Martial Hebert

Using spin images for efficient object recognition in cluttered 3D scenes

We present a 3D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matching surfaces by matching points using the spin image representation. The spin image is a data level shape descriptor that is used to match surfaces represented as surface meshes. We present a compression scheme for spin images that results in efficient multiple object recognition which we verify with results showing the simultaneous recognition of multiple objects from a library of 20 models. Furthermore, we demonstrate the robust performance of recognition in the presence of clutter and occlusion through analysis of recognition trials on 100 scenes.

Putting Objects in Perspective

Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. Most object detection methods consider all scales and locations in the image as equally likely. We show that with probabilistic estimates of 3D geometry, both in terms of surfaces and world coordinates, we can put objects into perspective and model the scale and location variance in the image. Our approach reflects the cyclical nature of the problem by allowing probabilistic object hypotheses to refine geometry and vice-versa. Our framework allows painless substitution of almost any object detector and is easily extended to include other aspects of image understanding. Our results confirm the benefits of our integrated approach.

The representation, recognition, and locating of 3-d objects

The problem of recognizing and locating rigid objects in 3-D space is important for applications of robotics and naviga tion. We analyze the task requirements in terms of what information needs to be represented, how to represent it, what kind of paradigms can be used to process it, and how to implement the paradigms. We describe shape surfaces by curves and patches, which we represent by linear primitives, such as points, lines, and planes. Next we describe algo rithms to construct this representation from range data. We then propose the paradigm of recognizing objects while locat ing them. We analyze the basic constraint of rigidity that can be exploited, which we implement as a prediction and verifi cation scheme that makes efficient use of the representation. Results are presented for data obtained from a laser range finder, but both the shape representation and the matching algorithm are general and can be used for other types of data, such as ultrasound, stereo, and tactile.

Vision and navigation for the Carnegie-Mellon Navlab

A distributed architecture articulated around the CODGER (communication database with geometric reasoning) knowledge database is described for a mobile robot system that includes both perception and navigation tools. Results are described for vision and navigation tests using a mobile testbed that integrates perception and navigation capabilities that are based on two types of vision algorithms: color vision for road following, and 3-D vision for obstacle detection and avoidance. The perception modules are integrated into a system that allows the vehicle to drive continuously in an actual outdoor environment. The resulting system is able to navigate continuously on roads while avoiding obstacles. >

A spectral technique for correspondence problems using pairwise constraints

We present an efficient spectral method for finding consistent correspondences between two sets of features. We build the adjacency matrix M of a graph whose nodes represent the potential correspondences and the weights on the links represent pairwise agreements between potential correspondences. Correct assignments are likely to establish links among each other and thus form a strongly connected cluster. Incorrect correspondences establish links with the other correspondences only accidentally, so they are unlikely to belong to strongly connected clusters. We recover the correct assignments based on how strongly they belong to the main cluster of M, by using the principal eigenvector of M and imposing the mapping constraints required by the overall correspondence mapping (one-to-one or one-to-many). The experimental evaluation shows that our method is robust to outliers, accurate in terms of matching rate, while being much faster than existing methods

Toward Objective Evaluation of Image Segmentation Algorithms

Unsupervised image segmentation is an important component in many image understanding algorithms and practical vision systems. However, evaluation of segmentation algorithms thus far has been largely subjective, leaving a system designer to judge the effectiveness of a technique based only on intuition and results in the form of a few example segmented images. This is largely due to image segmentation being an ill-defined problem-there is no unique ground-truth segmentation of an image against which the output of an algorithm may be compared. This paper demonstrates how a recently proposed measure of similarity, the normalized probabilistic rand (NPR) index, can be used to perform a quantitative comparison between image segmentation algorithms using a hand-labeled set of ground-truth segmentations. We show that the measure allows principled comparisons between segmentations created by different algorithms, as well as segmentations on different images. We outline a procedure for algorithm evaluation through an example evaluation of some familiar algorithms - the mean-shift-based algorithm, an efficient graph-based segmentation algorithm, a hybrid algorithm that combines the strengths of both methods, and expectation maximization. Results are presented on the 300 images in the publicly available Berkeley segmentation data set

Geometric context from a single image

Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes. Geometric classes describe the 3D orientation of an image region with respect to the camera. We provide a multiple-hypothesis framework for robustly estimating scene structure from a single image and obtaining confidences for each geometric label. These confidences can then be used to improve the performance of many other applications. We provide a thorough quantitative evaluation of our algorithm on a set of outdoor images and demonstrate its usefulness in two applications: object detection and automatic single-view reconstruction.

Efficient visual event detection using volumetric features

This paper studies the use of volumetric features as an alternative to popular local descriptor approaches for event detection in video sequences. Motivated by the recent success of similar ideas in object detection on static images, we generalize the notion of 2D box features to 3D spatio-temporal volumetric features. This general framework enables us to do real-time video analysis. We construct a realtime event detector for each action of interest by learning a cascade of filters based on volumetric features that efficiently scans video sequences in space and time. This event detector recognizes actions that are traditionally problematic for interest point methods - such as smooth motions where insufficient space-time interest points are available. Our experiments demonstrate that the technique accurately detects actions on real-world sequences and is robust to changes in viewpoint, scale and action speed. We also adapt our technique to the related task of human action classification and confirm that it achieves performance comparable to a current interest point based human activity recognizer on a standard database of human activities.

Recovering Surface Layout from an Image

Humans have an amazing ability to instantly grasp the overall 3D structure of a scene—ground orientation, relative positions of major landmarks, etc.—even from a single image. This ability is completely missing in most popular recognition algorithms, which pretend that the world is flat and/or view it through a patch-sized peephole. Yet it seems very likely that having a grasp of this “surface layout” of a scene should be of great assistance for many tasks, including recognition, navigation, and novel view synthesis.In this paper, we take the first step towards constructing the surface layout, a labeling of the image intogeometric classes. Our main insight is to learn appearance-based models of these geometric classes, which coarsely describe the 3D scene orientation of each image region. Our multiple segmentation framework provides robust spatial support, allowing a wide variety of cues (e.g., color, texture, and perspective) to contribute to the confidence in each geometric label. In experiments on a large set of outdoor images, we evaluate the impact of the individual cues and design choices in our algorithm. We further demonstrate the applicability of our method to indoor images, describe potential applications, and discuss extensions to a more complete notion of surface layout.

Simultaneous localization, mapping and moving object tracking

Simultaneous localization, mapping and moving object tracking (SLAMMOT) involves both simultaneous localization and mapping (SLAM) in dynamic environments and detecting and tracking these dynamic objects. In this paper, a mathematical framework is established to integrate SLAM and moving object tracking. Two solutions are described: SLAM with generalized objects, and SLAM with detection and tracking of moving objects (DATMO). SLAM with generalized objects calculates a joint posterior over all generalized objects and the robot. Such an approach is similar to existing SLAM algorithms, but with additional structure to allow for motion modeling of generalized objects. Unfortunately, it is computationally demanding and generally infeasible. SLAM with DATMO decomposes the estimation problem into two separate estimators. By maintaining separate posteriors for stationary objects and moving objects, the resulting estimation problems are much lower dimensional than SLAM with generalized objects. Both SLAM and moving object tracking from a moving vehicle in crowded urban areas are daunting tasks. Based on the SLAM with DATMO framework, practical algorithms are proposed which deal with issues of perception modeling, data association, and moving object detection. The implementation of SLAM with DATMO was demonstrated using data collected from the CMU Navlab11 vehicle at high speeds in crowded urban environments. Ample experimental results shows the feasibility of the proposed theory and algorithms.