Object Detection in Video Streams via Region Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing optical input systems for electronic devices, such as cameras monitoring hand and finger motions, are limited by the need for a fixed background, making them unsuitable for handheld devices like PDAs, mobile phones, and digital cameras, where the background is not constant.
Innovation Solution
A system that partitions video streams into regions of interest, using statistical analysis and pattern recognition to detect and track objects without edge detection, allowing for object detection and tracking in moving devices, and enabling the execution of OS commands based on recognized motion patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed camera position is used to enable background-based object detection, then detection reliability is improved, but device mobility is restricted
Solution Approach 1:
The system dynamically adapts to changing backgrounds by continuously analyzing video frames and adjusting detection parameters. Instead of relying on a static background, the system uses motion detection algorithms that identify objects based on their movement patterns relative to the dynamic environment, enabling reliable detection in mobile devices.
Solution Approach 2:
The system changes detection parameters adaptively based on environmental conditions. By adjusting sensitivity thresholds, detection windows, and motion analysis parameters according to the current scene characteristics, the system maintains high detection reliability whether the device is stationary or moving, thus resolving the contradiction between reliability and mobility.
2Measurement precision
If edge detection methods are used for object detection, then detection precision is improved, but computational complexity increases
Solution Approach 1:
The system segments the video stream into multiple frames and further divides each frame into regions of interest. By processing smaller segmented regions rather than entire frames, the computational complexity is reduced while maintaining detection precision through focused analysis of relevant areas.
Solution Approach 2:
The system applies detection algorithms only to specific regions where motion is detected or where objects are likely to be present, rather than analyzing every pixel in every frame. This partial action approach reduces computational load while maintaining sufficient detection precision for the application's needs.
Data Source
AI summary
Provided is a system and method for object detection and tracking in a video stream. Frames of the video stream are divided into regions of interest and a probability that the region contains at least a portion of an object to be tracked is calculated for each region of interest. The regions of interest in each frame are then classified based on the calculated probabilities. A region of interest (RI) frame is then constructed for each video frame that reports the classification of regions of interest in the video frame. Two or more RI frames are then compared in order to determine a motion of the object. Also provided is a system executing the presently described method, as well as a device including the system. The device may be for example, a portable computer, a mobile telephone, or an entertainment device.