Hand Tremor Motion Detection Using Adaptive Block Distance Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion detection methods for portable devices, such as cellular phones, face challenges in achieving high detection speed and precision for user hand tremor or intentional motion, particularly in applications like character recognition, where conventional methods either sacrifice speed for precision or vice versa.
Innovation Solution
A method and apparatus that utilize edge detection, block distance calculation, and adaptive neighborhood block search to differentiate between hand tremor and intentional motion by comparing block distances with predefined thresholds, incorporating a motion vector extractor and determiner to enhance detection speed and precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If larger-sized blocks are used for motion detection, then detection precision is improved, but detection speed decreases
Solution Approach 1:
The patent divides the image into multiple blocks of different sizes and performs motion detection on each block type. By segmenting the detection task across multiple block sizes (small, medium, large blocks), the system can use small blocks for fast initial detection and large blocks for precise final detection, thereby resolving the contradiction between speed and precision.
Solution Approach 2:
The patent performs preliminary motion detection using small-sized blocks first to quickly identify regions with motion. This preliminary action filters out areas without motion before proceeding to more computationally intensive detection on larger blocks, thus maintaining high speed while achieving precision where needed.
2Productivity
If smaller-sized blocks are used for motion detection, then detection speed is improved, but detection precision decreases
Solution Approach 1:
The patent segments the detection process into multiple stages using different block sizes. Small blocks are used for initial fast scanning, medium blocks for intermediate detection, and large blocks for final precise detection. This segmentation allows the system to achieve both speed and precision by applying the appropriate block size at each detection stage.
Solution Approach 2:
The patent applies partial action by performing detailed motion detection only on blocks that show motion in preliminary detection. Instead of applying full detection to the entire image with large blocks, it uses small blocks for initial screening and only applies larger block detection where necessary, thus improving speed while maintaining precision.
3Productivity
If conventional block matching methods are used, then detection speed is maintained, but detection precision in interest regions is insufficient
Solution Approach 1:
The patent applies different detection strategies to different regions of the image. In interest regions (such as regions containing text or important objects), it uses larger blocks and more precise matching methods. In non-interest regions, it uses smaller blocks and faster detection methods. This local quality approach ensures high precision where needed while maintaining overall detection speed.
Solution Approach 2:
The patent performs preliminary detection using fast block matching methods across the entire image to identify regions with motion. Once motion regions are identified, particularly in interest areas, it then applies more precise detection methods to those specific regions. This preliminary action allows the system to maintain high speed overall while achieving high precision in critical areas.
Data Source
AI summary
A method is provided for determining presence of a user's hand tremor or intentional motion during recognition of an image through photographing. Image sample blocks of a previous frame are detected by using an edge detecting method. A block distance between the detected image sample block of the previous frame and an estimated image sample block of a current frame is calculated. The calculated block distance is compared with a first threshold. The calculated block distance is compared with a second threshold when the calculated block distance is less than the first threshold.