Wearable Object Outlining for Visual Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented-reality devices struggle to efficiently identify and search for specific objects in a user's environment, leading to unnecessary computational resources being expended on irrelevant searches.
Innovation Solution
A wearable computing device and server system that detects a user's movement defining an outline of an area through video data, identifies objects within that area, and initiates a targeted search using edge detection and segmentation techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the device performs comprehensive object searches across the entire field of view, then the completeness of object detection is improved, but the computational resources and time required increase significantly
Solution Approach 1:
The system segments the field of view into multiple regions of interest based on detected movements or user gaze patterns. Instead of searching the entire field of view uniformly, computational resources are concentrated on specific segments where objects are more likely to be located, thereby reducing overall search time while maintaining detection completeness.
Solution Approach 2:
The system performs preliminary actions by detecting movements and pre-identifying potential regions of interest before initiating the actual object search. This preliminary segmentation and prioritization of search areas allows the system to prepare search strategies in advance, reducing the time required for comprehensive object detection when needed.
2Measurement precision
If the device searches the entire field of view for objects, then the accuracy of object identification is improved, but the computational energy consumption increases
Solution Approach 1:
The system applies local quality by allocating higher computational resources and more sophisticated analysis algorithms to specific regions of interest rather than uniformly across the entire field of view. Areas with detected movements or user attention receive enhanced processing for accurate object identification, while other areas use lighter processing, thereby reducing overall energy consumption while maintaining identification accuracy where needed.
Solution Approach 2:
The system performs partial action by conducting detailed object identification only in regions where movements are detected or where objects are most likely to be present. Instead of applying full computational power to the entire field of view, the system applies excessive processing only to relevant segments, reducing overall energy consumption while maintaining sufficient accuracy for the identified objects.
3Speed
If the device processes all video data in real-time, then the responsiveness of the augmented-reality experience is improved, but the device complexity and processing requirements increase
Solution Approach 1:
The system segments video data processing into multiple stages and regions. Instead of processing all video data uniformly at full resolution, the system divides the field of view into regions of interest and processes only those segments in real-time with high detail, while other areas receive reduced processing. This segmentation enables real-time responsiveness while reducing overall computational complexity.
Solution Approach 2:
The system applies partial action by processing video data at full detail only for regions where movements are detected or where user attention is focused. Other regions receive reduced processing or are processed asynchronously. This approach maintains real-time responsiveness for critical areas while reducing the overall processing requirements and device complexity.
Data Source
AI summary
Methods and devices for initiating a search of an object are disclosed. In one embodiment, a method is disclosed that includes receiving sensor data from a sensor on a wearable computing device and, based on the sensor data, detecting a movement that defines an outline of an area in the sensor data. The method further includes identifying an object that is located in the area and initiating a search on the object. In another embodiment, a server is disclosed that includes an interface configured to receive sensor data from a sensor on a wearable computing device, at least one processor, and data storage comprising instructions executable by the at least one processor to detect, based on the sensor data, a movement that defines an outline of an area in the sensor data, identify an object that is located in the area, and initiate a search on the object.