Robert B. Fisher

Can Pu, Chuanyu Yang, Jinnian Pu et al.

To enable a mobile manipulator to perform human tasks from a single teaching demonstration is vital to flexible manufacturing. We call our proposed method MMPA (Mobile Manipulator Process Automation with One-shot Teaching). Currently, there is no effective and robust MMPA framework which is not influenced by harsh industrial environments and the mobile base's parking precision. The proposed MMPA framework consists of two stages: collecting data (mobile base's location, environment information, end-effector's path) in the teaching stage for robot learning; letting the end-effector repeat the nearly same path as the reference path in the world frame to reproduce the work in the automation stage. More specifically, in the automation stage, the robot navigates to the specified location without the need of a precise parking. Then, based on colored point cloud registration, the proposed IPE (Iterative Pose Estimation by Eye & Hand) algorithm could estimate the accurate 6D relative parking pose of the robot arm base without the need of any marker. Finally, the robot could learn the error compensation from the parking pose's bias to modify the end-effector's path to make it repeat a nearly same path in the world coordinate system as recorded in the teaching stage. Hundreds of trials have been conducted with a real mobile manipulator to show the superior robustness of the system and the accuracy of the process automation regardless of the harsh industrial conditions and parking precision. For the released code, please contact marketing@amigaga.com

Chen Long-fei, Robert B. Fisher

A new application for real-time monitoring of the lack of movement in older adults' own homes is proposed, aiming to support people's lives and independence in their later years. A lightweight camera monitoring system, based on an RGB-D camera and a compact computer processor, was developed and piloted in community homes to observe the daily behavior of older adults. Instances of body inactivity were detected in everyday scenarios anonymously and unobtrusively. These events can be explained at a higher level, such as a loss of consciousness or physiological deterioration. The accuracy of the inactivity monitoring system is assessed, and statistics of inactivity events related to the daily behavior of older adults are provided. The results demonstrate that our method achieves high accuracy in inactivity detection across various environments and camera views. It outperforms existing state-of-the-art vision-based models in challenging conditions like dim room lighting and TV flickering. However, the proposed method does require some ambient light to function effectively.

Hanz Cuevas-Velasquez, Alejandro Galán-Cuenca, Antonio Javier Gallego et al.

Three-dimensional data registration is an established yet challenging problem that is key in many different applications, such as mapping the environment for autonomous vehicles, and modeling objects and people for avatar creation, among many others. Registration refers to the process of mapping multiple data into the same coordinate system by means of matching correspondences and transformation estimation. Novel proposals exploit the benefits of deep learning architectures for this purpose, as they learn the best features for the data, providing better matches and hence results. However, the state of the art is usually focused on cases of relatively small transformations, although in certain applications and in a real and practical environment, large transformations are very common. In this paper, we present ReLaTo (Registration for Large Transformations), an architecture that faces the cases where large transformations happen while maintaining good performance for local transformations. This proposal uses a novel Softmax pooling layer to find correspondences in a bilateral consensus manner between two point sets, sampling the most confident matches. These matches are used to estimate a coarse and global registration using weighted Singular Value Decomposition (SVD). A target-guided denoising step is then applied to both the obtained matches and latent features, estimating the final fine registration considering the local geometry. All these steps are carried out following an end-to-end approach, which has been shown to improve 10 state-of-the-art registration methods in two datasets commonly used for this task (ModelNet40 and KITTI), especially in the case of large transformations.

Chen Long-fei, Muhammad Ahmed Raza, Craig Innes et al.

Aging and chronic conditions affect older adults' daily lives, making early detection of developing health issues crucial. Weakness, common in many conditions, alters physical movements and daily activities subtly. However, detecting such changes can be challenging due to their subtle and gradual nature. To address this, we employ a non-intrusive camera sensor to monitor individuals' daily sitting and relaxing activities for signs of weakness. We simulate weakness in healthy subjects by having them perform physical exercise and observing the behavioral changes in their daily activities before and after workouts. The proposed system captures fine-grained features related to body motion, inactivity, and environmental context in real-time while prioritizing privacy. A Bayesian Network is used to model the relationships between features, activities, and health conditions. We aim to identify specific features and activities that indicate such changes and determine the most suitable time scale for observing the change. Results show 0.97 accuracy in distinguishing simulated weakness at the daily level. Fine-grained behavioral features, including non-dominant upper body motion speed and scale, and inactivity distribution, along with a 300-second window, are found most effective. However, individual-specific models are recommended as no universal set of optimal features and activities was identified across all participants.

