Large scale monocular vision-only mapping from a fixed-wing sUAS

This paper presents the application of a monocular visual SLAMon a fixed-wing small Unmanned Aerial System (sUAS) capable of simultaneous estimation of aircraft pose and scene structure. We demonstrate the robustness of unconstrained vision alone in producing reliable pose estimates of a sUAS, at altitude. It is ultimately capable of online state estimation feedback for aircraft control and next-best-view estimation for complete map coverage without the use of additional sensors.We explore some of the challenges of visual SLAM from a sUAS including dealing with planar structure, distant scenes and noisy observations. The developed techniques are applied on vision data gathered from a fast-moving fixed-wing radio control aircraft flown over a 1×1km rural area at an altitude of 20-100m.We present both raw Structure from Motion results and a SLAM solution that includes FAB-MAP based loop-closures and graph-optimised pose. Timing information is also presented to demonstrate near online capabilities. We compare the accuracy of the 6-DOF pose estimates to an off-the-shelfGPS aided INS over a 1.7kmtrajectory.We also present output 3D reconstructions of the observed scene structure and texture that demonstrates future applications in autonomous monitoring and surveying.

GrabCutSFM : how 3D information improves unsupervised object segmentation

In this paper, we present an unsupervised graph cut based object segmentation method using 3D information provided by Structure from Motion (SFM), called Grab- CutSFM. Rather than focusing on the segmentation problem using a trained model or human intervention, our approach aims to achieve meaningful segmentation autonomously with direct application to vision based robotics. Generally, object (foreground) and background have certain discriminative geometric information in 3D space. By exploring the 3D information from multiple views, our proposed method can segment potential objects correctly and automatically compared to conventional unsupervised segmentation using only 2D visual cues. Experiments with real video data collected from indoor and outdoor environments verify the proposed approach.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Vision-only autonomous navigation using topometric maps

This paper presents a mapping and navigation system for a mobile robot, which uses vision as its sole sensor modality. The system enables the robot to navigate autonomously, plan paths and avoid obstacles using a vision based topometric map of its environment. The map consists of a globally-consistent pose-graph with a local 3D point cloud attached to each of its nodes. These point clouds are used for direction independent loop closure and to dynamically generate 2D metric maps for locally optimal path planning. Using this locally semi-continuous metric space, the robot performs shortest path planning instead of following the nodes of the graph --- as is done with most other vision-only navigation approaches. The system exploits the local accuracy of visual odometry in creating local metric maps, and uses pose graph SLAM, visual appearance-based place recognition and point clouds registration to create the topometric map. The ability of the framework to sustain vision-only navigation is validated experimentally, and the system is provided as open-source software.

Outdoor flight testing of a pole inspection UAV incorporating high-speed vision

We present a pole inspection system for outdoor environments comprising a high-speed camera on a vertical take-off and landing (VTOL) aerial platform. The pole inspection task requires a vehicle to fly close to a structure while maintaining a fixed stand-off distance from it. Typical GPS errors make GPS-based navigation unsuitable for this task however. When flying outdoors a vehicle is also affected by aerodynamics disturbances such as wind gusts, so the onboard controller must be robust to these disturbances in order to maintain the stand-off distance. Two problems must therefor be addressed: fast and accurate state estimation without GPS, and the design of a robust controller. We resolve these problems by a) performing visual + inertial relative state estimation and b) using a robust line tracker and a nested controller design. Our state estimation exploits high-speed camera images (100Hz) and 70Hz IMU data fused in an Extended Kalman Filter (EKF). We demonstrate results from outdoor experiments for pole-relative hovering, and pole circumnavigation where the operator provides only yaw commands. Lastly, we show results for image-based 3D reconstruction and texture mapping of a pole to demonstrate the usefulness for inspection tasks.

Joint 2D and 3D cues for image segmentation towards robotic applications

This thesis investigates the fusion of 3D visual information with 2D image cues to provide 3D semantic maps of large-scale environments in which a robot traverses for robotic applications. A major theme of this thesis was to exploit the availability of 3D information acquired from robot sensors to improve upon 2D object classification alone. The proposed methods have been evaluated on several indoor and outdoor datasets collected from mobile robotic platforms including a quadcopter and ground vehicle covering several kilometres of urban roads.

Virtual 3D models of insects for accelerated quarantine control

We learn from the past that invasive species have caused tremendous damage to native species and serious disruption to agricultural industries. It is crucial for us to prevent this in the future. The first step of this process is to identify correctly an invasive species from native ones. Current identification methods, relying on mainly 2D images, can result in low accuracy and be time consuming. Such methods provide little help to a quarantine officer who has time constraints to response when on duty. To deal with this problem, we propose new solutions using 3D virtual models of insects. We explain how working with insects in the 3D domain can be much better than the 2D domain. We also describe how to create true-color 3D models of insects using an image-based 3D reconstruction method. This method is ideal for quarantine control and inspection tasks that involve the verification of a physical specimen against known invasive species. Finally we show that these insect models provide valuable material for other applications such as research, education, arts and entertainment. © 2013 IEEE.

