Hybrid Object Tracking via Cost Function Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video analytics solutions for object tracking in images and videos face high computational complexity, making them unsuitable for embedded platforms, despite their need for accurate and efficient object tracking across frames.
Innovation Solution
A hybrid object tracking system that computes a cost function based on visual dissimilarity, physical distance, and expected location between objects in successive frames, using a processor and memory unit to store and select pairs of objects for accurate tracking, and employs a feature gallery for predicting and validating object positions across frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If online learning based strategies with discriminative classifier models are used for object tracking, then tracking accuracy is improved, but computational complexity increases making it unsuitable for embedded platforms
Solution Approach 1:
The patent segments the object tracking problem into two distinct parts: (1) object detection in the current frame, and (2) object association with previous frames. This segmentation allows each part to be solved with appropriately optimized algorithms, reducing overall computational complexity while maintaining tracking accuracy.
Solution Approach 2:
The patent introduces an intermediary cost matrix that serves as a bridge between object detection and tracking. The cost matrix computes association costs based on multiple features (appearance, position, size) and uses optimization algorithms (Hungarian algorithm, greedy approach) to find optimal matches. This intermediary structure enables accurate tracking without requiring complex continuous learning models.
2Measurement precision
If complex discriminative classifier models are continuously updated for tracking, then tracking precision is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary action by pre-computing the cost matrix using multiple features (appearance similarity, position difference, size difference) before performing the actual association. This pre-computation approach allows the system to make rapid matching decisions during tracking without continuous model updates, reducing processing time while maintaining precision.
Solution Approach 2:
The patent computes association costs based on multiple features (appearance, position, size) which may be more than strictly necessary (excessive action). However, this partial/excessive computation is performed in a optimized manner using the cost matrix structure, allowing the system to achieve high tracking precision without proportionally increasing processing time.
Data Source
AI summary
An embodiment of the present invention discloses an object tracking system for tracking objects across a first frame and a second frame of a video. The object tracking system comprises of a processor, a predictor, a non-transitory storage element coupled to the processor and encoded instructions stored in the non-transitory storage element. The encoded instructions when implemented by the processor, configure the object tracking system to detect a reference object in a received first video and/or image frame (v/i) based on a pre-defined feature-based characteristic via the object tracking unit.