The Experts below are selected from a list of 43698 Experts worldwide ranked by ideXlab platform
Thomas S Huang - One of the best experts on this subject based on the ideXlab platform.
-
head Pose Estimation classification or regression
International Conference on Pattern Recognition, 2008Co-Authors: Guodong Guo, Charles R Dyer, Thomas S HuangAbstract:Head Pose Estimation has many useful applications in practice. How to estimate the head Pose automatically and robustly is still a challenging problem. In Pose Estimation, different Pose angles can be used as regression values or viewed as different class labels. Thus a question is raised in our study: which is proper for Pose Estimation - classification or regression? We investigate representative classification and regression methods on the same problem to see any difference. A method that combines regression and classification approaches is also examined. Preliminary experiments show some interesting results which might prompt further exploration of related issues in Pose Estimation.
-
subspace learning for human head Pose Estimation
International Conference on Multimedia and Expo, 2008Co-Authors: Thomas S HuangAbstract:This paper proPoses a fully automatic framework for static human head Pose Estimation. With a 2D human multi-view face image as input, the face region is detected and cropped out. Then the Pose of the face is assessed by the Pose categories. Based on the appearance of the face region, variant subspace learning methods including principal component analysis (PCA), linear discriminant analysis (LDA), locality preserving projection (LPP) and Pose-specific subspace (PSS) are proPosed for effective representation of the face Poses. Several aspects, such as human identification, illumination changes and expression variations are considered during the classification process. The experiment results on large public database demonstrate the effectiveness of the proPosed framework and recognition algorithms. Performance comparisons and discussions are also provided in detail to help the algorithm selection when designing practical face Pose Estimation systems for different scenarios.
-
graph embedded analysis for head Pose Estimation
International Conference on Automatic Face and Gesture Recognition, 2006Co-Authors: Thomas S HuangAbstract:Head Pose is an important vision cue for scene interpretation and human computer interaction. To determine the head Pose, one may consider the low-dimensional manifold structure of the face view points in image space. In this paper, we present an appearance-based strategy for head Pose Estimation using supervised graph embedding (GE) analysis. Thinking globally and fitting locally, we first construct the neighborhood weighted graph in the sense of supervised LLE. The unified projection is calculated in a closed-form solution based on the GE linearization. We then project new data (face view images) into the embedded low-dimensional subspace with the identical projection. The head Pose is finally estimated by the K-nearest neighbor classification. We test the proPosed method on 18,100 USF face view images. Experimental results show that, even using a very small training set (e.g. 10 subjects), GE achieves higher head Pose Estimation accuracy with more efficient dimensionality reduction than the existing methods.
-
head Pose Estimation in seminar room using multi view face detectors
CLEaR, 2006Co-Authors: Zhenqiu Zhang, Ming Liu, Thomas S HuangAbstract:Head Pose Estimation in low resolution is a challenge problem. Traditional Pose Estimation algorithms, which assume faces have been well aligned before Pose Estimation, would face much difficulty in this situation, since face alignment itself does not work well in this low resolution scenario. In this paper, we proPose to estimate head Pose using view-based multi-view face detectors directly. Naive Bayesian classifier is then applied to fuse the information of head Pose from multiple camera views. To model the temporal changing of head Pose, Hidden Markov Model is used to obtain the optimal sequence of head Pose with greatest likelihood.
Emre Akbas - One of the best experts on this subject based on the ideXlab platform.
-
multiPosenet fast multi person Pose Estimation using Pose residual network
European Conference on Computer Vision, 2018Co-Authors: Muhammed Kocabas, Salih Karagoz, Emre AkbasAbstract:In this paper, we present MultiPoseNet, a novel bottom-up multi-person Pose Estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, person segmentation and Pose Estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate Poses by assigning keypoints to person instances. On the COCO keypoints dataset, our Pose Estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with \(\sim 23\) frames/sec.
