoding in structured light, stereo matching algorithms) with simpler infrared intensity-based depth estimation. The computational model uses IR intensity values and pre-established relationships to infer depth, requiring significantly fewer processing resources while achieving sufficient accuracy for gesture recognition
Solution Approach 2:
The patent applies partial depth estimation by focusing computational effort only on regions containing hand gestures rather than processing the entire image frame. By identifying hand regions first and then estimating depth only for those areas, the system reduces overall computational load while maintaining depth sensing capability where needed
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
This method reduces the financial, computational, and power costs associated with traditional 3D depth cameras, making it suitable for small form-factor devices while still enabling effective three-dimensional gesture recognition.
Implementation Method 1
a two-dimensional infrared (IR) camera is used to estimate depth by projecting IR light and measuring its intensity
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A signal encoding an infrared (IR) image including a plurality of IR pixels is received from an IR camera. Each IR pixel specifies one or more IR parameters of that IR pixel. IR-skin pixels that image a human hand are identified in the IR image. For each IR-skin pixel, a depth of a human hand portion imaged by that IR-skin pixel is estimated based on the IR parameters of that IR-skin pixel. A skeletal hand model including a plurality of hand joints is derived. Each hand joint is defined with three independent position coordinates inferred from the estimated depths of each human hand portion.