The Experts below are selected from a list of 66744 Experts worldwide ranked by ideXlab platform

Alexander G Hauptmann - One of the best experts on this subject based on the ideXlab platform.

  • simaug learning robust representations from simulation for trajectory prediction
    European Conference on Computer Vision, 2020
    Co-Authors: Junwei Liang, Lu Jiang, Alexander G Hauptmann
    Abstract:

    This paper studies the problem of predicting future trajectories of people in unseen Cameras of novel scenarios and Views. We approach this problem through the real-data-free setting in which the model is trained only on 3D simulation data and applied out-of-the-box to a wide variety of real Cameras. We propose a novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data. The key idea is to mix the feature of the hardest Camera View with the adversarial feature of the original View. We refer to our method as SimAug. We show that SimAug achieves promising results on three real-world benchmarks using zero real training data, and state-of-the-art performance in the Stanford Drone and the VIRAT/ActEV dataset when using in-domain training data. Code and models are released at https://next.cs.cmu.edu/simaug.

  • simaug learning robust representations from simulation for trajectory prediction
    arXiv: Computer Vision and Pattern Recognition, 2020
    Co-Authors: Junwei Liang, Lu Jiang, Alexander G Hauptmann
    Abstract:

    This paper studies the problem of predicting future trajectories of people in unseen Cameras of novel scenarios and Views. We approach this problem through the real-data-free setting in which the model is trained only on 3D simulation data and applied out-of-the-box to a wide variety of real Cameras. We propose a novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data. The key idea is to mix the feature of the hardest Camera View with the adversarial feature of the original View. We refer to our method as SimAug. We show that SimAug achieves promising results on three real-world benchmarks using zero real training data, and state-of-the-art performance in the Stanford Drone and the VIRAT/ActEV dataset when using in-domain training data.

J K Aggarwal - One of the best experts on this subject based on the ideXlab platform.

  • tracking human motion in structured environments using a distributed Camera system
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
    Co-Authors: Qin Cai, J K Aggarwal
    Abstract:

    This paper presents a comprehensive framework for tracking coarse human models from sequences of synchronized monocular grayscale images in multiple Camera coordinates. It demonstrates the feasibility of an end-to-end person tracking system using a unique combination of motion analysis on 3D geometry in different Camera coordinates and other existing techniques in motion detection, segmentation, and pattern recognition. The system starts with tracking from a single Camera View. When the system predicts that the active Camera will no longer have a good View of the subject of interest, tracking will be switched to another Camera which provides a better View and requires the least switching to continue tracking. The nonrigidity of the human body is addressed by matching points of the middle line of the human image, spatially and temporally, using Bayesian classification schemes. Multivariate normal distributions are employed to model class-conditional densities of the features for tracking, such as location, intensity, and geometric features. Limited degrees of occlusion are tolerated within the system. Experimental results using a prototype system are presented and the performance of the algorithm is evaluated to demonstrate its feasibility for real time applications.

Dariu M. Gavrila - One of the best experts on this subject based on the ideXlab platform.

  • multi View 3d human pose estimation in complex environment
    International Journal of Computer Vision, 2012
    Co-Authors: Michael Hofmann, Dariu M. Gavrila
    Abstract:

    We introduce a framework for unconstrained 3D human upper body pose estimation from multiple Camera Views in complex environment. Its main novelty lies in the integration of three components: single-frame pose recovery, temporal integration and model texture adaptation. Single-frame pose recovery consists of a hypothesis generation stage, in which candidate 3D poses are generated, based on probabilistic hierarchical shape matching in each Camera View. In the subsequent hypothesis verification stage, the candidate 3D poses are re-projected into the other Camera Views and ranked according to a multi-View likelihood measure. Temporal integration consists of computing K-best trajectories combining a motion model and observations in a Viterbi-style maximum-likelihood approach. Poses that lie on the best trajectories are used to generate and adapt a texture model, which in turn enriches the shape likelihood measure used for pose recovery. The multiple trajectory hypotheses are used to generate pose predictions, augmenting the 3D pose candidates generated at the next time step. We demonstrate that our approach outperforms the state-of-the-art in experiments with large and challenging real-world data from an outdoor setting.

Bjorn Ottersten - One of the best experts on this subject based on the ideXlab platform.

  • View invariant action recognition from rgb data via 3d pose estimation
    International Conference on Acoustics Speech and Signal Processing, 2019
    Co-Authors: Renato Baptista, Enjie Ghorbel, Konstantinos Papadopoulos, Girum G Demisse, Djamila Aouada, Bjorn Ottersten
    Abstract:

    In this paper, we propose a novel View-invariant action recognition method using a single monocular RGB Camera. View-invariance remains a very challenging topic in 2D action recognition due to the lack of 3D information in RGB images. Most successful approaches make use of the concept of knowledge transfer by projecting 3D synthetic data to multiple Viewpoints. Instead of relying on knowledge transfer, we propose to augment the RGB data by a third dimension by means of 3D skeleton estimation from 2D images using a CNN-based pose estimator. In order to ensure View-invariance, a pre-processing for alignment is applied followed by data expansion as a way for denoising. Finally, a Long-Short Term Memory (LSTM) architecture is used to model the temporal dependency between skeletons. The proposed network is trained to directly recognize actions from aligned 3D skeletons. The experiments performed on the challenging Northwestern-UCLA dataset show the superiority of our approach as compared to state-of-the-art ones.

Thomas Funkhouser - One of the best experts on this subject based on the ideXlab platform.

  • semantic scene completion from a single depth image
    Computer Vision and Pattern Recognition, 2017
    Co-Authors: Shuran Song, Andy Zeng, Angel X Chang, Manolis Savva, Thomas Funkhouser
    Abstract:

    This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representation of volumetric occupancy and semantic labels for a scene from a single-View depth map observation. Previous work has considered scene completion and semantic labeling of depth maps separately. However, we observe that these two problems are tightly intertwined. To leverage the coupled nature of these two tasks, we introduce the semantic scene completion network (SSCNet), an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the Camera View frustum. Our network uses a dilation-based 3D context module to efficiently expand the receptive field and enable 3D context learning. To train our network, we construct SUNCG - a manually created largescale dataset of synthetic 3D scenes with dense volumetric annotations. Our experiments demonstrate that the joint model outperforms methods addressing each task in isolation and outperforms alternative approaches on the semantic scene completion task. The dataset and code is available at http://sscnet.cs.princeton.edu.

  • semantic scene completion from a single depth image
    arXiv: Computer Vision and Pattern Recognition, 2016
    Co-Authors: Shuran Song, Andy Zeng, Angel X Chang, Manolis Savva, Thomas Funkhouser
    Abstract:

    This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representation of volumetric occupancy and semantic labels for a scene from a single-View depth map observation. Previous work has considered scene completion and semantic labeling of depth maps separately. However, we observe that these two problems are tightly intertwined. To leverage the coupled nature of these two tasks, we introduce the semantic scene completion network (SSCNet), an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the Camera View frustum. Our network uses a dilation-based 3D context module to efficiently expand the receptive field and enable 3D context learning. To train our network, we construct SUNCG - a manually created large-scale dataset of synthetic 3D scenes with dense volumetric annotations. Our experiments demonstrate that the joint model outperforms methods addressing each task in isolation and outperforms alternative approaches on the semantic scene completion task.