Out-of-Focus Video Frame Detection in Analytics Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video surveillance systems face challenges in distinguishing foreground objects due to out-of-focus video frames, which can lead to incorrect background modeling and impaired object recognition capabilities.
Innovation Solution
A method involving pyramid image decomposition and Haar wavelet transform to detect sharp and blurry edge areas in video frames, determining sharpness and blurriness values, and identifying out-of-focus frames to prevent incorrect background modeling and improve object recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If out-of-focus video frames are processed in the video surveillance system, then the system can maintain continuous operation, but the accuracy of foreground object detection and background modeling deteriorates
Solution Approach 1:
The system performs focus quality assessment on video frames before they are used for background modeling or foreground detection. By evaluating sharpness metrics and detecting out-of-focus conditions in advance, the system prevents degraded frames from entering the processing pipeline, thus maintaining detection accuracy while preserving continuous operation through automated frame rejection
Solution Approach 2:
A focus detection module acts as an intermediary between the video input and the background modeling/foreground detection processes. This intermediary assesses frame quality and controls the flow of frames to subsequent processing stages, ensuring that only in-focus frames are used for critical operations while maintaining system continuity
2Duration of action of stationary object
If out-of-focus frames are used for background modeling, then the system can update background information continuously, but the reliability of background subtraction and object detection deteriorates
Solution Approach 1:
The system evaluates frame focus quality before incorporating frames into background models. By checking sharpness metrics and detecting out-of-focus conditions in advance, the system prevents degraded frames from corrupting the background model, thus maintaining modeling continuity while ensuring update reliability through selective frame acceptance
Solution Approach 2:
The focus detection module provides feedback control to the background modeling process by identifying out-of-focus frames and preventing their use in model updates. This feedback mechanism ensures that only high-quality frames contribute to background model evolution, maintaining both continuity and reliability of the modeling process
Data Source
AI summary
Techniques are disclosed for detecting an out-of-focus camera in a video analytics system. In one embodiment, a preprocessor component performs a pyramid image decomposition on a video frame captured by a camera. The preprocessor further determines sharp edge areas, candidate blurry edge areas, and actual blurry edge areas, in each level of the pyramid image decomposition. Based on the sharp edge areas, the candidate blurry edge areas, and actual blurry edge areas, the preprocessor determines a sharpness value and a blurriness value which indicate the overall sharpness and blurriness of the video frame, respectively. Based on the sharpness value and the blurriness value, the preprocessor further determines whether the video frame is out-of-focus and whether to send the video frame to components of a computer vision engine and/or a machine learning engine.