Deep convolutional neural networks have been leveraged to achieve huge improvements in video understanding and human activity recognition performance in the past decade. However, most existing methods focus on activities that have similar time scales, leaving the task of action recognition on multiscale human behaviors less explored. In this study, a two-stream multiscale human activity recognition and anticipation (MS-HARA) network is proposed, which is jointly optimized using a multitask learning method. The MS-HARA network fuses the two streams of the network using an efficient temporal-channel attention (TCA)-based fusion approach to improve the model's representational ability for both temporal and spatial features. We investigate the multiscale human activities from two basic categories, namely, midterm activities and long-term activities. The network is designed to function as part of a real-time processing framework to support interaction and mutual understanding between humans and intelligent machines. It achieves state-of-the-art results on several datasets for different tasks and different application domains. The midterm and long-term action recognition and anticipation performance, as well as the network fusion, are extensively tested to show the efficiency of the proposed network. The results show that the MS-HARA network can easily be extended to different application domains.

Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been great interest in leveraging weakly, semi- or self- supervised methods to avoid this, with much success. Whilst weakly and semi-supervised methods require some annotation, self-supervised methods have used cues such as motion to relieve the need for annotation altogether. However, a complete absence of annotation typically degrades their performance, and ambiguities that arise during motion grouping can inhibit their ability to find accurate object boundaries. In this paper, we propose a new self-supervised mobile object detection approach called SCT. This uses both motion cues and expected object sizes to improve detection performance, and predicts a dense grid of 3$D$oriented bounding boxes to improve object discovery. We significantly outperform the state-of-the-art self-supervised mobile object detection method TCR on the KITTI tracking benchmark, and achieve performance that is within 30 % of the fully supervised PV-RCNN++ method for IoUs$\leq$0.5. Our source code will be made available online.

Birds of prey rely on vision to execute flight manoeuvres that are key to their survival, such as intercepting fast-moving targets or navigating through clutter. A better understanding of the role played by vision during these manoeuvres is not only relevant within the field of animal behaviour, but could also have applications for autonomous drones. In this paper, we present a novel method that uses computer vision tools to analyse the role of active vision in bird flight, and demonstrate its use to answer behavioural questions. Combining motion capture data from Harris' hawks with a hybrid 3D model of the environment, we render RGB images, semantic maps, depth information and optic flow outputs that characterise the visual experience of the bird in flight. In contrast with previous approaches, our method allows us to consider different camera models and alternative gaze strategies for the purposes of hypothesis testing, allows us to consider visual input over the complete visual field of the bird, and is not limited by the technical specifications and performance of a head-mounted camera light enough to attach to a bird's head in flight. We present pilot data from three sample flights: a pursuit flight, in which a hawk intercepts a moving target, and two obstacle avoidance flights. With this approach, we provide a reproducible method that facilitates the collection of large volumes of data across many individuals, opening up new avenues for data-driven models of animal behaviour. Supplementary Information: The online version contains supplementary material available at 10.1007/s11263-022-01733-2.

Unmanned aerial vehicles (UAVs) have been used for many applications in recent years, from urban search and rescue, to agricultural surveying, to autonomous underground mine exploration. However, deploying UAVs in tight, indoor spaces, especially close to humans, remains a challenge. One solution, when limited payload is required, is to use micro-UAVs, which pose less risk to humans and typically cost less to replace after a crash. However, micro-UAVs can only carry a limited sensor suite, e.g. a monocular camera instead of a stereo pair or LiDAR, complicating tasks like dense mapping and markerless multi-person 3D human pose estimation, which are needed to operate in tight environments around people. Monocular approaches to such tasks exist, and dense monocular mapping approaches have been successfully deployed for UAV applications. However, despite many recent works on both marker-based and markerless multi-UAV single-person motion capture, markerless single-camera multi-person 3D human pose estimation remains a much earlier-stage technology, and we are not aware of existing attempts to deploy it in an aerial context. In this paper, we present what is thus, to our knowledge, the first system to perform simultaneous mapping and multi-person 3D human pose estimation from a monocular camera mounted on a single UAV. In particular, we show how to loosely couple state-of-the-art monocular depth estimation and monocular 3D human pose estimation approaches to reconstruct a hybrid map of a populated indoor scene in real time. We validate our component-level design choices via extensive experiments on the large-scale ScanNet and GTA-IM datasets. To evaluate our system-level performance, we also construct a new Oxford Hybrid Mapping dataset of populated indoor scenes.

