Motion Detection Using Multi-Frame Correlation Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video surveillance systems face challenges in accurately detecting motion due to noise, errors, and changes in environmental illumination, leading to incorrect detection of moving objects and frequent false alarms.
Innovation Solution
A motion detection scheme that compares a current frame with reference frames to determine correlation, using a threshold-based approach to differentiate between motion and noise or illumination changes, and considers multiple frames to confirm the presence of an object, thereby reducing false positives and improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single frame is compared with reference frame to detect motion, then the detection speed is fast, but the detection accuracy is low due to noise and illumination changes
Solution Approach 1:
The patent segments the motion detection process into multiple independent comparison stages. Instead of making a single determination from one frame, the system divides the detection into: (1) comparing current frame with reference frame, (2) comparing previous frame with its reference frame, and (3) making a final determination only when both comparisons indicate motion. This segmentation allows the system to maintain high accuracy while managing complexity through modular processing steps.
Solution Approach 2:
The patent applies preliminary action by performing an initial comparison between the current frame and reference frame before making the final motion detection determination. This first comparison serves as a preliminary filter that identifies potential motion, which then triggers a second comparison with the previous frame. Only when both preliminary comparisons confirm motion does the system make the final detection, thereby improving accuracy through preliminary verification steps.
2Reliability
If multiple frames are compared to confirm motion, then the false alarm rate is reduced, but the detection time is increased
Solution Approach 1:
The patent applies dynamics by making the detection process adaptive rather than static. The system dynamically adjusts the number of frames to compare based on the initial comparison result. When the first frame comparison shows no significant motion, the process terminates early, avoiding unnecessary time consumption. Only when motion is detected does the system proceed to compare additional frames, thereby maintaining high reliability while minimizing detection time through dynamic process adjustment.
Solution Approach 2:
The patent applies local quality by applying different processing depths to different detection scenarios. For frames showing no motion, the system performs minimal processing (single comparison). For frames showing potential motion, the system performs deeper processing (multiple comparisons). This localized quality adjustment ensures that time is invested only where necessary, maintaining high reliability for actual motion detection while minimizing time loss for static scenes.
3Productivity
If threshold-based comparison is used, then the processing speed is fast, but the detection accuracy deteriorates under varying illumination conditions
Solution Approach 1:
The patent applies feedback by using the result of the first frame comparison to control the execution of the second comparison. The system calculates a difference metric for the current frame versus reference frame, then uses this result as feedback to determine whether to proceed with comparing the previous frame. This feedback mechanism allows the system to maintain fast processing speed by skipping unnecessary comparisons while improving precision by triggering additional verification only when the initial feedback indicates potential motion.
Solution Approach 2:
The patent introduces an intermediary comparison step that mediates between the initial fast comparison and the final motion determination. The first frame comparison acts as an intermediary that quickly filters out obvious non-motion cases, while the second comparison serves as another intermediary layer for verification. This multi-layer intermediary approach maintains processing speed by avoiding direct complex analysis in all cases while improving precision through intermediate verification steps.
Data Source
AI summary
In implementations of the subject matter described herein, a current captured frame of a video is compared with a respective reference frame to determine a correlation therebetween. The correlation is used to indicate a change degree of the current frame. If the correlation for the current frame is below a predetermined threshold, the current frame may not be directly determined as including a motion of an object. Instead, correlations between one or more frames before or after the current frame and their respective reference frames are took into account. If the correlations of the frames under consideration are below the predetermined threshold, it may be detected that the current frame includes a motion of an object. In this way, incorrect detection of the object motion is reduced in the cases when larger changes in frames of a video are caused by factors such as noise and error, and the accuracy of the object motion detection is improved.