Adjusting Camera Image Capture Region via Spoken Demonstrative Pronouns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices with fixed camera image capture regions are limited in capturing wider areas or objects beyond the preset view, restricting the services they can provide to users.
Innovation Solution
An information processing method and apparatus that adjust the image capture region based on demonstrative pronouns in user utterances, determining the appropriate angle of view and light intensity for the camera to scan and recognize targets indicated by the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the camera uses a fixed image capture region with preset angle of view, then the camera structure is simple and easy to control, but the capture area is limited and cannot capture wider regions or objects beyond the fixed region
Solution Approach 1:
The patent applies the dynamics principle by making the camera's image capture region adjustable rather than fixed. The system dynamically changes the camera's scanning region based on the detected target object and the user's spoken utterance, allowing the capture area to adapt to different scenarios while maintaining manageable system complexity through automated control.
Solution Approach 2:
The patent changes the parameter of the image capture region (position, size, angle of view) based on the type of target object detected. Different parameters are selected according to the object category (e.g., person, vehicle, animal), enabling the system to capture appropriate regions for various targets without requiring manual intervention.
2Reliability
If the camera scans the entire possible region to ensure complete coverage, then no target is missed, but the processing time and power consumption increase significantly
Solution Approach 1:
The system performs preliminary actions by first receiving the user's spoken utterance and detecting the target object before initiating the camera scan. The image capture region is pre-determined based on the utterance and detected target, so the camera only scans the relevant area rather than the entire possible region, reducing processing time while maintaining recognition accuracy.
Solution Approach 2:
The patent extracts only the necessary portion of the image capture region based on the user's utterance and detected target. Instead of processing the entire possible scan area, the system extracts and processes only the relevant region where the target is likely to be located, significantly reducing processing time and power consumption while maintaining reliable target recognition.
3Productivity
If the camera adjusts the image capture region based on spoken utterance and target detection, then processing time and power consumption are reduced, but the system complexity and control difficulty increase
Solution Approach 1:
The system performs self-service by automatically adjusting the image capture region based on the user's spoken utterance and detected target object. The system independently determines the appropriate scan region without requiring manual control or complex user input, reducing processing time and power consumption while keeping the control mechanism straightforward through automated decision-making.
4Adaptability or versatility
If the camera uses a fixed angle of view, then the optical system is simple and stable, but the angle of view cannot be adjusted to capture different distances or regions
Solution Approach 1:
The patent applies dynamics by making the angle of view adjustable rather than fixed. The system dynamically changes the scanning angle based on the detected target object and user utterance, allowing the camera to adapt to different capture requirements (e.g., close-up, wide-angle, distant objects) while maintaining optical system simplicity through automated parameter adjustment.
Data Source
AI summary
Disclosed are an information processing method and information processing apparatus which execute an installed artificial intelligence (AI) algorithm and/or machine learning algorithm to process a spoken utterance of a user in a 5G communication environment. The information processing method according to an embodiment of the present disclosure may include receiving a spoken utterance of a user and extracting, from the spoken utterance, a demonstrative pronoun referring to a target indicated by the user, determining an image capture region to be scanned by a camera according to the type of the demonstrative pronoun, recognizing the target indicated by the user from a result of scanning the image capture region, and feeding back a result of processing the spoken utterance to the user on the basis of a result of recognizing the target indicated by the user.