No file available
To read the file of this research,
you can request a copy directly from the authors.
RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation
Preprints and early-stage research may not have been peer reviewed yet.
Abstract
We propose a novel efficient and lightweight model for human pose estimation from a single image. Our model is designed to achieve competitive results at a fraction of the number of parameters and computational cost of various state-of-the-art methods. To this end, we explicitly incorporate part-based structural and geometric priors in a hierarchical prediction framework. At the coarsest resolution, and in a manner similar to classical part-based approaches, we leverage the kinematic structure of the human body to propagate convolutional feature updates between the keypoints or body parts. Unlike classical approaches, we adopt end-to-end training to learn this geometric prior through feature updates from data. We then propagate the feature representation at the coarsest resolution up the hierarchy to refine the predicted pose in a coarse-to-fine fashion. The final network effectively models the geometric prior and intuition within a lightweight deep neural network, yielding state-of-the-art results for a model of this size on two standard datasets, Leeds Sports Pose and MPII Human Pose.
... Therefore, other detection methods based on heatmap regression are used. In reference [24][25][26] , the heatmap detection method is used to obtain the probability distribution and location information of the joint points. This method usually has higher prediction accuracy than coordinate regression. ...
... With deep learning gradually becoming the mainstream method in the field of computer vision, human posture estimation technology has developed rapidly. However, 2D human posture estimation 14,15,17,18,[23][24][25][26][27][28] only uses RGB single-modal information, lacks spatial generalization ability, and is greatly affected by lighting, texture, and wrinkles of the subject's clothing. At the same time, the most common way of existing multimodal fusion is to use RGB modality and depth modality as inputs to the network at the same time. ...
In rehabilitation medicine, real-time analysis of the gait for human wearing lower-limb exoskeleton rehabilitation robot during walking can effectively prevent patients from experiencing excessive and asymmetric gait during rehabilitation training, thereby avoiding falls or even secondary injuries. To address the above situation, we propose a gait detection method based on computer vision for the real-time monitoring of gait during human–machine integrated walking. Specifically, we design a neural network model called GaitPoseNet, which is used for posture recognition in human–machine integrated walking. Using RGB images as input and depth features as output, regression of joint coordinates through depth estimation of implicit supervised networks. In addition, joint guidance strategy (JGS) is designed in the network framework. The degree of correlation between the various joints of the human body is used as a detection target to effectively overcome prediction difficulties due to partial joint occlusion during walking. Finally, a post processing algorithm is designed to describe patients’ walking motion by combining the pixel coordinates of each joint point and leg length. Our advantage is that we provide a non-contact measurement method with strong universality, and use depth estimation and JGS to improve measurement accuracy. Conducting experiments on the Walking Pose with Exoskeleton (WPE) Dataset shows that our method can reach 95.77% PCKs@0.1, 93.14% PCKs@0.08 and 3.55 ms runtime. Therefore our method achieves advanced performance considering both speed and accuracy.
Random data augmentation is a critical technique to avoid overfitting in training deep neural network models. However, data augmentation and network training are usually treated as two isolated processes, limiting the effectiveness of network training. Why not jointly optimize the two? We propose adversarial data augmentation to address this limitation. The main idea is to design an augmentation network (generator) that competes against a target network (discriminator) by generating "hard" augmentation operations online. The augmentation network explores the weaknesses of the target network, while the latter learns from "hard" augmentations to achieve better performance. We also design a reward/penalty strategy for effective joint training. We demonstrate our approach on the problem of human pose estimation and carry out a comprehensive experimental analysis, showing that our method can significantly improve state-of-the-art models without additional data efforts.
