Stationary Object Tracking via Partial Image Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing surveillance technologies face challenges in accurately tracking stationary individuals due to concealment by moving objects, leading to interrupted tracking and failure in crowded environments, and require additional equipment, making them impractical for general monitoring.
Innovation Solution
An image processing device that identifies moving and stationary regions in video frames, extracts features from non-overlapping regions, and uses these features for accurate verification of stationary objects, even when concealment occurs, without relying on new equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If feature extraction is performed from the entire region of a stationary object, then the feature extraction is simple, but tracking accuracy deteriorates when the stationary object is concealed by moving objects
Solution Approach 1:
The patent segments the stationary object region into multiple partial images, extracting features only from regions not overlapped by moving objects. This segmentation approach maintains tracking accuracy by avoiding concealed regions while keeping the extraction process systematic and manageable.
Solution Approach 2:
The patent applies local quality by selectively extracting features from specific partial regions of the stationary object that are not concealed, rather than uniformly processing the entire object. This ensures high-quality feature extraction from visible portions while ignoring obscured areas.
2Duration of action of stationary object
If tracking is performed by continuously capturing the stationary object, then tracking continuity is maintained, but additional equipment is required which increases device complexity
Solution Approach 1:
The patent makes the existing surveillance camera perform multiple functions by adding image processing capabilities to distinguish stationary objects from moving objects and to track stationary objects through partial image analysis, eliminating the need for specialized tracking equipment.
Solution Approach 2:
The system uses the surveillance camera's own captured images to track stationary objects by analyzing partial regions, making the system self-sufficient without requiring external or additional tracking devices.
3Productivity
If feature extraction is performed from regions overlapped by moving objects, then the feature extraction process is simple, but verification accuracy deteriorates due to interference from moving objects
Solution Approach 1:
The patent extracts and removes the influence of moving objects by identifying and excluding regions overlapped by moving objects from the feature extraction process, thereby obtaining pure features from the stationary object without interference.
Solution Approach 2:
The patent introduces an intermediary step of identifying moving object regions and creating a mask to separate stationary object features from moving object interference, allowing accurate feature extraction from non-overlapped regions.
Data Source
AI summary
Provided is a technique for extracting information with which it is possible to track an object to be tracked, even if it happens that the object to be tracked is hidden or the like. This image processing device is provided with: a moving region identification unit which identifies, in a video, the image region associated with a moving object shown in the video; a stationary region identification unit which identifies, in the video, the image region associated with a stationary object shown in the video; and an extraction unit which extracts a feature of a partial image that is included in the image region associated with the stationary object, and that does not overlap the image region associated with the moving object.