Abstract:While gait recognition has seen many advances in recent years, the occlusion problem has largely been ignored. This problem is especially important for gait recognition from uncontrolled outdoor sequences at range - since any small obstruction can affect the recognition system. Most current methods assume the availability of complete body information while extracting the gait features. When parts of the body are occluded, these methods may hallucinate and output a corrupted gait signature as they try to look for body parts which are not present in the input at all. To address this, we exploit the learned occlusion type while extracting identity features from videos. Thus, in this work, we propose an occlusion aware gait recognition method which can be used to model intrinsic occlusion awareness into potentially any state-of-the-art gait recognition method. Our experiments on the challenging GREW and BRIAR datasets show that networks enhanced with this occlusion awareness perform better at recognition tasks than their counterparts trained on similar occlusions.
Abstract:We propose a novel concept of augmented reality (AR) human-drone interaction driven by RL-based swarm behavior to achieve intuitive and immersive control of a swarm formation of unmanned aerial vehicles. The DroneARchery system developed by us allows the user to quickly deploy a swarm of drones, generating flight paths simulating archery. The haptic interface LinkGlide delivers a tactile stimulus of the bowstring tension to the forearm to increase the precision of aiming. The swarm of released drones dynamically avoids collisions between each other, the drone following the user, and external obstacles with behavior control based on deep reinforcement learning. The developed concept was tested in the scenario with a human, where the user shoots from a virtual bow with a real drone to hit the target. The human operator observes the ballistic trajectory of the drone in an AR and achieves a realistic and highly recognizable experience of the bowstring tension through the haptic display. The experimental results revealed that the system improves trajectory prediction accuracy by 63.3% through applying AR technology and conveying haptic feedback of pulling force. DroneARchery users highlighted the naturalness (4.3 out of 5 point Likert scale) and increased confidence (4.7 out of 5) when controlling the drone. We have designed the tactile patterns to present four sliding distances (tension) and three applied force levels (stiffness) of the haptic display. Users demonstrated the ability to distinguish tactile patterns produced by the haptic display representing varying bowstring tension(average recognition rate is of 72.8%) and stiffness (average recognition rate is of 94.2%). The novelty of the research is the development of an AR-based approach for drone control that does not require special skills and training from the operator.
Abstract:Anthropomorphic robot avatars present a conceptually novel approach to remote affective communication, allowing people across the world a wider specter of emotional and social exchanges over traditional 2D and 3D image data. However, there are several limitations of current telepresence robots, such as the high weight, complexity of the system that prevents its fast deployment, and the limited workspace of the avatars mounted on either static or wheeled mobile platforms. In this paper, we present a novel concept of telecommunication through a robot avatar based on an anthropomorphic swarm of drones; SwarMan. The developed system consists of nine nanocopters controlled remotely by the operator through a gesture recognition interface. SwarMan allows operators to communicate by directly following their motions and by recognizing one of the prerecorded emotional patterns, thus rendering the captured emotion as illumination on the drones. The LSTM MediaPipe network was trained on a collected dataset of 600 short videos with five emotional gestures. The accuracy of achieved emotion recognition was 97% on the test dataset. As communication through the swarm avatar significantly changes the visual appearance of the operator, we investigated the ability of the users to recognize and respond to emotions performed by the swarm of drones. The experimental results revealed a high consistency between the users in rating emotions. Additionally, users indicated low physical demand (2.25 on the Likert scale) and were satisfied with their performance (1.38 on the Likert scale) when communicating by the SwarMan interface.
Abstract:To achieve high fidelity haptic rendering of soft objects in a high mobility virtual environment, we propose a novel haptic display DandelionTouch. The tactile actuators are delivered to the fingertips of the user by a swarm of drones. Users of DandelionTouch are capable of experiencing tactile feedback in a large space that is not limited by the device's working area. Importantly, they will not experience muscle fatigue during long interactions with virtual objects. Hand tracking and swarm control algorithm allow guiding the swarm with hand motions and avoid collisions inside the formation. Several topologies of the impedance connection between swarm units were investigated in this research. The experiment, in which drones performed a point following task on a square trajectory in real-time, revealed that drones connected in a Star topology performed the trajectory with low mean positional error (RMSE decreased by 20.6% in comparison with other impedance topologies and by 40.9% in comparison with potential field-based swarm control). The achieved velocities of the drones in all formations with impedance behavior were 28% higher than for the swarm controlled with the potential field algorithm. Additionally, the perception of several vibrotactile patterns was evaluated in a user study with 7 participants. The study has shown that the proposed combination of temporal delay and frequency modulation allows users to successfully recognize the surface property and motion direction in VR simultaneously (mean recognition rate of 70%, maximum of 93%). DandelionTouch suggests a new type of haptic feedback in VR systems where no hand-held or wearable interface is required.