-
multiPosenet fast multi person Pose Estimation using Pose residual network
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Muhammed Kocabas, Salih Karagoz, Emre AkbasAbstract:In this paper, we present MultiPoseNet, a novel bottom-up multi-person Pose Estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and Pose Estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate Poses by assigning keypoints to person instances. On the COCO keypoints dataset, our Pose Estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: this https URL
Muhammed Kocabas - One of the best experts on this subject based on the ideXlab platform.
-
multiPosenet fast multi person Pose Estimation using Pose residual network
European Conference on Computer Vision, 2018Co-Authors: Muhammed Kocabas, Salih Karagoz, Emre AkbasAbstract:In this paper, we present MultiPoseNet, a novel bottom-up multi-person Pose Estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, person segmentation and Pose Estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate Poses by assigning keypoints to person instances. On the COCO keypoints dataset, our Pose Estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with \(\sim 23\) frames/sec.
-
multiPosenet fast multi person Pose Estimation using Pose residual network
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Muhammed Kocabas, Salih Karagoz, Emre AkbasAbstract:In this paper, we present MultiPoseNet, a novel bottom-up multi-person Pose Estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and Pose Estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate Poses by assigning keypoints to person instances. On the COCO keypoints dataset, our Pose Estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: this https URL
James J Little - One of the best experts on this subject based on the ideXlab platform.
-
exploiting temporal information for 3d human Pose Estimation
European Conference on Computer Vision, 2018Co-Authors: Mir Rayat Imtiaz Hossain, James J LittleAbstract:In this work, we address the problem of 3D human Pose Estimation from a sequence of 2D human Poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D Pose Estimation to train deep networks end-to-end to predict from images directly, the top-performing approaches have shown the effectiveness of dividing the task of 3D Pose Estimation into two steps: using a state-of-the-art 2D Pose estimator to estimate the 2D Pose from images and then mapping them into 3D space. They also showed that a low-dimensional representation like 2D locations of a set of joints can be discriminative enough to estimate 3D Pose with high accuracy. However, Estimation of 3D Pose for individual frames leads to temporally incoherent estimates due to independent error in each frame causing jitter. Therefore, in this work we utilize the temporal information across a sequence of 2D joint locations to estimate a sequence of 3D Poses. We designed a sequence-to-sequence network comPosed of layer-normalized LSTM units with shortcut connections connecting the input to the output on the decoder side and imPosed temporal smoothness constraint during training. We found that the knowledge of temporal consistency improves the best reported result on Human3.6M dataset by approximately \(12.2\%\) and helps our network to recover temporally consistent 3D Poses over a sequence of images even when the 2D Pose detector fails.
-
a simple yet effective baseline for 3d human Pose Estimation
arXiv: Computer Vision and Pattern Recognition, 2017Co-Authors: Julieta Martinez, Rayat Hossain, Javier Romero, James J LittleAbstract:Following the success of deep convolutional networks, state-of-the-art methods for 3d human Pose Estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d Pose (visual) understanding, or from a failure to map 2d Poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d Pose Estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d Pose Estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human Pose Estimation.
Salih Karagoz - One of the best experts on this subject based on the ideXlab platform.
-
multiPosenet fast multi person Pose Estimation using Pose residual network
European Conference on Computer Vision, 2018Co-Authors: Muhammed Kocabas, Salih Karagoz, Emre AkbasAbstract:In this paper, we present MultiPoseNet, a novel bottom-up multi-person Pose Estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, person segmentation and Pose Estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate Poses by assigning keypoints to person instances. On the COCO keypoints dataset, our Pose Estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with \(\sim 23\) frames/sec.
-
multiPosenet fast multi person Pose Estimation using Pose residual network
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Muhammed Kocabas, Salih Karagoz, Emre AkbasAbstract:In this paper, we present MultiPoseNet, a novel bottom-up multi-person Pose Estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and Pose Estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate Poses by assigning keypoints to person instances. On the COCO keypoints dataset, our Pose Estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: this https URL
