Audio Guide Landmark Recognition for Accessible Voice Descriptions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current audio guides are not user-friendly for individuals with vision loss, as they rely on visual inputs like numbers, barcodes, or QR codes, and lack customization options for information detail levels.
Innovation Solution
An audio guide system using a portable device with an imaging sensor, beacons, and a computing infrastructure that identifies landmarks via image capture and comparison to reference images, generates audio descriptions through a large language model, and adapts to user preferences for detail and interest levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If current audio guides use visual inputs like numbers, barcodes, or QR codes for identification, then the system can provide audio descriptions, but the system becomes unusable for people experiencing vision loss
Solution Approach 1:
The patent replaces visual identification mechanisms (barcodes, QR codes, numbers) with an imaging sensor that captures images of points of interest. The system then uses image processing and comparison algorithms to automatically identify landmarks, substituting manual visual input with automated visual capture and processing.
Solution Approach 2:
The system enables self-service operation where the imaging sensor automatically captures images and the processing circuitry automatically compares them against stored reference images to identify points of interest. This eliminates the need for user intervention in the identification process, making the system accessible to visually impaired users.
2Adaptability or versatility
If audio guides use a one-size-fits-all approach for information delivery, then the system is simple to operate, but it does not provide customization for users to control the level of detail
Solution Approach 1:
The patent implements dynamic adaptability by allowing the system to adjust its information delivery based on user preferences. Users can control the level of detail and types of information received, and the system dynamically modifies its output accordingly. This is achieved through configurable parameters that adjust the processing and delivery of audio descriptions.
Solution Approach 2:
The system changes operational parameters related to information detail and type based on user preferences. The processing circuitry can adjust the amount of processing applied to images and the level of detail included in audio descriptions, allowing customization without fundamentally changing the system architecture.
3Ease of operation
If the system captures and processes images to identify landmarks automatically, then accessibility for visually impaired users is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent stores reference images of points of interest in advance within the system. When an image is captured, the processing circuitry compares it against these pre-stored references, eliminating the need for real-time database queries or complex AI processing. This preliminary preparation significantly reduces processing time during actual use.
Solution Approach 2:
The system uses image copying and comparison techniques where captured images are compared against stored reference images. This approach allows for rapid identification by matching visual patterns without requiring complex computational analysis, reducing processing time while maintaining accuracy.
Data Source
AI summary
A method of providing audio descriptions of landmarks includes causing a user device to capture an image via an imaging sensor of the user device, comparing the captured image to a reference image to identify a landmark that appears in the captured image, providing a prompt requesting a description associated with the identified landmark to a large language model (LLM), receiving an audio file of the description associated with the identified landmark, and providing the audio file of the description associated with the identified landmark to the one or more user devices.