Combined Object Categorization and Segmentation With an Implicit Shape Model

TLDR

The field generally assumes no prior figure‑ground segmentation before recognition, yet our approach automatically segments objects during categorization. We propose a method for object categorization in real‑world scenes. By integrating recognition and segmentation into a single probabilistic Implicit Shape Model, the method generates per‑pixel confidence maps, extends to multiple objects with an MDL‑based ambiguity resolution, and is evaluated on a standard car‑detection dataset. The method significantly outperforms existing approaches while requiring an order of magnitude fewer training examples, and it also successfully categorizes and segments articulated objects with diverse textures and partial occlusion.

Abstract

We present a method for object categorization in real-world scenes. Following a common consensus in the field, we do not assume that a figure- ground segmentation is available prior to recognition. However, in contrast to most standard approaches for object class recognition, our approach automati- cally segments the object as a result of the categorization. This combination of recognition and segmentation into one process is made pos- sible by our use of an Implicit Shape Model, which integrates both into a common probabilistic framework. In addition to the recognition and segmentation result, it also generates a per-pixel confidence measure specifying the area that supports a hypothesis and how much it can be trusted. We use this confidence to derive a nat- ural extension of the approach to handle multiple objects in a scene and resolve ambiguities between overlapping hypotheses with a novel MDL-based criterion. In addition, we present an extensive evaluation of our method on a standard dataset for car detection and compare its performance to existing methods from the literature. Our results show that the proposed method significantly outper- forms previously published methods while needing one order of magnitude less training examples. Finally, we present results for articulated objects, which show that the proposed method can categorize and segment unfamiliar objects in differ- ent articulations and with widely varying texture patterns, even under significant partial occlusion.