The 2-D median filter, one of the oldest and most well-established image-filtering techniques, still sees widespread use throughout computer vision. Despite its relative algorithmic simplicity, accelerating the 2-D median filter via a hardware implementation becomes increasingly challenging as the window size increases, since the resources required grow quartically with the window size. Previous works, in a non-FPGA context, have shown that separately applying several directional median filters to an image, and then taking the median of their results, yields performance that is competitive with, and in some cases even better than, that of a classic 2-D window median. Inspired by these approaches, we propose a novel way of substituting a 2-D median filter on an FPGA with a sequence of directional median filters, in our case arranged as a pipeline, in the pursuit of an FPGA implementation that achieves better scalability and hardware efficiency without sacrificing accuracy. We empirically show that the combination of three particular directional filters, in any order, achieves this, whilst requiring quadratically fewer resources on the FPGA and allowing for much higher throughput.

The 2-D median filter, one of the oldest and most well-established image-filtering techniques, still sees widespread use throughout computer vision. Despite its relative algorithmic simplicity, accelerating the 2-D median filter via a hardware implementation becomes increasingly challenging as the window size increases, since the resources required grow quadratically with the window size. Previous works, in a non-FPGA context, have shown that applying a sequence of multiple directional median filters to an image yields results that are competitive with, and in some cases even better than, those of a classic 2-D window median. Inspired by these approaches, we propose a novel way of substituting a 2-D median filter on an FPGA with a sequence of directional median filters, in our case in the pursuit of an FPGA implementation that achieves better scalability and hardware efficiency without sacrificing accuracy. We empirically show that the combination of three particular directional filters, in any order, achieves this, whilst requiring quadratically fewer resources on the FPGA. Our approach allows for much higher throughput and is easier to implement as a pipeline.

Miscalibration -- a mismatch between a model's confidence and its correctness -- of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as opposed to the standard cross-entropy loss, focal loss (Lin et al., 2017) allows us to learn models that are already very well calibrated. When combined with temperature scaling, whilst preserving accuracy, it yields state-of-the-art calibrated models. We provide a thorough analysis of the factors causing miscalibration, and use the insights we glean from this to justify the empirically excellent performance of focal loss. To facilitate the use of focal loss in practice, we also provide a principled approach to automatically select the hyperparameter involved in the loss function. We perform extensive experiments on a variety of computer vision and NLP datasets, and with a wide variety of network architectures, and show that our approach achieves state-of-the-art calibration without compromising on accuracy in almost all cases. Code is available at https://github.com/torrvision/focal_calibration.

Camera pose estimation is an important problem in computer vision, with applications as diverse as simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques match the current image against keyframes with known poses coming from a tracker, directly regress the pose, or establish correspondences between keypoints in the current image and points in the scene in order to estimate the pose. In recent years, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but have traditionally needed to be trained offline on the target scene, preventing relocalisation in new environments. Recently, we showed how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. The adapted forests achieved relocalisation performance that was on par with that of offline forests, and our approach was able to estimate the camera pose in close to real time, which made it desirable for systems that require online relocalisation. In this paper, we present an extension of this work that achieves significantly better relocalisation performance whilst running fully in real time. To achieve this, we make several changes to the original approach: (i) instead of simply accepting the camera pose hypothesis produced by RANSAC without question, we make it possible to score the final few hypotheses it considers using a geometric approach and select the most promising one; (ii) we chain several instantiations of our relocaliser (with different parameter settings) together in a cascade, allowing us to try faster but less accurate relocalisation first, only falling back to slower, more accurate relocalisation as necessary; and (iii) we tune the parameters of our cascade, and the individual relocalisers it contains, to achieve effective overall performance. Taken together, these changes allow us to significantly improve upon the performance our original state-of-the-art method was able to achieve on the well-known 7-Scenes and Stanford 4 Scenes benchmarks. As additional contributions, we present a novel way of visualising the internal behaviour of our forests, and use the insights gleaned from this to show how to entirely circumvent the need to pre-train a forest on a generic scene.

Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training trajectory, and the latter can struggle in textureless regions. By contrast, scene coordinate regression (SCoRe) methods generalise to novel poses and can leverage dense correspondences to improve robustness, and recent work has shown how to adapt SCoRe forests between scenes, allowing their state-of-the-art performance to be leveraged online. However, because they use features hand-crafted for indoor use, they do not generalise well to harder outdoor scenes. Whilst replacing the forest with a neural network and learning suitable features for outdoor use is possible, the techniques used to adapt forests between scenes are unfortunately harder to transfer to a network context. In this paper, we address this by proposing a novel way of leveraging a network trained on one scene to predict points in another scene. Our approach replaces the appearance clustering performed by the branching structure of a regression forest with a two-step process that first uses the network to predict points in the original scene, and then uses these predicted points to look up clusters of points from the new scene. We show experimentally that our online approach achieves state-of-the-art performance on both the 7-Scenes and Cambridge Landmarks datasets, whilst running in under 300ms, making it highly effective in live scenarios.

We propose a 2D multi-level appearance representation of the human body in RGB images, spatially modelled using a fully-connected graphical model. The appearance model is based on a CNN body part detector, which uses shared features in a cascade architecture to simultaneously detect body parts with different levels of granularity. We use a fully-connected Conditional Random Field (CRF) as our spatial model, over which approximate inference is efficiently performed using the Mean-Field algorithm, implemented as a Recurrent Neural Network (RNN). The stronger visual support from body parts with different levels of granularity, along with the fully-connected pairwise spatial relations, which have their weights learnt by the model, improve the performance of the bottom-up part detector. We adopt an end-to-end training strategy to leverage the potential of both our appearance and spatial models, and achieve competitive results on the MPII and LSP datasets.

Stereo depth estimation is used for many computer vision applications. Though many popular methods strive solely for depth quality, for real-time mobile applications (e.g. prosthetic glasses or micro-UAVs), speed and power efficiency are equally, if not more, important. Many real-world systems rely on Semi-Global Matching (SGM) to achieve a good accuracy vs. speed balance, but power efficiency is hard to achieve with conventional hardware, making the use of embedded devices such as FPGAs attractive for low-power applications. However, the full SGM algorithm is ill-suited to deployment on FPGAs, and so most FPGA variants of it are partial, at the expense of accuracy. In a non-FPGA context, the accuracy of SGM has been improved by More Global Matching (MGM), which also helps tackle the streaking artifacts that afflict SGM. In this paper, we propose a novel, resource-efficient method that is inspired by MGM's techniques for improving depth quality, but which can be implemented to run in real time on a low-power FPGA. Through evaluation on multiple datasets (KITTI and Middlebury), we show that in comparison to other real-time capable stereo approaches, we can achieve a state-of-the-art balance between accuracy, power efficiency and speed, making our approach highly desirable for use in real-time systems with limited power.

Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes to the scene goes up as the capture time increases. These are good reasons to want instead to capture several smaller sub-scenes that can be joined to make the whole scene. Achieving this has traditionally been difficult: joining sub-scenes that may never have been viewed from the same angle requires a high-quality camera relocaliser that can cope with novel poses, and tracking drift in each sub-scene can prevent them from being joined to make a consistent overall scene. Recent advances, however, have significantly improved our ability to capture medium-sized sub-scenes with little to no tracking drift: real-time globally consistent reconstruction systems can close loops and re-integrate the scene surface on the fly, whilst new visual-inertial odometry approaches can significantly reduce tracking drift during live reconstruction. Moreover, high-quality regression forest-based relocalisers have recently been made more practical by the introduction of a method to allow them to be trained and used online. In this paper, we leverage these advances to present what to our knowledge is the first system to allow multiple users to collaborate interactively to reconstruct dense, voxel-based models of whole buildings using only consumer-grade hardware, a task that has traditionally been both time-consuming and dependent on the availability of specialised hardware. Using our system, an entire house or lab can be reconstructed in under half an hour and at a far lower cost than was previously possible.

In recent years, major advances have been made in 3D scene reconstruction. However, much less progress has been made for objects, which can exhibit far fewer unambiguous geometric/texture cues than a full scene, and thus are much harder to track against. In this work we present a novel probabilistic object reconstruction framework that simultaneously allows for online, implicit deformation of the objects surface to reduce tracking drift and handle loop closure events. Coupled with our probabilistic formulation is the use of a multi subsegment representation of the object, used to enforce global consistency, with segmentation of the object built in to the formulation. Finally, we employ a CRF framework to refine the overall segmentation, defined by a probability field over the object. We present compelling results over the current state-of-the-art object reconstruction work and demonstrate robustness and consistency w.r.t. established dense SLAM frameworks.

Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but must be trained offline on the target scene, preventing relocalisation in new environments. In this paper, we show how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. Our adapted forests achieve relocalisation performance that is on par with that of offline forests, and our approach runs in under 150ms, making it desirable for real-time systems that require online relocalisation.

Graph-based image segmentation is popular, because graphs can naturally represent image parts and the relationships between them. Whilst many single-scale approaches exist, significant interest has been shown in segmentation hierarchies, which represent image objects at different scales. However, segmenting arbitrary images automatically remains elusive: segmentation is under-specified, with different users expecting different outcomes. Hierarchical segmentation compounds this, since it is unclear where in the hierarchy objects should appear. Users can easily edit flat segmentations to influence the outcome, but editing hierarchical segmentations is harder: indeed, many existing interactive editing techniques make only small, local hierarchy changes. In this paper, we address this by introducing ‘zipping’ operations for segmentation hierarchies to facilitate user interaction. We use these operations to implement algorithms for non-sibling node merging and parent switching, and perform experiments on both 2D and 3D images to show that these latter algorithms can significantly reduce the interaction burden on the user.

Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes. However, since the model that they learn depends strongly on the spatial layout of the tracked object, they are notoriously sensitive to deformation. Models based on colour statistics have complementary traits: they cope well with variation in shape, but suffer when illumination is not consistent throughout a sequence. Moreover, colour distributions alone can be insufficiently discriminative. In this paper, we show that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks.

Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction) is not explicitly coupled to the objective for the tracker (estimation of object position). In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. By explicitly allowing the output space to express the needs of the tracker, we avoid the need for an intermediate classification step. Our method uses a kernelised structured output support vector machine (SVM), which is learned online to provide adaptive tracking. To allow our tracker to run at high frame rates, we (a) introduce a budgeting mechanism that prevents the unbounded growth in the number of support vectors that would otherwise occur during tracking, and (b) show how to implement tracking on the GPU. Experimentally, we show that our algorithm is able to outperform state-of-the-art trackers on various benchmark videos. Additionally, we show that we can easily incorporate additional features and kernels into our framework, which results in increased tracking performance.

It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very different materials. In this paper, we therefore present an approach that augments the available dense visual cues with sparse auditory cues in order to estimate dense object and material labels. Since estimates of object class and material properties are mutually informative, we optimise our multi-output labelling jointly using a random-field framework. We evaluate our system on a new dataset with paired visual and auditory data that we make publicly available. We demonstrate that this joint estimation of object and material labels significantly outperforms the estimation of either category in isolation.

We present an augmented reality system for large scale 3D reconstruction and recognition in outdoor scenes. Unlike existing prior work, which tries to reconstruct scenes using active depth cameras, we use a purely passive stereo setup, allowing for outdoor use and extended sensing range. Our system not only produces a map of the 3D environment in real-time, it also allows the user to draw (or 'paint') with a laser pointer directly onto the reconstruction to segment the model into objects. Given these examples our system then learns to segment other parts of the 3D map during online acquisition. Unlike typical object recognition systems, ours therefore very much places the user 'in the loop' to segment particular objects of interest, rather than learning from predefined databases. The laser pointer additionally helps to 'clean up' the stereo reconstruction and final 3D map, interactively. Using our system, within minutes, a user can capture a full 3D map, segment it into objects of interest, and refine parts of the model during capture. We provide full technical details of our system to aid replication, as well as quantitative evaluation of system components. We demonstrate the possibility of using our system for helping the visually impaired navigate through spaces. Beyond this use, our system can be used for playing large-scale augmented reality games, shared online to augment streetview data, and used for more detailed car and person navigation.

Our abilities in scene understanding, which allow us to perceive the 3D structure of our surroundings and intuitively recognise the objects we see, are things that we largely take for granted, but for robots, the task of understanding large scenes quickly remains extremely challenging. Recently, scene understanding approaches based on 3D reconstruction and semantic segmentation have become popular, but existing methods either do not scale, fail outdoors, provide only sparse reconstructions or are rather slow. In this paper, we build on a recent hash-based technique for large-scale fusion and an efficient mean-field inference algorithm for densely-connected CRFs to present what to our knowledge is the first system that can perform dense, large-scale, outdoor semantic reconstruction of a scene in (near) real time. We also present a `semantic fusion' approach that allows us to handle dynamic objects more effectively than previous approaches. We demonstrate the effectiveness of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense reconstruction and labelling of a number of scenes.