Warped Object Imaging for Accurate Floor Object Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic apparatuses face challenges in maintaining consistent object recognition accuracy due to varying camera angles and distances, particularly struggling with objects captured at long distances or on the floor, leading to low recognition rates.
Innovation Solution
The apparatus includes a sensor, camera, and processor with an AI model that detects objects, identifies floor objects, and warps object regions based on distance information to correct distortions, allowing for accurate identification by the AI model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the camera captures objects at long distance or from low position, then the coverage area increases, but the object recognition accuracy decreases
Solution Approach 1:
The system performs preliminary warping of the object region based on distance information before inputting it to the AI model. This preliminary correction of perspective distortion ensures that the AI model receives properly proportioned object images, thereby maintaining high recognition accuracy even when objects are captured at long distances or from low positions
Solution Approach 2:
The system changes the geometric parameters of the object region by warping it according to distance information. This parameter transformation corrects the perspective distortion caused by long-distance or low-position capture, enabling the AI model to accurately recognize objects regardless of capture conditions
2Measurement precision
If high-resolution camera is used to improve object recognition, then the recognition accuracy for distant objects improves, but the device complexity and cost increase
Solution Approach 1:
The system replaces the mechanical solution of using higher-resolution cameras with a computational solution. By warping the object region based on distance information and using AI processing, the system achieves improved recognition accuracy for distant objects without requiring more complex or expensive camera hardware
3Area of stationary object
If the image is divided into multiple regions for recognition, then the recognition coverage improves, but the computation amount and processing time increase
Solution Approach 1:
The system extracts only the relevant object region from the entire image for warping and AI processing, rather than processing the whole image or dividing it into multiple regions. This extraction approach maintains comprehensive recognition coverage while significantly reducing the computation amount and improving processing speed
Data Source
AI summary
An electronic apparatus is provided. The electronic apparatus includes: a sensor; a camera; a memory; and a processor configured to be connected to the sensor, the camera, and the memory. The memory includes an artificial intelligence model trained to identify at least one object. The processor is further configured to: detect an object based on sensing data received from the sensor; based on the detected object being identified as having a height less than a predetermined threshold value, warp an object region, including the detected object, in an image acquired through the camera based on distance information of the object region; and identify the detected object by inputting the warped object region into the artificial intelligence model.