Depth Estimation Using Object Bottom Position and Pitch Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining object distance, such as stereoscopic cameras and structured light projection, often require specialized imaging hardware not available on all computing devices, and may not accurately account for camera pitch angles, leading to errors in depth estimation.
Innovation Solution
A method using image data from a camera to calculate the object bottom ratio and apply a distance projection model, which compensates for camera pitch by adjusting the object bottom ratio with an offset, allowing for accurate distance estimation on devices without stereoscopic capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If stereoscopic cameras or structured light projectors are used to determine object distance, then measurement precision is improved, but device complexity increases due to specialized imaging hardware
Solution Approach 1:
The patent extracts the essential depth information from a single 2D image by identifying the bottom position of objects and using geometric relationships with the ground plane, eliminating the need for stereoscopic cameras or structured light projectors while maintaining measurement capability
Solution Approach 2:
The method uses the ground plane itself as a reference for depth measurement, leveraging the natural geometry of the environment (camera height above ground, object bottom contact with ground) to compute distances without requiring additional specialized hardware
2Device complexity
If traditional single-camera depth estimation is used without pitch compensation, then device complexity remains low, but measurement precision deteriorates due to inaccurate depth estimates
Solution Approach 1:
The patent introduces pitch angle as a compensating parameter, adjusting the object bottom ratio calculation based on the camera's orientation relative to the ground plane, thereby maintaining accuracy across varying camera orientations without adding complex hardware
Data Source
AI summary
A method may include receiving, from a camera, image data representing an object in an environment and determining, based on the image data, a vertical position within the image data of a bottom of the object. The method may also include determining an object bottom ratio between the vertical position and a height of the image data and determining, by way of a distance projection model and based on the object bottom ratio, an estimate of a physical distance between the camera and the object. The distance projection model may define, for each respective candidate object bottom ratio of a plurality of candidate object bottom ratios, a mapping between (i) the respective candidate object bottom ratio and (ii) a corresponding physical distance in the environment. The method may additionally include generating an indication of the estimate of the physical distance between the camera and the object.