Object-Aware Bit Rate Control for Surveillance Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Surveillance systems face challenges in maintaining video quality and storage efficiency due to the limitations of existing variable bit rate techniques, which fail to account for specific objects of interest and their movement within video frames, leading to suboptimal encoding bit rates.
Innovation Solution
A storage system with a controller that identifies objects in video data using machine learning, determines their movement and type, and dynamically adjusts the encoding bit rate to improve video quality and storage efficiency by suggesting changes to the video capture device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If conventional variable bit rate techniques are used for video encoding, then storage efficiency is improved, but video quality of specific objects of interest deteriorates
Solution Approach 1:
The patent applies local quality by differentiating encoding treatment between different regions of the video frame. Specifically, the system identifies objects of interest (such as humans, animals, vehicles) and applies higher bit rates to regions containing these objects while using lower bit rates for background regions. This selective encoding approach maintains high video quality for important objects while reducing overall storage requirements, directly resolving the contradiction between storage efficiency and video quality.
Solution Approach 2:
The system dynamically changes encoding parameters (bit rate) based on the presence and movement characteristics of detected objects. When objects of interest are detected, the system adjusts the bit rate parameter upward for those specific regions; when no important objects are present, the bit rate is reduced. This dynamic parameter adjustment allows the system to optimize both storage efficiency and video quality adaptively.
2Manufacturing precision
If higher encoding bit rate is used to maintain video quality, then video quality is improved, but storage efficiency and network bandwidth utilization deteriorate
Solution Approach 1:
The system implements local quality enhancement by applying different bit rates to different spatial regions within the video frame. Regions containing objects of interest receive higher bit rates to preserve detail and quality, while empty or background regions use lower bit rates. This spatial differentiation allows the system to maintain high video quality where needed while minimizing overall storage and bandwidth consumption.
Solution Approach 2:
The system dynamically adjusts the encoding bit rate parameter based on real-time detection of objects and their movement characteristics. By changing the bit rate parameter adaptively - increasing it when objects of interest are present and decreasing it when they are absent - the system optimizes the trade-off between video quality and storage efficiency, avoiding the need to maintain high bit rates throughout the entire video stream.
3Manufacturing precision
If object detection and tracking is implemented to enable dynamic bit rate adjustment, then video quality for objects of interest is improved, but device complexity increases
Solution Approach 1:
The patent replaces complex mechanical or manual video quality adjustment mechanisms with automated electronic systems. Specifically, machine learning-based object detection algorithms automatically identify objects of interest, and electronic control systems automatically adjust encoding parameters based on detection results. This substitution of automated electronic control for manual or mechanical systems achieves high video quality while managing complexity through software-based solutions.
Solution Approach 2:
The system implements self-service by enabling the video encoding system to automatically detect objects, track their movement, and adjust bit rates without external intervention. The machine learning models continuously analyze video frames, identify objects of interest, and the encoding system autonomously adapts parameters in real-time. This self-adjusting capability improves video quality for important objects while reducing the need for complex external control systems.
Data Source
AI summary
A storage system and method for object monitoring/anticipation in surveillance systems are provided. In one embodiment, a storage system is provided comprising a memory and a controller. The controller is configured to identify positions of an object in a plurality of frames of video data provided by a video capture device; determine a rate of movement of the object based on the identified positions; and based on the determined rate of movement of the object, provide a suggestion to the video capture device to dynamically modify an encoding bit rate of the video data to improve video quality of the object. Other embodiments are provided.