Abstract-We study the problem of detecting objects in still, grayscale images. Our primary focus is development of a learning-based approach to the problem, that makes use of a sparse, part-based representation. A vocabulary of distinctive object parts is automatically constructed from a set of sample images of the object class of interest; images are then represented using parts from this vocabulary, together with spatial relations observed among the parts. Based on this representation, a learning algorithm is used to automatically learn to detect instances of the object class in new images. The approach can be applied to any object with distinguishable parts in a relatively fixed spatial configuration; it is evaluated here on difficult sets of real-world images containing side views of cars, and is seen to successfully detect objects in varying conditions amidst background clutter and mild occlusion. In evaluating object detection approaches, several important methodological issues arise that have not been satisfactorily addressed in previous work. A secondary focus of this paper is to highlight these issues and to develop rigorous evaluation standards for the object detection problem. A critical evaluation of our approach under the proposed standards is presented.
This paper presents a framework for fusing together global and local information in images to form a powerful object detection system. We begin by describing two detection algorithms. The first algorithm uses independent component analysis (ICA) to derive an image representation that captures global information in the input data. The second algorithm uses a part-based representation that relies on local properties of the data. The strengths of the two detection algorithms are then combined to form a more powerful detector. The approach is evaluated on a database of real-world images containing side views of cars. The combined detector gives distinctly superior performance than each of the individual detectors, achieving a high detection accuracy of 94% on this difficult test set.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.