Abstract:Heterogeneous teams of mobile robots and UAVs are offering a substantial benefit in an autonomous exploration of the environment. Nevertheless, although joint exploration scenarios for such systems are widely discussed, they are still suffering from low adaptability to changes in external conditions and faults of swarm agents during the UAV docking. We propose a novel vision-based drone swarm docking system for robust landing on a moving platform when one of the agents lost its position signal. The proposed SwarmHawk system relies on vision-based detection for the mobile platform tracking and navigation of its agents. Each drone of the swarm carries an RGB camera and AprilTag3 QR-code marker on board. SwarmHawk can switch between two modes of operation, acting as a homogeneous swarm in case of global UAV localization or assigning leader drones to navigate its neighbors in case of a camera fault in one of the drones or global localization failure. Two experiments were performed to evaluate SwarmHawk's performance under the global and local localization with static and moving platforms. The experimental results revealed a sufficient accuracy in the swarm landing task on a static mobile platform (error of 4.2 cm in homogeneous formation and 1.9 cm in leader-follower formation) and on moving platform (error of 6.9 cm in homogeneous formation and 4.7 cm in leader-follower formation). Moreover, the drones showed a good landing on a platform moving along a complex trajectory (average error of 19.4 cm) in leader-follower formation. The proposed SwarmHawk technology can be potentially applied in various swarm scenarios, including complex environment exploration, inspection, and drone delivery.
Abstract:The paper focuses on a heterogeneous swarm of drones to achieve a dynamic landing of formation on a moving robot. This challenging task was not yet achieved by scientists. The key technology is that instead of facilitating each agent of the swarm of drones with computer vision that considerably increases the payload and shortens the flight time, we propose to install only one camera on the leader drone. The follower drones receive the commands from the leader UAV and maintain a collision-free trajectory with the artificial potential field. The experimental results revealed a high accuracy of the swarm landing on a static mobile platform (RMSE of 4.48 cm). RMSE of swarm landing on the mobile platform moving with the maximum velocities of 1.0 m/s and 1.5 m/s equals 8.76 cm and 8.98 cm, respectively. The proposed SwarmHive technology will allow the time-saving landing of the swarm for further drone recharging. This will make it possible to achieve self-sustainable operation of a multi-agent robotic system for such scenarios as rescue operations, inspection and maintenance, autonomous warehouse inventory, cargo delivery, and etc.
Abstract:The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting approaches. Specifically, the approaches exhibit unacceptably large standard deviation wrt statistical measures (MSE, MAE). To address such concerns in a holistic manner, we make two fundamental contributions. Firstly, we modify the training pipeline to accommodate the knowledge of dataset skew. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian binning approach. More specifically, we propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage bin-aware optimization. As the second contribution, we introduce additional performance measures which are more inclusive and throw light on various comparative performance aspects of the deep networks. We also show that our binning-based modifications retain their superiority wrt the newly proposed performance measures. Overall, our contributions enable a practically useful and detail-oriented characterization of performance for crowd counting approaches.
Abstract:Withtheadventofsocialmedia,therehasbeenanextremely rapid increase in the content shared online. Consequently, the propagation of fake news and hostile messages on social media platforms has also skyrocketed. In this paper, we address the problem of detecting hostile and fake content in the Devanagari (Hindi) script as a multi-class, multi-label problem. Using NLP techniques, we build a model that makes use of an abusive language detector coupled with features extracted via Hindi BERT and Hindi FastText models and metadata. Our model achieves a 0.97 F1 score on coarse grain evaluation on Hostility detection task. Additionally, we built models to identify fake news related to Covid-19 in English tweets. We leverage entity information extracted from the tweets along with textual representations learned from word embeddings and achieve a 0.93 F1 score on the English fake news detection task.
Abstract:This research paper proposes a COVID-19 monitoring and response system to identify the surge in the volume of patients at hospitals and shortage of critical equipment like ventilators in South-east Asian countries, to understand the burden on health facilities. This can help authorities in these regions with resource planning measures to redirect resources to the regions identified by the model. Due to the lack of publicly available data on the influx of patients in hospitals, or the shortage of equipment, ICU units or hospital beds that regions in these countries might be facing, we leverage Twitter data for gleaning this information. The approach has yielded accurate results for states in India, and we are working on validating the model for the remaining countries so that it can serve as a reliable tool for authorities to monitor the burden on hospitals.
Abstract:Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data sets quickly via a general framework for building weak models, also known as labeling functions, and denoising them through ensemble learning techniques. We present a fast, simple data programming method for augmenting text data sets by generating neighborhood-based weak models with minimal supervision. Furthermore, our method employs an iterative procedure to identify sparsely distributed examples from large volumes of unlabeled data. The iterative data programming techniques improve newer weak models as more labeled data is confirmed with human-in-loop. We show empirical results on sentence classification tasks, including those from a task of improving intent recognition in conversational agents.