Unsupervised Detection and Tracking of Arbitrary Objects with Dependent Dirichlet Process Mixtures
This provides a general framework for video analysis that reduces the need for object-specific methods, though it appears incremental as it builds on existing Dirichlet process techniques.
The paper tackles the problem of unsupervised detection and tracking of arbitrary objects in videos, proposing a dependent Dirichlet process mixture model that achieves detection and tracking across diverse objects, backgrounds, and occlusions without modification.
This paper proposes a technique for the unsupervised detection and tracking of arbitrary objects in videos. It is intended to reduce the need for detection and localization methods tailored to specific object types and serve as a general framework applicable to videos with varied objects, backgrounds, and image qualities. The technique uses a dependent Dirichlet process mixture (DDPM) known as the Generalized Polya Urn (GPUDDPM) to model image pixel data that can be easily and efficiently extracted from the regions in a video that represent objects. This paper describes a specific implementation of the model using spatial and color pixel data extracted via frame differencing and gives two algorithms for performing inference in the model to accomplish detection and tracking. This technique is demonstrated on multiple synthetic and benchmark video datasets that illustrate its ability to, without modification, detect and track objects with diverse physical characteristics moving over non-uniform backgrounds and through occlusion.