Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userReal-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
125
0
0.0
(
0
)
Added by
Alessio Quaglino PhD
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Event-based cameras are novel, efficient sensors inspired by the human vision system, generating an asynchronous, pixel-wise stream of data. Learning from such data is generally performed through heavy preprocessing and event integration into images. This requires buffering of possibly long sequences and can limit the response time of the inference system. In this work, we instead propose to directly use events from a DVS camera, a stream of intensity changes and their spatial coordinates. This sequence is used as the input for a novel emph{asynchronous} RNN-like architecture, the Input-filtering Neural ODEs (INODE). This is inspired by the dynamical systems and filtering literature. INODE is an extension of Neural ODEs (NODE) that allows for input signals to be continuously fed to the network, like in filtering. The approach naturally handles batches of time series with irregular time-stamps by implementing a batch forward Euler solver. INODE is trained like a standard RNN, it learns to discriminate short event sequences and to perform event-by-event online inference. We demonstrate our approach on a series of classification tasks, comparing against a set of LSTM baselines. We show that, independently of the camera resolution, INODE can outperform the baselines by a large margin on the ASL task and its on par with a much larger LSTM for the NCALTECH task. Finally, we show that INODE is accurate even when provided with very few events.
rate research
Read More
Robotic vision plays a key role for perceiving the environment in grasping applications. However, the conventional framed-based robotic vision, suffering from motion blur and low sampling rate, may not meet the automation needs of evolving industrial requirements. This paper, for the first time, proposes an event-based robotic grasping framework for multiple known and unknown objects in a cluttered scene. Compared with standard frame-based vision, neuromorphic vision has advantages of microsecond-level sampling rate and no motion blur. Building on that, the model-based and model-free approaches are developed for known and unknown objects grasping respectively. For the model-based approach, event-based multi-view approach is used to localize the objects in the scene, and then point cloud processing allows for the clustering and registering of objects. Differently, the proposed model-free approach utilizes the developed event-based object segmentation, visual servoing and grasp planning to localize, align to, and grasp the targeting object. The proposed approaches are experimentally validated with objects of different sizes, using a UR10 robot with an eye-in-hand neuromorphic camera and a Barrett hand gripper. Moreover, the robustness of the two proposed event-based grasping approaches are validated in a low-light environment. This low-light operating ability shows a great advantage over the grasping using the standard frame-based vision. Furthermore, the developed model-free approach demonstrates the advantage of dealing with unknown object without prior knowledge compared to the proposed model-based approach.
How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications. Spiking neural network (SNN), as one of the brain-inspired event-triggered computing models, has the potential to extract effective spatio-temporal features from the event streams. However, when aggregating individual events into frames with a new higher temporal resolution, existing SNN models do not attach importance to that the serial frames have different signal-to-noise ratios since event streams are sparse and non-uniform. This situation interferes with the performance of existing SNNs. In this work, we propose a temporal-wise attention SNN (TA-SNN) model to learn frame-based representation for processing event streams. Concretely, we extend the attention concept to temporal-wise input to judge the significance of frames for the final decision at the training stage, and discard the irrelevant frames at the inference stage. We demonstrate that TA-SNN models improve the accuracy of event streams classification tasks. We also study the impact of multiple-scale temporal resolutions for frame-based representation. Our approach is tested on three different classification tasks: gesture recognition, image classification, and spoken digit recognition. We report the state-of-the-art results on these tasks, and get the essential improvement of accuracy (almost 19%) for gesture recognition with only 60 ms.
Continuous deep learning architectures have recently re-emerged as Neural Ordinary Differential Equations (Neural ODEs). This infinite-depth approach theoretically bridges the gap between deep learning and dynamical systems, offering a novel perspective. However, deciphering the inner working of these models is still an open challenge, as most applications apply them as generic black-box modules. In this work we open the box, further developing the continuous-depth formulation with the aim of clarifying the influence of several design choices on the underlying dynamics.
3D hand pose estimation from monocular videos is a long-standing and challenging problem, which is now seeing a strong upturn. In this work, we address it for the first time using a single event camera, i.e., an asynchronous vision sensor reacting on brightness changes. Our EventHands approach has characteristics previously not demonstrated with a single RGB or depth camera such as high temporal resolution at low data throughputs and real-time performance at 1000 Hz. Due to the different data modality of event cameras compared to classical cameras, existing methods cannot be directly applied to and re-trained for event streams. We thus design a new neural approach which accepts a new event stream representation suitable for learning, which is trained on newly-generated synthetic event streams and can generalise to real data. Experiments show that EventHands outperforms recent monocular methods using a colour (or depth) camera in terms of accuracy and its ability to capture hand motions of unprecedented speed. Our method, the event stream simulator and the dataset will be made publicly available.
Deformable image registration, aiming to find spatial correspondence between a given image pair, is one of the most critical problems in the domain of medical image analysis. In this paper, we present a generic, fast, and accurate diffeomorphic image registration framework that leverages neural ordinary differential equations (NODEs). We model each voxel as a moving particle and consider the set of all voxels in a 3D image as a high-dimensional dynamical system whose trajectory determines the targeted deformation field. Compared with traditional optimization-based methods, our framework reduces the running time from tens of minutes to tens of seconds. Compared with recent data-driven deep learning methods, our framework is more accessible since it does not require large amounts of training data. Our experiments show that the registration results of our method outperform state-of-the-arts under various metrics, indicating that our modeling approach is well fitted for the task of deformable image registration.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
