CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2012 vol.34 Issue No.05 - May
Issue No.05 - May (2012 vol.34)
V. Lepetit , Comput. Vision Lab. (CVLAB), Ecole Polytech. Federate de Lausane, Lausanne, Switzerland
We present a method for real-time 3D object instance detection that does not require a time-consuming training stage, and can handle untextured objects. At its core, our approach is a novel image representation for template matching designed to be robust to small image transformations. This robustness is based on spread image gradient orientations and allows us to test only a small subset of all possible pixel locations when parsing the image, and to represent a 3D object with a limited set of templates. In addition, we demonstrate that if a dense depth sensor is available we can extend our approach for an even better performance also taking 3D surface normal orientations into account. We show how to take advantage of the architecture of modern computers to build an efficient but very discriminant representation of the input images that can be used to consider thousands of templates in real time. We demonstrate in many experiments on real data that our method is much faster and more robust with respect to background clutter than current state-of-the-art methods.
object detection, computer vision, gradient methods, image matching, image representation, 3D surface normal orientation, gradient response map, real-time detection, textureless object, 3D object instance detection, image representation, template matching, spread image gradient orientation, dense depth sensor, Robustness, Real time systems, Three dimensional displays, Image edge detection, Training, Clutter, Transforms, multimodality template matching., Computer vision, real-time detection and object recognition, tracking
V. Lepetit, "Gradient Response Maps for Real-Time Detection of Textureless Objects", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 5, pp. 876-888, May 2012, doi:10.1109/TPAMI.2011.206