Marco Andreetto

Learn More
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depthwise separable convolutions to build light weight deep neural networks. We introduce two simple global hyperparameters that efficiently trade off between latency and accuracy. These(More)
This work is motivated by the desire of exploiting for 3D registration purposes the photometric information current range cameras typically associate to range data. Automatic pairwise 3D registration procedures are two steps procedures with the first step performing an automatic crude estimate of the rigid motion parameters and the second step refining them(More)
A widespread use of three-dimensional (3D) models in cultural heritage application requires low cost equipment and technically simple modeling procedures. In this context, methods for automatic 3D modeling of textured objects can play a central role. Such methods need fully automatic techniques for 3D view registration and for the removal of texture(More)
Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a flexible probabilistic model, for representing the shape and appearance of each segment, with the popular “bag of visual words” model for recognition. If applied to a(More)
We propose a simple probabilistic generative model for image segmentation. Like other probabilistic algorithms (such as EM on a mixture of Gaussians) the proposed model is principled, provides both hard and probabilistic cluster assignments, as well as the ability to naturally incorporate prior knowledge. While previous probabilistic approaches are(More)
This work presents a new method for registering computer tomography (CT) volumetric data of human bone structures relative to observations made at different times. The system we advance was tested with different kinds of CT data sets. We report on some representative experimental results obtained with the CT data of the hip bones of a patient prior to and(More)
Cast shadows are an informative cue to the shape of objects. They are particularly valuable for discovering object’s concavities which are not available from other cues such as occluding boundaries. We propose a new method for recovering shape from shadows which we call shadow carving. Given a conservative estimate of the volume occupied by an object, it is(More)
The contribution of this paper is twofold: (1) it presents an automatic 3D modeling technique and (2) it advances a procedure for its metrological evaluation in the context of a medical application, the 3D modeling of dental plaster casts. The motivation for this work is the creation of a "virtual gypsotheque" where cumbersome dental plaster casts can be(More)
We show a control algorithm to guide a robotic walking assistant along a planned path. The control strategy exploits the electromechanical brakes mounted on the back wheels of the walker. In order to reduce the hardware requirements we adopt a Bang Bang approach relying of four actions (with saturated value for the braking torques). When the platform is far(More)
This paper presents a control algorithm that steers a robotic walking assistant along a planned path using electromechanical brakes. The device is modeled as a Dubins' car, i.e., a wheeled vehicle that moves only forward in the plane and has a limited turning radius. In order to reduce the cost of the hardware, no force sensor is employed. This feature(More)