In-field human motion capture (HMC) is drawing increasing attention due to the multitude of application areas. Plenty of research is currently invested in camera-based (markerless) HMC, with the advantage of no infrastructure being required on the body, and additional context information being available from the surroundings. However, the inherent drawbacks of camera-based approaches are the limited field of view and occlusions.
View Article and Find Full Text PDFRecently, transformer architectures have shown superior performance compared to their CNN counterparts in many computer vision tasks. The self-attention mechanism enables transformer networks to connect visual dependencies over short as well as long distances, thus generating a large, sometimes even a global receptive field. In this paper, we propose our Parallel Local-Global Vision Transformer (PLG-ViT), a general backbone model that fuses local window self-attention with global self-attention.
View Article and Find Full Text PDFIn-car activity monitoring is a key enabler of various automotive safety functions. Existing approaches are largely based on vision systems. Radar, however, can provide a low-cost, privacy-preserving alternative.
View Article and Find Full Text PDFThis paper presents a novel architecture for simultaneous estimation of highly accurate optical flows and rigid scene transformations for difficult scenarios where the brightness assumption is violated by strong shading changes. In the case of rotating objects or moving light sources, such as those encountered for driving cars in the dark, the scene appearance often changes significantly from one view to the next. Unfortunately, standard methods for calculating optical flows or poses are based on the expectation that the appearance of features in the scene remains constant between views.
View Article and Find Full Text PDFObject detection is a computer vision task that involves localisation and classification of objects in an image. Video data implicitly introduces several challenges, such as blur, occlusion and defocus, making video object detection more challenging in comparison to still image object detection, which is performed on individual and independent images. This paper tackles these challenges by proposing an attention-heavy framework for video object detection that aggregates the disentangled features extracted from individual frames.
View Article and Find Full Text PDFSupervised image-to-image translation has been proven to generate realistic images with sharp details and to have good quantitative performance. Such methods are trained on a paired dataset, where an image from the source domain already has a corresponding translated image in the target domain. However, this paired dataset requirement imposes a huge practical constraint, requires domain knowledge or is even impossible to obtain in certain cases.
View Article and Find Full Text PDFAugmented reality (AR), combining virtual elements with the real world, has demonstrated impressive results in a variety of application fields and gained significant research attention in recent years due to its limitless potential [...
View Article and Find Full Text PDFDepth maps produced by LiDAR-based approaches are sparse. Even high-end LiDAR sensors produce highly sparse depth maps, which are also noisy around the object boundaries. Depth completion is the task of generating a dense depth map from a sparse depth map.
View Article and Find Full Text PDFPerforming 3D reconstruction from a single 2D input is a challenging problem that is trending in literature. Until recently, it was an ill-posed optimization problem, but with the advent of learning-based methods, the performance of 3D reconstruction has also significantly improved. Infinitely many different 3D objects can be projected onto the same 2D plane, which makes the reconstruction task very difficult.
View Article and Find Full Text PDFThe generally unsupervised nature of autoencoder models implies that the main training metric is formulated as the error between input images and their corresponding reconstructions. Different reconstruction loss variations and latent space regularizations have been shown to improve model performances depending on the tasks to solve and to induce new desirable properties such as disentanglement. Nevertheless, measuring the success in, or enforcing properties by, the input pixel space is a challenging endeavour.
View Article and Find Full Text PDFWe present TIMo (ime-of-flight ndoor nitoring), a dataset for video-based monitoring of indoor spaces captured using a time-of-flight (ToF) camera. The resulting depth videos feature people performing a set of different predefined actions, for which we provide detailed annotations. Person detection for people counting and anomaly detection are the two targeted applications.
View Article and Find Full Text PDFIn recent years, due to the advancements in machine learning, object detection has become a mainstream task in the computer vision domain. The first phase of object detection is to find the regions where objects can exist. With the improvements in deep learning, traditional approaches, such as sliding windows and manual feature selection techniques, have been replaced with deep learning techniques.