Sun Zhaole, Jihong Zhu, Robert B. Fisher

Deformable linear object (DLO) manipulation is needed in many fields. Previous research on deformable linear object (DLO) manipulation has primarily involved parallel jaw gripper manipulation with fixed grasping positions. However, the potential for dexterous manipulation of DLOs using an anthropomorphic hand is under-explored. We present DexDLO, a model-free framework that learns dexterous dynamic manipulation policies for deformable linear objects with a fixed-base dexterous hand in an end-to-end way. By abstracting several common DLO manipulation tasks into goal-conditioned tasks, our DexDLO can perform these tasks, such as DLO grabbing, DLO pulling, DLO end-tip position controlling, etc. Using the Mujoco physics simulator, we demonstrate that our framework can efficiently and effectively learn five different DLO manipulation tasks with the same framework parameters. We further provide a thorough analysis of learned policies, reward functions, and reduced observations for a comprehensive understanding of the framework.

Can Pu, Chuanyu Yang, Jinnian Pu et al.

Recovering an outdoor environment's surface mesh is vital for an agricultural robot during task planning and remote visualization. Our proposed solution is based on a newly-designed panoramic stereo camera along with a hybrid novel software framework that consists of three fusion modules. The panoramic stereo camera with a pentagon shape consists of 5 stereo vision camera pairs to stream synchronized panoramic stereo images for the following three fusion modules. In the disparity fusion module, rectified stereo images produce the initial disparity maps using multiple stereo vision algorithms. Then, these initial disparity maps, along with the intensity images, are input into a disparity fusion network to produce refined disparity maps. Next, the refined disparity maps are converted into full-view point clouds or single-view point clouds for the pose fusion module. The pose fusion module adopts a two-stage global-coarse-to-local-fine strategy. In the first stage, each pair of full-view point clouds is registered by a global point cloud matching algorithm to estimate the transformation for a global pose graph's edge, which effectively implements loop closure. In the second stage, a local point cloud matching algorithm is used to match single-view point clouds in different nodes. Next, we locally refine the poses of all corresponding edges in the global pose graph using three proposed rules, thus constructing a refined pose graph. The refined pose graph is optimized to produce a global pose trajectory for volumetric fusion. In the volumetric fusion module, the global poses of all the nodes are used to integrate the single-view point clouds into the volume to produce the mesh of the whole garden. The proposed framework and its three fusion modules are tested on a real outdoor garden dataset to show the superiority of the performance.

Jie Zhang, Robert B. Fisher

The lip is a dominant dynamic facial unit when a person is speaking. Detecting lip events is beneficial to speech analysis and support for the hearing impaired. This paper proposes a 3D lip event detection pipeline that automatically determines the lip events from a 3D speaking lip sequence. We define a motion divergence measure using 3D lip landmarks to quantify the interframe dynamics of a 3D speaking lip. Then, we cast the interframe motion detection in a multi-temporal-resolution framework that allows the detection to be applicable to different speaking speeds. The experiments on the S3DFM Dataset investigate the overall 3D lip dynamics based on the proposed motion divergence. The proposed 3D pipeline is able to detect opening and closing lip events across 100 sequences, achieving a state-of-the-art performance.

Li Nanbo, Cian Eastwood, Robert B. Fisher

Learning object-centric representations of multi-object scenes is a promising approach towards machine intelligence, facilitating high-level reasoning and control from visual sensory data. However, current approaches for unsupervised object-centric scene representation are incapable of aggregating information from multiple observations of a scene. As a result, these "single-view" methods form their representations of a 3D scene based only on a single 2D observation (view). Naturally, this leads to several inaccuracies, with these methods falling victim to single-view spatial ambiguities. To address this, we propose The Multi-View and Multi-Object Network (MulMON) -- a method for learning accurate, object-centric representations of multi-object scenes by leveraging multiple views. In order to sidestep the main technical difficulty of the multi-object-multi-view scenario -- maintaining object correspondences across views -- MulMON iteratively updates the latent object representations for a scene over multiple views. To ensure that these iterative updates do indeed aggregate spatial information to form a complete 3D scene understanding, MulMON is asked to predict the appearance of the scene from novel viewpoints during training. Through experiments, we show that MulMON better-resolves spatial ambiguities than single-view methods -- learning more accurate and disentangled object representations -- and also achieves new functionality in predicting object segmentations for novel viewpoints.

