Online calibration of stereo rigs for long-term autonomy

Stereo-based visual odometry algorithms are heavily dependent on an accurate calibration of the rigidly fixed stereo pair. Even small shifts in the rigid transform between the cameras can impact on feature matching and 3D scene triangulation, adversely affecting pose estimates and applications dependent on long-term autonomy. In many field-based scenarios where vibration, knocks and pressure change affect a robotic vehicle, maintaining an accurate stereo calibration cannot be guaranteed over long periods. This paper presents a novel method of recalibrating overlapping stereo camera rigs from online visual data while simultaneously providing an up-to-date and up-to-scale pose estimate. The proposed technique implements a novel form of partitioned bundle adjustment that explicitly includes the homogeneous transform between a stereo camera pair to generate an optimal calibration. Pose estimates are computed in parallel to the calibration, providing online recalibration which seamlessly integrates into a stereo visual odometry framework. We present results demonstrating accurate performance of the algorithm on both simulated scenarios and real data gathered from a wide-baseline stereo pair on a ground vehicle traversing urban roads.

Automatic object segmentation of unstructured scenes using colour and depth maps

This study presents a segmentation pipeline that fuses colour and depth information to automatically separate objects of interest in video sequences captured from a quadcopter. Many approaches assume that cameras are static with known position, a condition which cannot be preserved in most outdoor robotic applications. In this study, the authors compute depth information and camera positions from a monocular video sequence using structure from motion and use this information as an additional cue to colour for accurate segmentation. The authors model the problem similarly to standard segmentation routines as a Markov random field and perform the segmentation using graph cuts optimisation. Manual intervention is minimised and is only required to determine pixel seeds in the first frame which are then automatically reprojected into the remaining frames of the sequence. The authors also describe an automated method to adjust the relative weights for colour and depth according to their discriminative properties in each frame. Experimental results are presented for two video sequences captured using a quadcopter. The quality of the segmentation is compared to a ground truth and other state-of-the-art methods with consistently accurate results.

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.

Aircraft collision avoidance using spherical visual predictive control and single point features

This paper presents practical vision-based collision avoidance for objects approximating a single point feature. Using a spherical camera model, a visual predictive control scheme guides the aircraft around the object along a conical spiral trajectory. Visibility, state and control constraints are considered explicitly in the controller design by combining image and vehicle dynamics in the process model, and solving the nonlinear optimization problem over the resulting state space. Importantly, range is not required. Instead, the principles of conical spiral motion are used to design an objective function that simultaneously guides the aircraft along the avoidance trajectory, whilst providing an indication of the appropriate point to stop the spiral behaviour. Our approach is aimed at providing a potential solution to the See and Avoid problem for unmanned aircraft and is demonstrated through a series.

Automated marine mammal detection from aerial imagery

This paper presents two algorithms to automate the detection of marine species in aerial imagery. An algorithm from an initial pilot study is presented in which morphology operations and colour analysis formed the basis of its working principle. A second approach is presented in which saturation channel and histogram-based shape profiling were used. We report on performance for both algorithms using datasets collected from an unmanned aerial system at an altitude of 1000 ft. Early results have demonstrated recall values of 48.57% and 51.4%, and precision values of 4.01% and 4.97%.

Detection of dugongs from unmanned aerial vehicles

Monitoring and estimation of marine populations is of paramount importance for the conservation and management of sea species. Regular surveys are used to this purpose followed often by a manual counting process. This paper proposes an algorithm for automatic detection of dugongs from imagery taken in aerial surveys. Our algorithm exploits the fact that dugongs are rare in most images, therefore we determine regions of interest partially based on color rarity. This simple observation makes the system robust to changes in illumination. We also show that by applying the extended-maxima transform on red-ratio images, submerged dugongs with very fuzzy edges can be detected. Performance figures obtained here are promising in terms of degree of confidence in the detection of marine species, but more importantly our approach represents a significant step in automating this type of surveys.

Gradual training of cascaded shape regression for facial landmark localization and pose estimation

Facial landmarks play an important role in face recognition. They serve different steps of the recognition such as pose estimation, face alignment, and local feature extraction. Recently, cascaded shape regression has been proposed to accurately locate facial landmarks. A large number of weak regressors are cascaded in a sequence to fit face shapes to the correct landmark locations. In this paper, we propose to improve the method by applying gradual training. With this training, the regressors are not directly aimed to the true locations. The sequence instead is divided into successive parts each of which is aimed to intermediate targets between the initial and the true locations. We also investigate the incorporation of pose information in the cascaded model. The aim is to find out whether the model can be directly used to estimate head pose. Experiments on the Annotated Facial Landmarks in the Wild database have shown that the proposed method is able to improve the localization and give accurate estimates of pose.

High altitude stereo visual odometry

Stereo visual odometry has received little investigation in high altitude applications due to the generally poor performance of rigid stereo rigs at extremely small baseline-to-depth ratios. Without additional sensing, metric scale is considered lost and odometry is seen as effective only for monocular perspectives. This paper presents a novel modification to stereo based visual odometry that allows accurate, metric pose estimation from high altitudes, even in the presence of poor calibration and without additional sensor inputs. By relaxing the (typically fixed) stereo transform during bundle adjustment and reducing the dependence on the fixed geometry for triangulation, metrically scaled visual odometry can be obtained in situations where high altitude and structural deformation from vibration would cause traditional algorithms to fail. This is achieved through the use of a novel constrained bundle adjustment routine and accurately scaled pose initializer. We present visual odometry results demonstrating the technique on a short-baseline stereo pair inside a fixed-wing UAV flying at significant height (~30-100m).

