Achievements and Challenges in Recognizing and Reconstructing Civil Infrastructure

The US National Academy of Engineering recently identified restoring and improving urban infrastructure as one of the grand challenges of engineering. Part of this challenge stems from the lack of viable methods to map/label existing infrastructure. For computer vision, this challenge becomes “How can we automate the process of extracting geometric, object oriented models of infrastructure from visual data?” Object recognition and reconstruction methods have been successfully devised and/or adapted to answer this question for small or linear objects (e.g. columns). However, many infrastructure objects are large and/or planar without significant and distinctive features, such as walls, floor slabs, and bridge decks. How can we recognize and reconstruct them in a 3D model? In this paper, strategies for infrastructure object recognition and reconstruction are presented, to set the stage for posing the question above and discuss future research in featureless, large/planar object recognition and modeling.

Comparing crowding in human and ideal observers.

A visual target is more difficult to recognize when it is surrounded by other, similar objects. This breakdown in object recognition is known as crowding. Despite a long history of experimental work, computational models of crowding are still sparse. Specifically, few studies have examined crowding using an ideal-observer approach. Here, we compare crowding in ideal observers with crowding in humans. We derived an ideal-observer model for target identification under conditions of position and identity uncertainty. Simulations showed that this model reproduces the hallmark of crowding, namely a critical spacing that scales with viewing eccentricity. To examine how well the model fits quantitatively to human data, we performed three experiments. In Experiments 1 and 2, we measured observers' perceptual uncertainty about stimulus positions and identities, respectively, for a target in isolation. In Experiment 3, observers identified a target that was flanked by two distractors. We found that about half of the errors in Experiment 3 could be accounted for by the perceptual uncertainty measured in Experiments 1 and 2. The remainder of the errors could be accounted for by assuming that uncertainty (i.e., the width of internal noise distribution) about stimulus positions and identities depends on flanker proximity. Our results provide a mathematical restatement of the crowding problem and support the hypothesis that crowding behavior is a sign of optimality rather than a perceptual defect.

A neurophysiologically plausible population code model for feature integration explains visual crowding.

An object in the peripheral visual field is more difficult to recognize when surrounded by other objects. This phenomenon is called "crowding". Crowding places a fundamental constraint on human vision that limits performance on numerous tasks. It has been suggested that crowding results from spatial feature integration necessary for object recognition. However, in the absence of convincing models, this theory has remained controversial. Here, we present a quantitative and physiologically plausible model for spatial integration of orientation signals, based on the principles of population coding. Using simulations, we demonstrate that this model coherently accounts for fundamental properties of crowding, including critical spacing, "compulsory averaging", and a foveal-peripheral anisotropy. Moreover, we show that the model predicts increased responses to correlated visual stimuli. Altogether, these results suggest that crowding has little immediate bearing on object recognition but is a by-product of a general, elementary integration mechanism in early vision aimed at improving signal quality.

Synchronization of user-generated videos through trajectory correspondence and a refinement procedure

Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied through the time-stamp information embedded in the video streams. User-generated videos shot using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. Our first contribution is a synchronization technique which tries to establish correspondence between feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. We evaluate performance using a number of real video recordings and show that our method is able to synchronize to within 1 sec, which is significantly better than previous approaches. Our second contribution is a robust and unsupervised view-invariant activity recognition descriptor that exploits recurrence plot theory on spatial tiles. The descriptor is individually shown to better characterize the activities from different views under occlusions than state-of-the-art approaches. We combine this descriptor with our proposed synchronization method and show that it can further refine the synchronization index. © 2013 ACM.

Single camera pose estimation using Bayesian filtering and Kinect motion priors

Traditional approaches to upper body pose estimation using monocular vision rely on complex body models and a large variety of geometric constraints. We argue that this is not ideal and somewhat inelegant as it results in large processing burdens, and instead attempt to incorporate these constraints through priors obtained directly from training data. A prior distribution covering the probability of a human pose occurring is used to incorporate likely human poses. This distribution is obtained offline, by fitting a Gaussian mixture model to a large dataset of recorded human body poses, tracked using a Kinect sensor. We combine this prior information with a random walk transition model to obtain an upper body model, suitable for use within a recursive Bayesian filtering framework. Our model can be viewed as a mixture of discrete Ornstein-Uhlenbeck processes, in that states behave as random walks, but drift towards a set of typically observed poses. This model is combined with measurements of the human head and hand positions, using recursive Bayesian estimation to incorporate temporal information. Measurements are obtained using face detection and a simple skin colour hand detector, trained using the detected face. The suggested model is designed with analytical tractability in mind and we show that the pose tracking can be Rao-Blackwellised using the mixture Kalman filter, allowing for computational efficiency while still incorporating bio-mechanical properties of the upper body. In addition, the use of the proposed upper body model allows reliable three-dimensional pose estimates to be obtained indirectly for a number of joints that are often difficult to detect using traditional object recognition strategies. Comparisons with Kinect sensor results and the state of the art in 2D pose estimation highlight the efficacy of the proposed approach.