Li Nanbo, Muhammad Ahmed Raza, Hu Wenbin et al.

Learning object-centric scene representations is essential for attaining structural understanding and abstraction of complex scenes. Yet, as current approaches for unsupervised object-centric representation learning are built upon either a stationary observer assumption or a static scene assumption, they often: i) suffer single-view spatial ambiguities, or ii) infer incorrectly or inaccurately object representations from dynamic scenes. To address this, we propose Dynamics-aware Multi-Object Network (DyMON), a method that broadens the scope of multi-view object-centric representation learning to dynamic scenes. We train DyMON on multi-view-dynamic-scene data and show that DyMON learns -- without supervision -- to factorize the entangled effects of observer motions and scene object dynamics from a sequence of observations, and constructs scene object spatial representations suitable for rendering at arbitrary times (querying across time) and from arbitrary viewpoints (querying across space). We also show that the factorized scene representations (w.r.t. objects) support querying about a single object by space and time independently.

Hanz Cuevas-Velasquez, Antonio Javier Gallego, Robert B. Fisher

We present an innovative two-headed attention layer that combines geometric and latent features to segment a 3D scene into semantically meaningful subsets. Each head combines local and global information, using either the geometric or latent features, of a neighborhood of points and uses this information to learn better local relationships. This Geometric-Latent attention layer (Ge-Latto) is combined with a sub-sampling strategy to capture global features. Our method is invariant to permutation thanks to the use of shared-MLP layers, and it can also be used with point clouds with varying densities because the local attention layer does not depend on the neighbor order. Our proposal is simple yet robust, which allows it to achieve competitive results in the ShapeNetPart and ModelNet40 datasets, and the state-of-the-art when segmenting the complex dataset S3DIS, with 69.2% IoU on Area 5, and 89.7% overall accuracy using K-fold cross-validation on the 6 areas.

Victor Villena-Martinez, Sergiu Oprea, Marcelo Saval-Calvo et al.

Registration is the process that computes the transformation that aligns sets of data. Commonly, a registration process can be divided into four main steps: target selection, feature extraction, feature matching, and transform computation for the alignment. The accuracy of the result depends on multiple factors, the most significant are the quantity of input data, the presence of noise, outliers and occlusions, the quality of the extracted features, real-time requirements and the type of transformation, especially those ones defined by multiple parameters, like non-rigid deformations. Recent advancements in machine learning could be a turning point in these issues, particularly with the development of deep learning (DL) techniques, which are helping to improve multiple computer vision problems through an abstract understanding of the input data. In this paper, a review of deep learning-based registration methods is presented. We classify the different papers proposing a framework extracted from the traditional registration pipeline to analyse the new learning-based proposal strengths. Deep Registration Networks (DRNs) try to solve the alignment task either replacing part of the traditional pipeline with a network or fully solving the registration problem. The main conclusions extracted are, on the one hand, 1) learning-based registration techniques cannot always be clearly classified in the traditional pipeline. 2) These approaches allow more complex inputs like conceptual models as well as the traditional 3D datasets. 3) In spite of the generality of learning, the current proposals are still ad hoc solutions. Finally, 4) this is a young topic that still requires a large effort to reach general solutions able to cope with the problems that affect traditional approaches.

Antonio-Javier Gallego, Jorge Calvo-Zaragoza, Robert B. Fisher

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as domain adaptation. Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected set is then added to the source training set by considering the labels provided by the network as ground truth, and the process is repeated until all target samples are labelled. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms.

Ammar Mahmood, Ana Giraldo Ospina, Mohammed Bennamoun et al.

Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, like kelps. This paper presents an automatic hierarchical classification method (local binary classification as opposed to the conventional flat classification) to classify kelps in images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned feature representations extracted from deep residual networks. We show that these generic features outperform the traditional off-the-shelf CNN features and the conventional hand-crafted features. Experiments also demonstrate that the hierarchical classification method outperforms the traditional parallel multi-class classifications by a significant margin (90.0% vs 57.6% and 77.2% vs 59.0%) on Benthoz15 and Rottnest datasets respectively. Furthermore, we compare different hierarchical classification approaches and experimentally show that the sibling hierarchical training approach outperforms the inclusive hierarchical approach by a significant margin. We also report an application of our proposed method to study the change in kelp cover over time for annually repeated AUV surveys.

