Abstract
The large shape variability and partial occlusions challenge most object detection and tracking methods for nonrigid targets such as pedestrians. This paper presents a new approach based on a two-layer statistical field model that characterizes the prior of the complex shape variations as a Boltzmann distribution and embeds this prior and the complex image likelihood into a Markov field. A probabilistic variational analysis of this model reveals a set of fixed-point equations characterizing the equilibrium of the field. It leads to computationally efficient methods for calculating the image likelihood and for training the model. Based on that, effective algorithms for detecting nonrigid objects are developed. This new approach has several advantages. First, it is intrinsically suitable for capturing local nonrigidity. In addition, due to the distributed likelihood, this approach is robust to partial occlusions. Moreover, the two-layer structure provides large flexibility of modeling the image observations, which makes the new method robust to clutters. Extensive experiments demonstrate its effectiveness.
Original language | English (US) |
---|---|
Pages (from-to) | 753-765 |
Number of pages | 13 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 28 |
Issue number | 5 |
DOIs | |
State | Published - May 2006 |
Funding
This work was supported in part by US National Science Foundation (NSF) Grant IIS-0308222, IIS-0347877 (CAREER), Northwestern startup funds, and the Murphy Fellowships. The authors also greatly thank the reviewers for the constructive comments and suggestions.
Keywords
- Image models
- Machine learning
- Markov random fields
- Object detection
- Probabilistic algorithms
- Shape
- Statistical computing
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics