IPST: Incremental Pictorial Structures for Model-free Tracking of Deformable Objects
Autor: | Epameinondas Antonakos, Grigorios Chrysos, Stefanos Zafeiriou |
---|---|
Rok vydání: | 2018 |
Předmět: |
Computer science
business.industry Frame (networking) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Tracking (particle physics) Object (computer science) 01 natural sciences Computer Graphics and Computer-Aided Design Task (project management) Generative model Discriminative model Minimum bounding box 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence 010306 general physics business Software |
Zdroj: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 27(7) |
ISSN: | 1941-0042 |
Popis: | Model-free tracking is a well-studied task in computer vision. Typically, a rectangular bounding box containing a single object is provided in the first (few) frame(s) and then the method tracks the object in the rest frames. However, for deformable objects (e.g. faces, bodies) the single bounding box scenario is suboptimal; a part-based approach would be more effective. The current state-of-the-art part-based approach is incrementally trained discriminative deformable part models (DPM). Nevertheless, training discriminative DPMs with one or a few examples poses a huge challenge. We argue that a generative model is a better fit for the task. To that end, we utilize the powerful pictorial structures, which we augment with incremental updates to account for object adaptations. Our proposed incremental pictorial structures, which we call incremental pictorial structures for model-free tracking (IPST), are experimentally validated in different scenarios. In a thorough experimentation we demonstrate that IPST outperforms the existing model-free methods in facial landmark tracking, body tracking, and animal tracking (newly introduced to verify the strength in ad hoc cases). |
Databáze: | OpenAIRE |
Externí odkaz: |