Can Pu, Robert B. Fisher

Existing disparity fusion methods based on deep learning achieve state-of-the-art performance, but they require ground truth disparity data to train. As far as I know, this is the first time an unsupervised disparity fusion not using ground truth disparity data has been proposed. In this paper, a mathematical model for disparity fusion is proposed to guide an adversarial network to train effectively without ground truth disparity data. The initial disparity maps are inputted from the left view along with auxiliary information (gradient, left & right intensity image) into the refiner and the refiner is trained to output the refined disparity map registered on the left view. The refined left disparity map and left intensity image are used to reconstruct a fake right intensity image. Finally, the fake and real right intensity images (from the right stereo vision camera) are fed into the discriminator. In the model, the refiner is trained to output a refined disparity value close to the weighted sum of the disparity inputs for global initialisation. Then, three refinement principles are adopted to refine the results further. (1) The reconstructed intensity error between the fake and real right intensity image is minimised. (2) The similarities between the fake and real right image in different receptive fields are maximised. (3) The refined disparity map is smoothed based on the corresponding intensity image. The adversarial networks' architectures are effective for the fusion task. The fusion time using the proposed network is small. The network can achieve 90 fps using Nvidia Geforce GTX 1080Ti on the Kitti2015 dataset when the input resolution is 1242 * 375 (Width * Height) without downsampling and cropping. The accuracy of this work is equal to (or better than) the state-of-the-art supervised methods.

Nicola Strisciuglio, Radim Tylecek, Michael Blaich et al.

Robots are increasingly present in modern industry and also in everyday life. Their applications range from health-related situations, for assistance to elderly people or in surgical operations, to automatic and driver-less vehicles (on wheels or flying) or for driving assistance. Recently, an interest towards robotics applied in agriculture and gardening has arisen, with applications to automatic seeding and cropping or to plant disease control, etc. Autonomous lawn mowers are succesful market applications of gardening robotics. In this paper, we present a novel robot that is developed within the TrimBot2020 project, funded by the EU H2020 program. The project aims at prototyping the first outdoor robot for automatic bush trimming and rose pruning.

Hanz Cuevas-Velasquez, Nanbo Li, Radim Tylecek et al.

Visual servoing is a well-known task in robotics. However, there are still challenges when multiple visual sources are combined to accurately guide the robot or occlusions appear. In this paper we present a novel visual servoing approach using hybrid multi-camera input data to lead a robot arm accurately to dynamically moving target points in the presence of partial occlusions. The approach uses four RGBD sensors as Eye-to-Hand (EtoH) visual input, and an arm-mounted stereo camera as Eye-in-Hand (EinH). A Master supervisor task selects between using the EtoH or the EinH, depending on the distance between the robot and target. The Master also selects the subset of EtoH cameras that best perceive the target. When the EinH sensor is used, if the target becomes occluded or goes out of the sensor's view-frustum, the Master switches back to the EtoH sensors to re-track the object. Using this adaptive visual input data, the robot is then controlled using an iterative planner that uses position, orientation and joint configuration to estimate the trajectory. Since the target is dynamic, this trajectory is updated every time-step. Experiments show good performance in four different situations: tracking a ball, targeting a bulls-eye, guiding a straw to a mouth and delivering an item to a moving hand. The experiments cover both simple situations such as a ball that is mostly visible from all cameras, and more complex situations such as the mouth which is partially occluded from some of the sensors.

Marcelo Saval-Calvo, Jorge Azorin-Lopez, Andres Fuster-Guillo et al.

Research into object deformations using computer vision techniques has been under intense study in recent years. A widely used technique is 3D non-rigid registration to estimate the transformation between two instances of a deforming structure. Despite many previous developments on this topic, it remains a challenging problem. In this paper we propose a novel approach to non-rigid registration combining two data spaces in order to robustly calculate the correspondences and transformation between two data sets. In particular, we use point color as well as 3D location as these are the common outputs of RGB-D cameras. We have propose the Color Coherent Point Drift (CCPD) algorithm (an extension of the CPD method [1]). Evaluation is performed using synthetic and real data. The synthetic data includes easy shapes that allow evaluation of the effect of noise, outliers and missing data. Moreover, an evaluation of realistic figures obtained using Blensor is carried out. Real data acquired using a general purpose Primesense Carmine sensor is used to validate the CCPD for real shapes. For all tests, the proposed method is compared to the original CPD showing better results in registration accuracy in most cases.