Capturing natural-colour 3D models of insects for species discovery and diagnostics

Collections of biological specimens are fundamental to scientific understanding and characterization of natural diversity - past, present and future. This paper presents a system for liberating useful information from physical collections by bringing specimens into the digital domain so they can be more readily shared, analyzed, annotated and compared. It focuses on insects and is strongly motivated by the desire to accelerate and augment current practices in insect taxonomy which predominantly use text, 2D diagrams and images to describe and characterize species. While these traditional kinds of descriptions are informative and useful, they cannot cover insect specimens "from all angles" and precious specimens are still exchanged between researchers and collections for this reason. Furthermore, insects can be complex in structure and pose many challenges to computer vision systems. We present a new prototype for a practical, cost-effective system of off-the-shelf components to acquire natural-colour 3D models of insects from around 3 mm to 30 mm in length. ("Natural-colour" is used to contrast with "false-colour", i.e., colour generated from, or applied to, gray-scale data post-acquisition.) Colour images are captured from different angles and focal depths using a digital single lens reflex (DSLR) camera rig and two-axis turntable. These 2D images are processed into 3D reconstructions using software based on a visual hull algorithm. The resulting models are compact (around 10 megabytes), afford excellent optical resolution, and can be readily embedded into documents and web pages, as well as viewed on mobile devices. The system is portable, safe, relatively affordable, and complements the sort of volumetric data that can be acquired by computed tomography. This system provides a new way to augment the description and documentation of insect species holotypes, reducing the need to handle or ship specimens. It opens up new opportunities to collect data for research, education, art, entertainment, biodiversity assessment and biosecurity control. © 2014 Nguyen et al.

Separable spatiotemporal priors for convex reconstruction of time-varying 3D point clouds

Reconstructing 3D motion data is highly under-constrained due to several common sources of data loss during measurement, such as projection, occlusion, or miscorrespondence. We present a statistical model of 3D motion data, based on the Kronecker structure of the spatiotemporal covariance of natural motion, as a prior on 3D motion. This prior is expressed as a matrix normal distribution, composed of separable and compact row and column covariances. We relate the marginals of the distribution to the shape, trajectory, and shape-trajectory models of prior art. When the marginal shape distribution is not available from training data, we show how placing a hierarchical prior over shapes results in a convex MAP solution in terms of the trace-norm. The matrix normal distribution, fit to a single sequence, outperforms state-of-the-art methods at reconstructing 3D motion data in the presence of significant data loss, while providing covariance estimates of the imputed points.

Towards web-based semantic enrichment of 3D insects

Natural history collections are an invaluable resource housing a wealth of knowledge with a long tradition of contributing to a wide range of fields such as taxonomy, quarantine, conservation and climate change. It is recognized however [Smith and Blagoderov 2012] that such physical collections are often heavily underutilized as a result of the practical issues of accessibility. The digitization of these collections is a step towards removing these access issues, but other hurdles must be addressed before we truly unlock the potential of this knowledge.

A Profilometric Approach to 3D Face Reconstruction and Its Application to Face Recognition

3D Face Recognition is an active area of research for past several years. For a 3D face recognition system one would like to have an accurate as well as low cost setup for constructing 3D face model. In this paper, we use Profilometry approach to obtain a 3D face model.This method gives a low cost solution to the problem of acquiring 3D data and the 3D face models generated by this method are sufficiently accurate. We also develop an algorithm that can use the 3D face model generated by the above method for the recognition purpose.

Constrained 3D sketching with haptics and active motion annotation

The aim of this work is to enable seamless transformation of product concepts to CAD models. This necessitates availability of 3D product sketches. The present work concerns intuitive generation of 3D strokes and intrinsic support for space sharing and articulation for the components of the product being sketched. Direct creation of 3D strokes in air lacks in precision, stability and control. The inadequacy of proprioceptive feedback for the task is complimented in this work with stereo vision and haptics. Three novel methods based on pencil-paper interaction analogy for haptic rendering of strokes have been investigated. The pen-tilt based rendering is simpler and found to be more effective. For the spatial conformity, two modes of constraints for the stylus movements, corresponding to the motions on a control surface and in a control volume have been studied using novel reactive and field based haptic rendering schemes. The field based haptics, which in effect creates an attractive force field near a surface, though non-realistic, provided highly effective support for the control-surface constraints. The efficacy of the reactive haptic rendering scheme for the constrained environments has been demonstrated using scribble strokes. This can enable distributed collaborative 3D concept development. The notion of motion constraints, defined through sketch strokes enables intuitive generation of articulated 3D sketches and direct exploration of motion annotations found in most product concepts. The work, thus, establishes that modeling of the constraints is a central issue in 3D sketching.

Dynamics of 3D view invariance in monkey inferotemporal cortex

Rotations in depth are challenging for object vision because features can appear, disappear, be stretched or compressed. Yet we easily recognize objects across views. Are the underlying representations view invariant or dependent? This question has been intensely debated in human vision, but the neuronal representations remain poorly understood. Here, we show that for naturalistic objects, neurons in the monkey inferotemporal (IT) cortex undergo a dynamic transition in time, whereby they are initially sensitive to viewpoint and later encode view-invariant object identity. This transition depended on two aspects of object structure: it was strongest when objects foreshortened strongly across views and were similar to each other. View invariance in IT neurons was present even when objects were reduced to silhouettes, suggesting that it can arise through similarity between external contours of objects across views. Our results elucidate the viewpoint debate by showing that view invariance arises dynamically in IT neurons out of a representation that is initially view dependent.