Robust scale initialization for long-range stereo visual odometry

Achieving a robust, accurately scaled pose estimate in long-range stereo presents significant challenges. For large scene depths, triangulation from a single stereo pair is inadequate and noisy. Additionally, vibration and flexible rigs in airborne applications mean accurate calibrations are often compromised. This paper presents a technique for accurately initializing a long-range stereo VO algorithm at large scene depth, with accurate scale, without explicitly computing structure from rigidly fixed camera pairs. By performing a monocular pose estimate over a window of frames from a single camera, followed by adding the secondary camera frames in a modified bundle adjustment, an accurate, metrically scaled pose estimate can be found. To achieve this the scale of the stereo pair is included in the optimization as an additional parameter. Results are presented both on simulated and field gathered data from a fixed-wing UAV flying at significant altitude, where the epipolar geometry is inaccurate due to structural deformation and triangulation from a single pair is insufficient. Comparisons are made with more conventional VO techniques where the scale is not explicitly optimized, and demonstrated over repeated trials to indicate robustness.

Feature-domain super-resolution for iris recognition

Uncooperative iris identification systems at a distance suffer from poor resolution of the acquired iris images, which significantly degrades iris recognition performance. Super-resolution techniques have been employed to enhance the resolution of iris images and improve the recognition performance. However, most existing super-resolution approaches proposed for the iris biometric super-resolve pixel intensity values, rather than the actual features used for recognition. This paper thoroughly investigates transferring super-resolution of iris images from the intensity domain to the feature domain. By directly super-resolving only the features essential for recognition, and by incorporating domain specific information from iris models, improved recognition performance compared to pixel domain super-resolution can be achieved. A framework for applying super-resolution to nonlinear features in the feature-domain is proposed. Based on this framework, a novel feature-domain super-resolution approach for the iris biometric employing 2D Gabor phase-quadrant features is proposed. The approach is shown to outperform its pixel domain counterpart, as well as other feature domain super-resolution approaches and fusion techniques.

Detecting anomalous events at railway level crossings

Collisions between pedestrians and vehicles continue to be a major problem throughout the world. Pedestrians trying to cross roads and railway tracks without any caution are often highly susceptible to collisions with vehicles and trains. Continuous financial, human and other losses have prompted transport related organizations to come up with various solutions addressing this issue. However, the quest for new and significant improvements in this area is still ongoing. This work addresses this issue by building a general framework using computer vision techniques to automatically monitor pedestrian movements in such high-risk areas to enable better analysis of activity, and the creation of future alerting strategies. As a result of rapid development in the electronics and semi-conductor industry there is extensive deployment of CCTV cameras in public places to capture video footage. This footage can then be used to analyse crowd activities in those particular places. This work seeks to identify the abnormal behaviour of individuals in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM), Full-2D HMM and Spatial HMM to model the normal activities of people. The outliers of the model (i.e. those observations with insufficient likelihood) are identified as abnormal activities. Location features, flow features and optical flow textures are used as the features for the model. The proposed approaches are evaluated using the publicly available UCSD datasets, and we demonstrate improved performance using a Semi-2D Hidden Markov Model compared to other state of the art methods. Further we illustrate how our proposed methods can be applied to detect anomalous events at rail level crossings.

Histogram of weighted local directions for gait recognition

In this paper, we explore the effectiveness of patch-based gradient feature extraction methods when applied to appearance-based gait recognition. Extending existing popular feature extraction methods such as HOG and LDP, we propose a novel technique which we term the Histogram of Weighted Local Directions (HWLD). These 3 methods are applied to gait recognition using the GEI feature, with classification performed using SRC. Evaluations on the CASIA and OULP datasets show significant improvements using these patch-based methods over existing implementations, with the proposed method achieving the highest recognition rate for the respective datasets. In addition, the HWLD can easily be extended to 3D, which we demonstrate using the GEV feature on the DGD dataset, observing improvements in performance.

Recognising team activities from noisy data

Recently, vision-based systems have been deployed in professional sports to track the ball and players to enhance analysis of matches. Due to their unobtrusive nature, vision-based approaches are preferred to wearable sensors (e.g. GPS or RFID sensors) as it does not require players or balls to be instrumented prior to matches. Unfortunately, in continuous team sports where players need to be tracked continuously over long-periods of time (e.g. 35 minutes in field-hockey or 45 minutes in soccer), current vision-based tracking approaches are not reliable enough to provide fully automatic solutions. As such, human intervention is required to fix-up missed or false detections. However, in instances where a human can not intervene due to the sheer amount of data being generated - this data can not be used due to the missing/noisy data. In this paper, we investigate two representations based on raw player detections (and not tracking) which are immune to missed and false detections. Specifically, we show that both team occupancy maps and centroids can be used to detect team activities, while the occupancy maps can be used to retrieve specific team activities. An evaluation on over 8 hours of field hockey data captured at a recent international tournament demonstrates the validity of the proposed approach.

Representing and discovering adversarial team behaviors using player roles

In this paper, we describe a method to represent and discover adversarial group behavior in a continuous domain. In comparison to other types of behavior, adversarial behavior is heavily structured as the location of a player (or agent) is dependent both on their teammates and adversaries, in addition to the tactics or strategies of the team. We present a method which can exploit this relationship through the use of a spatiotemporal basis model. As players constantly change roles during a match, we show that employing a "role-based" representation instead of one based on player "identity" can best exploit the playing structure. As vision-based systems currently do not provide perfect detection/tracking (e.g. missed or false detections), we show that our compact representation can effectively "denoise" erroneous detections as well as enabe temporal analysis, which was previously prohibitive due to the dimensionality of the signal. To evaluate our approach, we used a fully instrumented field-hockey pitch with 8 fixed high-definition (HD) cameras and evaluated our approach on approximately 200,000 frames of data from a state-of-the-art real-time player detector and compare it to manually labelled data.