Jie Zhang, Christos Maniatis, Luis Horna et al.

The availability of high-speed 3D video sensors has greatly facilitated 3D shape acquisition of dynamic and deformable objects, but high frame rate 3D reconstruction is always degraded by spatial noise and temporal fluctuations. This paper presents a simple yet powerful intensity video guided multi-frame 4D fusion pipeline. Temporal tracking of intensity image points (of moving and deforming objects) allows registration of the corresponding 3D data points, whose 3D noise and fluctuations are then reduced by spatio-temporal multi-frame 4D fusion. We conducted simulated noise tests and real experiments on four 3D objects using a 1000 fps 3D video sensor. The results demonstrate that the proposed algorithm is effective at reducing 3D noise and is robust against intensity noise. It outperforms existing algorithms with good scalability on both stationary and dynamic objects.

Christos Maniatis, Marcelo Saval-Calvo, Radim Tylecek et al.

The problem of finding a next best viewpoint for 3D modeling or scene mapping has been explored in computer vision over the last decade. This paper tackles a similar problem, but with different characteristics. It proposes a method for dynamic next best viewpoint recovery of a target point while avoiding possible occlusions. Since the environment can change, the method has to iteratively find the next best view with a global understanding of the free and occupied parts. We model the problem as a set of possible viewpoints which correspond to the centers of the facets of a virtual tessellated hemisphere covering the scene. Taking into account occlusions, distances between current and future viewpoints, quality of the viewpoint and joint constraints (robot arm joint distances or limits), we evaluate the next best viewpoint. The proposal has been evaluated on 8 different scenarios with different occlusions and a short 3D video sequence to validate its dynamic performance.

Erik Rodner, Marcel Simon, Robert B. Fisher et al.

In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to image transformations encountered during wild image capture?; (2) how can we predict CNN sensitivity?; and (3) can we increase the robustness of CNNs with respect to image degradations? To answer the first question, we provide an extensive empirical sensitivity analysis of commonly used CNN architectures (AlexNet, VGG19, GoogleNet) across various types of image degradations. This allows for predicting CNN performance for new domains comprised by images of lower quality or captured from a different viewpoint. We also show how the sensitivity of CNN outputs can be predicted for single images. Furthermore, we demonstrate that input layer dropout or pre-filtering during test time only reduces CNN sensitivity for high levels of degradation. Experiments for fine-grained recognition tasks reveal that VGG19 is more robust to severe image degradations than AlexNet and GoogleNet. However, small intensity noise can lead to dramatic changes in CNN performance even for VGG19.

Han Gong, Graham D. Finlayson, Robert B. Fisher

Color transfer is an image editing process that adjusts the colors of a picture to match a target picture's color theme. A natural color transfer not only matches the color styles but also prevents after-transfer artifacts due to image compression, noise, and gradient smoothness change. The recently discovered color homography theorem proves that colors across a change in photometric viewing condition are related by a homography. In this paper, we propose a color-homography-based color transfer decomposition which encodes color transfer as a combination of chromaticity shift and shading adjustment. A powerful form of shading adjustment is shown to be a global shading curve by which the same shading homography can be applied elsewhere. Our experiments show that the proposed color transfer decomposition provides a very close approximation to many popular color transfer methods. The advantage of our approach is that the learned color transfer can be applied to many other images (e.g. other frames in a video), instead of a frame-to-frame basis. We demonstrate two applications for color transfer enhancement and video color grading re-application. This simple model of color transfer is also important for future color transfer algorithm design.

Graham D. Finlayson, Han Gong, Robert B. Fisher

Homographies -- a mathematical formalism for relating image points across different camera viewpoints -- are at the foundations of geometric methods in computer vision and are used in geometric camera calibration, image registration, and stereo vision and other tasks. In this paper, we show the surprising result that colors across a change in viewing condition (changing light color, shading and camera) are also related by a homography. We propose a new color correction method based on color homography. Experiments demonstrate that solving the color homography problem leads to more accurate calibration.

Graham D. Finlayson, Han Gong, Robert B. Fisher

We show the surprising result that colors across a change in viewing condition (changing light color, shading and camera) are related by a homography. Our homography color correction application delivers improved color fidelity compared with the linear least-square.