A new distance for scale-invariant 3D shape recognition and registration

This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for the first time. We introduce a new distance between poses in this spacethe SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form mean, in contrast to Riemannian distance, so is fast to compute. We demonstrate improved performance over the state of the art in both recognition and registration on a real and challenging dataset, by comparing our distance with others in a mean shift framework, as well as with the commonly used Hough voting approach. © 2011 IEEE.

Silhouette-based object phenotype recognition using 3D shape priors

This paper tackles the novel challenging problem of 3D object phenotype recognition from a single 2D silhouette. To bridge the large pose (articulation or deformation) and camera viewpoint changes between the gallery images and query image, we propose a novel probabilistic inference algorithm based on 3D shape priors. Our approach combines both generative and discriminative learning. We use latent probabilistic generative models to capture 3D shape and pose variations from a set of 3D mesh models. Based on these 3D shape priors, we generate a large number of projections for different phenotype classes, poses, and camera viewpoints, and implement Random Forests to efficiently solve the shape and pose inference problems. By model selection in terms of the silhouette coherency between the query and the projections of 3D shapes synthesized using the galleries, we achieve the phenotype recognition result as well as a fast approximate 3D reconstruction of the query. To verify the efficacy of the proposed approach, we present new datasets which contain over 500 images of various human and shark phenotypes and motions. The experimental results clearly show the benefits of using the 3D priors in the proposed method over previous 2D-based methods. © 2011 IEEE.

Testing of Depth-Encoded Hough Voting for Infrastructure Object Detection

The lack of viable methods to map and label existing infrastructure is one of the engineering grand challenges for the 21st century. For instance, over two thirds of the effort needed to geometrically model even simple infrastructure is spent on manually converting a cloud of points to a 3D model. The result is that few facilities today have a complete record of as-built information and that as-built models are not produced for the vast majority of new construction and retrofit projects. This leads to rework and design changes that can cost up to 10% of the installed costs. Automatically detecting building components could address this challenge. However, existing methods for detecting building components are not view and scale-invariant, or have only been validated in restricted scenarios that require a priori knowledge without considering occlusions. This leads to their constrained applicability in complex civil infrastructure scenes. In this paper, we test a pose-invariant method of labeling existing infrastructure. This method simultaneously detects objects and estimates their poses. It takes advantage of a recent novel formulation for object detection and customizes it to generic civil infrastructure scenes. Our preliminary experiments demonstrate that this method achieves convincing recognition results.

Scale-invariant vote-based 3D recognition and registration from point clouds

This chapter presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transformations for the first time. We introduce a new distance between poses in this spacethe SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form mean, in contrast to Riemannian distance, so is fast to compute. We demonstrate improved performance over the state of the art in both recognition and registration on a (real and) challenging dataset, by comparing our distance with others in a mean shift framework, as well as with the commonly used Hough voting approach. © 2013 Springer-Verlag Berlin Heidelberg.

Image-based localization and pose recovery using scale invariant features

In this paper, we propose a vision based mobile robot localization strategy. Local scale-invariant features are used as natural landmarks in unstructured and unmodified environment. The local characteristics of the features we use prove to be robust to occlusion and outliers. In addition, the invariance of the features to viewpoint change makes them suitable landmarks for mobile robot localization. Scale-invariant features detected in the first exploration are indexed into a location database. Indexing and voting allow efficient recognition of global localization. The localization result is verified by epipolar geometry between the representative view in database and the view to be localized, thus the probability of false localization will be decreased. The localization system can recover the pose of the camera mounted on the robot by essential matrix decomposition. Then the position of the robot can be computed easily. Both calibrated and un-calibrated cases are discussed and relative position estimation based on calibrated camera turns out to be the better choice. Experimental results show that our approach is effective and reliable in the case of illumination changes, similarity transformations and extraneous features. © 2004 IEEE.