Detecting Multiple Objects Using Boosting Conditional Random Field

The contextual information is exploited to detect and localize multiple object categories in an image. The context model incorporates global image features, dependencies among object categories and output of local detectors into one probabilistic framework. The performance benefit of context models has been limited because Markov Random Field technique was tested on data sets with only a few object categories. The Sun 09 dataset is used with images that contain many instances of different object categories. The coherent structure among object categories models the object co-occurrences and spatial relationships using tree structured graphical model. The context model and spatial relationship improves object recognition performance and provides coherent interpretation of scene, enables reliable image querying system by multiple object categories. Boosted Random Field (BRF) technique is introduced to combine both Boosting and Conditional Random Field for improving the accuracy and speed. BRF provides better performance and requires fewer computations. BRF searches objects in an image and detects stuff things in an office.