Imaging Main Object Determination Across Frames with Lower Processing Load
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing imaging technologies face high processing loads when simultaneously tracking multiple objects, making it difficult to accurately determine a main object that aligns with user intent.
Innovation Solution
An apparatus and method for determining a main object using image acquisition, selection based on feature points, and user input to identify and switch main objects, reducing processing load by matching candidates across multiple frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If simultaneous tracking of multiple objects using recurrent neural network is implemented, then object detection capability is improved, but processing load becomes too high for hardware implementation
Solution Approach 1:
The patent segments the object tracking task by selecting only one main object candidate from multiple detected objects based on feature point information, rather than simultaneously tracking all objects. This segmentation reduces the processing load while maintaining detection capability for the most relevant object.
Solution Approach 2:
The patent extracts only the necessary information (feature points and feature amounts) from detected objects to identify the main object candidate, rather than processing complete object data. This extraction approach maintains detection accuracy while reducing computational complexity.
2Measurement precision
If feature point information is used to select main object candidates, then main object determination accuracy is improved, but processing time increases due to multiple frame comparisons
Solution Approach 1:
The patent performs preliminary selection of main object candidates using feature point information from the current frame before conducting temporal consistency checks. This preliminary action narrows down the candidates, making subsequent verification faster and more accurate.
Solution Approach 2:
The patent compares feature amounts across multiple frames to determine temporal consistency of main object candidates. By copying and comparing only the essential feature amounts rather than full object data, the system maintains accuracy while reducing processing time.
Data Source
AI summary
A main object determination apparatus includes an image acquisition unit configured to acquire images captured at different timings, a selection unit configured to select main object candidate(s) from objects in the images, a determination unit configured to determine whether the main object candidate(s) each selected at the respective different timings are the same, and an input unit configured to receive an operation. In a case where the determination unit determines that the main object candidate(s) selected by the selection unit in an image of interest and one or more images captured within a predetermined time before the image of interest is captured are the same, the determination unit determines the main object candidate(s) to be a main object. In a case where the input unit receives an instruction to specify a new main object, the determination unit switches the main object according to the instruction.