This work is on landmark localization using binarized approximations of Convolutional Neural Networks (CNNs). Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost performance. (b) Based on our analysis, we propose a novel hierarchical, parallel and multi-scale residual block architecture that yields large performance improvement over the standard bottleneck block when having the same number of parameters, thus bridging the gap between the original network and its binarized counterpart. (c) We also show that the performance boost offered by the proposed architecture is not only observed for the case of binary networks but also generalizes for the case of real valued weights and activations. (d) We perform a large number of ablation studies that shed light on the properties and the performance of the proposed block. (e) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance. Code can be download from http://www.cs.nott.ac.uk/~psxab5/binary-cnn-landmarks/
This paper is on human pose estimation using Convolutional Neural Networks. Our main contribution is a CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for the case of severe part occlusions. To this end, we propose a detection-followed-by-regression CNN cascade. The first part of our cascade outputs part detection heatmaps and the second part performs regression on these heatmaps. The benefits of the proposed architecture are multi-fold: It guides the network where to focus in the image and effectively encodes part constraints and context. More importantly, it can effectively cope with occlusions because part detection heatmaps for occluded parts provide low confidence scores which subsequently guide the regression part of our network to rely on contextual information in order to predict the location of these parts. Additionally, we show that the proposed cascade is flexible enough to readily allow the integration of various CNN architectures for both detection and regression, including recent ones based on residual learning. Finally, we illustrate that our cascade achieves top performance on the MPII and LSP data sets. Code can be downloaded from http://www.cs.nott.ac.uk/~psxab5/
Human pose estimation has made significant progress during the last years. However current datasets are limited in their coverage of the overall pose estimation challenges. Still these serve as the common sources to evaluate, train and compare different models on. In this paper we intro-duce a novel benchmark "MPII Human Pose" 1 that makes a significant advance in terms of diversity and difficulty, a contribution that we feel is required for future develop-ments in human body models. This comprehensive dataset was collected using an established taxonomy of over 800 human activities [1]. The collected images cover a wider variety of human activities than previous datasets including various recreational, occupational and householding activ-ities, and capture people from a wider range of viewpoints. We provide a rich set of labels including positions of body joints, full 3D torso and head orientation, occlusion labels for joints and body parts, and activity labels. For each im-age we provide adjacent video frames to facilitate the use of motion information. Given these rich annotations we per-form a detailed analysis of leading human pose estimation approaches and gaining insights for the success and fail-ures of these methods.
Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators. Theoretically, we provide a new probabilistic perspective on backpropagating through these DP operators, and relate them to inference in graphical models. We derive two particular instantiations of our framework, a smoothed Viterbi algorithm for sequence prediction and a smoothed DTW algorithm for time-series alignment. We showcase these instantiations on two structured prediction tasks and on structured and sparse attention for neural machine translation.
Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.
Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a max operator regularized with a strongly convex function. We show that this operator is differentiable and that its gradient defines a mapping from real values to probabilities, suitable as an attention mechanism. Our framework includes softmax and a slight generalization of the recently-proposed sparsemax as special cases. However, we also show how our framework can incorporate modern structured penalties, resulting in new attention mechanisms that focus on entire segments or groups of an input, encouraging parsimony and interpretability. We derive efficient algorithms to compute the forward and backward passes of these attention mechanisms, enabling their use in a neural network trained with backpropagation. To showcase their potential as a drop-in replacement for existing attention mechanisms, we evaluate them on three large-scale tasks: textual entailment, machine translation, and sentence summarization. Our attention mechanisms improve interpretability without sacrificing performance; notably, on textual entailment and summarization, we outperform the existing attention mechanisms based on softmax and sparsemax.
The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation (Models and code available at http:// pose. mpi-inf. mpg. de).
This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32 memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58 faster convolutional operations (in terms of number of the high precision operations) and 32 memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a Binary-Weight-Network version of AlexNet is the same as the full-precision AlexNet. We compare our method with recent network binarization methods, BinaryConnect and BinaryNets, and outperform these methods by large margins on ImageNet, more than in top-1 accuracy. Our code is available at: http:// allenai. org/ plato/ xnornet.
We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects. The hallmarks of DDN are its incorporation of geometric constraints within a convolutional neural network (CNN) framework, ease and efficiency of training, as well as generality of application. A novel shape basis network (SBN) forms the first stage of the cascade, whereby landmarks are initialized by combining the benefits of CNN features and a learned shape basis to reduce the complexity of the highly nonlinear pose manifold. In the second stage, a point transformer network (PTN) estimates local deformation parameterized as thin-plate spline transformation for a finer refinement. Our framework does not incorporate either handcrafted features or part connectivity, which enables an end-to-end shape prediction pipeline during both training and testing. In contrast to prior cascaded networks for landmark localization that learn a mapping from feature space to landmark locations, we demonstrate that the regularization induced through geometric priors in the DDN makes it easier to train, yet produces superior results. The efficacy and generality of the architecture is demonstrated through state-of-the-art performances on several benchmarks for multiple tasks such as facial landmark localization, human body pose estimation and bird part localization.
We present a method for estimating articulated human pose from a single
static image based on a graphical model with novel pairwise relations that make
adaptive use of local image measurements. More precisely, we specify a
graphical model for human pose which exploits the fact the local image
measurements can be used both to detect parts (or joints) and also to predict
the spatial relationships between them (Image Dependent Pairwise Relations).
These spatial relationships are represented by a mixture model. We use Deep
Convolutional Neural Networks (DCNNs) to learn conditional probabilities for
the presence of parts and their spatial relationships within image patches.