View Article and Find Full Text PDFThe problem of accurate three-dimensional reconstruction is important for many research and industrial applications. Light field depth estimation utilizes many observations of the scene and hence can provide accurate reconstruction. We present a method, which enhances existing reconstruction algorithm with per-layer disparity filtering and consistency-based holes filling.
View Article and Find Full Text PDFElectroencephalogram (EEG) is widely used for the diagnosis of neurological conditions like epilepsy, neurodegenerative illnesses and sleep related disorders. Proper interpretation of EEG recordings requires the expertise of trained neurologists, a resource which is scarce in the developing world. Neurologists spend a significant portion of their time sifting through EEG recordings looking for abnormalities.
View Article and Find Full Text PDFIn this paper, we present the idea of Self Supervised learning on the shape completion and classification of point clouds. Most 3D shape completion pipelines utilize AutoEncoders to extract features from point clouds used in downstream tasks such as classification, segmentation, detection, and other related applications. Our idea is to add contrastive learning into AutoEncoders to encourage global feature learning of the point cloud classes.
View Article and Find Full Text PDFIEEE Trans Pattern Anal Mach Intell
December 2022
3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. Existing methods addressing it directly regress hand meshes via 2D convolutional neural networks, which leads to artifacts due to perspective distortions in the images. To address the limitations of the existing methods, we develop HandVoxNet++, i.
View Article and Find Full Text PDFTable detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparativelyightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre- and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions.
View Article and Find Full Text PDFIn this paper, we propose two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation. Our first approach "PointsToRotation" is based on a Deep Neural Network alone, whereas our second approach "PointsToPose" is a hybrid model combining Deep Learning and a voting-based mechanism. Our methods utilize a point cloud estimator, which we trained on multi-view infrared images in a semi-supervised manner, generating point clouds based on one image only.
View Article and Find Full Text PDFRecent progress in deep learning has led to accurate and efficient generic object detection networks. Training of highly reliable models depends on large datasets with highly textured and rich images. However, in real-world scenarios, the performance of the generic object detection system decreases when (i) occlusions hide the objects, (ii) objects are present in low-light images, or (iii) they are merged with background information.
View Article and Find Full Text PDFEstimation and tracking of 6DoF poses of objects in images is a challenging problem of great importance for robotic interaction and augmented reality. Recent approaches applying deep neural networks for pose estimation have shown encouraging results. However, most of them rely on training with real images of objects with severe limitations concerning ground truth pose acquisition, full coverage of possible poses, and training dataset scaling and generalization capability.
View Article and Find Full Text PDFThe estimation of human hand pose has become the basis for many vital applications where the user depends mainly on the hand pose as a system input. Virtual reality (VR) headset, shadow dexterous hand and in-air signature verification are a few examples of applications that require to track the hand movements in real-time. The state-of-the-art 3D hand pose estimation methods are based on the Convolutional Neural Network (CNN).
View Article and Find Full Text PDFRecovery of articulated 3D structure from 2D observations is a challenging computer vision problem with many applications. Current learning-based approaches achieve state-of-the-art accuracy on public benchmarks but are restricted to specific types of objects and motions covered by the training datasets. Model-based approaches do not rely on training data but show lower accuracy on these datasets.
View Article and Find Full Text PDFHand shape and pose recovery is essential for many computer vision applications such as animation of a personalized hand mesh in a virtual environment. Although there are many hand pose estimation methods, only a few deep learning based algorithms target 3D hand shape and pose from a single RGB or depth image. Jointly estimating hand shape and pose is very challenging because none of the existing real benchmarks provides ground truth hand shape.
View Article and Find Full Text PDFSynchronization of behavior such as gestures or postures is assumed to serve crucial functions in social interaction but has been poorly studied to date in schizophrenia. Using a virtual collaborative environment (VCS), we tested 1) whether synchronization of behavior, i.e.
View Article and Find Full Text PDF