Tracking with multi-level features
This work addresses the problem of improving tracking accuracy in computer vision, though it appears incremental as it builds on existing tracking frameworks with a novel integration approach.
The paper tackled multiple object tracking by integrating low and mid-level features through a quadratic program formulation, achieving superior performance over classic tracking-by-detection and other greedy feature integration methods in evaluations across multiple scenarios.
We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features. In particular, we formulate the tracking problem as a quadratic program coupling detections and dense point trajectories. Due to the computational complexity of the initial QP, we propose an approximation by two auxiliary problems, a temporal and spatial association, where the temporal subproblem can be efficiently solved by a linear program and the spatial association by a clustering algorithm. The objective function of the QP is used in order to find the optimal number of clusters, where each cluster ideally represents one person. Evaluation is provided for multiple scenarios, showing the superiority of our method with respect to classic tracking-by-detection methods and also other methods that greedily integrate low-level features.