Hence our model combines the representational flexibility of graphical models
with the efficiency and statistical power of DCNNs. Our method significantly
outperforms the state of the art methods on the LSP and FLIC datasets and also
performs very well on the Buffy dataset without any training.
We describe a method for articulated human detection and human pose estimation in static images based on a new representation of deformable part models. Rather than modeling articulation using a family of warped (rotated and foreshortened) templates, we use a mixture of small, nonoriented parts. We describe a general, flexible mixture model that jointly captures spatial relations between part locations and co-occurrence relations between part mixtures, augmenting standard pictorial structure models that encode just spatial relations. Our models have several notable properties: 1) They efficiently model articulation by sharing computation across similar warps, 2) they efficiently model an exponentially large set of global mixtures through composition of local mixtures, and 3) they capture the dependency of global geometry on local appearance (parts look different at different locations). When relations are tree structured, our models can be efficiently optimized with dynamic programming. We learn all parameters, including local appearances, spatial relations, and co-occurrence relations (which encode local rigidity) with a structured SVM solver. Because our model is efficient enough to be used as a detector that searches over scales and image locations, we introduce novel criteria for evaluating pose estimation and human detection, both separately and jointly. We show that currently used evaluation criteria may conflate these two issues. Most previous approaches model limbs with rigid and articulated templates that are trained independently of each other, while we present an extensive diagnostic evaluation that suggests that flexible structure and joint training are crucial for strong performance. We present experimental results on standard benchmarks that suggest our approach is the state-of-the-art system for pose estimation, improving past work on the challenging Parse and Buffy datasets while being orders of magnitude faster.
In this paper we present a computationally efficient framework for part-based modeling and recognition of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to represent an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. We address the problem of using pictorial structure models to find instances of an object in an image as well as the problem of learning an object model from training examples, presenting efficient algorithms in both cases. We demonstrate the techniques by learning models that represent faces and human bodies and using the resulting models to locate the corresponding objects in novel images.
The task of 2-D articulated human pose estimation in natural images is extremely challenging due to the high level of variation in human appearance. These variations arise from different clothing, anatomy, imaging conditions and the large number of poses it is possible for a human body to take. Recent work has shown state-of-the-art results by partitioning the pose space and using strong nonlinear classifiers such that the pose dependence and multi-modal nature of body part appearance can be captured. We propose to extend these methods to handle much larger quantities of training data, an order of magnitude larger than current datasets, and show how to utilize Amazon Mechanical Turk and a latent annotation update scheme to achieve high quality annotations at low cost. We demonstrate a significant increase in pose estimation accuracy, while simultaneously reducing computational expense by a factor of 10, and contribute a dataset of 10,000 highly articulated poses.
We investigate the task of 2D articulated human pose estimation in unconstrained still images. This is extremely challenging because of variation in pose, anatomy, clothing, and imaging conditions. Current methods use simple models of body part appearance and plausible configurations due to limitations of available training data and constraints on computational expense. We show that such models severely limit accuracy. Building on the successful pictorial structure model (PSM) we propose richer models of both appearance and pose, using state-of-the-art discriminative classifiers without introducing unacceptable computational expense. We introduce a new annotated database of challenging consumer images, an order of magnitude larger than currently available datasets, and demonstrate over 50 % relative improvement in pose estimation accuracy over a stateof-the-art method.
Deep fully-connected part-based models for human pose estimation
- Rodrigo De Bem
- Anurag Arnab
- Stuart Golodetz
- Michael Sapienza
- Philip Torr
Rodrigo de Bem, Anurag Arnab, Stuart Golodetz, Michael
Sapienza, and Philip Torr. Deep fully-connected part-based
models for human pose estimation. In Asian Conference on
Machine Learning, pages 327-342, 2018. 2
Pose proposal networks
- Taiki Sekii
Taiki Sekii. Pose proposal networks. In Proceedings of the
European Conference on Computer Vision, pages 342-357,
2018. 5
Joint training of a convolutional network and a graphical model for human pose estimation
- Arjun Jonathan J Tompson
- Yann Jain
- Christoph Lecun
- Bregler
Jonathan J Tompson, Arjun Jain, Yann LeCun, and Christoph
Bregler. Joint training of a convolutional network and a
graphical model for human pose estimation. In Advances
in neural information processing systems, pages 1799-1807,
2014. 2, 5
Ran El-Yaniv, and Yoshua Bengio
- Matthieu Courbariaux
- Itay Hubara
- Daniel Soudry
Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran
El-Yaniv, and Yoshua Bengio. Binarized neural networks:
Training deep neural networks with weights and activations
constrained to +1 or-1. arXiv preprint arXiv:1602.02830,
2016. 3