Performance Of Human Pose Estimation Research Articles

Ghost attentional down net: An effective lightweight top-down network for human pose estimation

Deep learning has demonstrated remarkable advantages in the field of human pose estimation. However, traditional methods often rely on widening and deepening networks to enhance the performance of human pose estimation, consequently increasing the parameter count and complexity of the networks. To address this issue, this paper introduces Ghost Attentional Down network, a lightweight human pose estimation network based on HRNet. This network leverages the fusion of features from high-resolution and low-resolution branches to boost performance. Additionally, GADNet utilizes GaBlock and GdBlock, which incorporate lightweight convolutions and attention mechanisms, for feature extraction, thereby reducing the parameter count and computational complexity of the network. The fusion of relationships between different channels ensures the optimal utilization of informative feature channels and resolves the issue of feature redundancy. Experimental results conducted on the COCO dataset, with consistent image resolution and environmental settings, demonstrate that employing GADNet leads to a reduction of 60.7% in parameter count and 61.2% in computational complexity compared to the HRNet network model, while achieving comparable accuracy levels. Moreover, when compared to commonly used human pose estimation networks such as Cascaded Pyramid Network (CPN), Stacked Hourglass Network, and HRNet, GADNet achieves high-precision detection of human keypoints even with fewer parameters and lower computational complexity, our network has higher accuracy compared to MobileNet and ShuffleNet.

Cross Dimensional Subspace Attention for human pose estimation

This paper discusses and studies the importance of Cross Dimensional Subspace Attention for human pose estimation. The Cross Dimensional Subspace Attention module is to realize the interaction between the channel and spatial dimensions of the feature map by dimensional transposition and to learn the individual attention of the feature map subspace, to obtain the global dependence of feature in the feature space and strengthen the ignored semantic and spatial information. This paper focuses on the feature fusion of human pose estimation network. In our method, the feature tensor is rotated and partitioned to obtain the cross-dimension interaction information and learn different mapping of features in subspace, which is conducive to multi-scale feature fusion. On the basis of HRNet (High-Resolution Net) backbone network, our training and testing results on the COCO keypoint detection dataset and the MPII dataset show that our method can effectively improve the performance of human pose estimation.

MfvPose: A multi-scale hybrid framework for human pose estimation

Human pose estimation is a challenging visual task that relies on spatial location information. To improve the performance of human pose estimation, it is important to accurately determine the constraint relationship among keypoints. To address this, we propose MfvPose, a novel hybrid model that leverages rich multi-scale information. The proposed model incorporates the HRFOV module, which uses cascaded atrous convolution to maintain high-resolution representations of the backbone extractor and enrich the multi-scale information. In addition, we introduce learnable scalar weights to the Transformer encoder. In detail, it involves a multiplication by a diagonal matrix with learnable scalar weights on output of each residual block, which improves the dynamics of model training and enhances the accuracy of human pose estimation. It is experimentally shown that our proposed MfvPose achieves promising results on various benchmarks.

PosePipe: Open-Source Human Pose Estimation Pipeline for Rehabilitation Research

<h3>Research Objectives</h3> While computer vision algorithms for human pose estimation (HPE) are advancing rapidly, both in terms of accuracy and the types of understanding they enable, using these cutting edge approaches for clinical research presents many challenges including the range of algorithms, algorithmic interdependencies and data management. In order to advance the use of HPE in clinical research, we have developed an open-source pipeline based that reduces these challenges. <h3>Design</h3> Retrospective observation study on the use of HPE pipeline on videos of people involved in rehabilitation. <h3>Setting</h3> Videos acquired in both inpatient and outpatient contexts. <h3>Participants</h3> Convenience sample of videos including from a clinical gait analysis laboratory and newly collected data including gait from people with a range of diagnoses. <h3>Interventions</h3> None. <h3>Main Outcome Measures</h3> Ability to efficiently analyze large volumes of videos acquired in clinic and qualitative review of the outputs. <h3>Results</h3> We have used the pipeline to analyze tens of thousands of videos acquired in clinical settings. If includes wrappers for numerous specific implementations of classes of algorithms, making exploratory analysis and comparison feasible. Among the classes of algorithms are tracking algorithms, 2D keypoint detection, 3D lifting layers, and body model parameter estimation. The movement of specific subjects of interest is isolated using tracking algorithms, which perform well even with other visible people. However, it occasionally swaps identities between patients and therapists and detection failures are more common for people using assistive devices. Identifying 2D keypoints is fairly reliable, but struggles with some prosthetic limbs. Lifting methods perform well when lifting these keypoints into 3D joint locations. Approaches that estimate the parameters of a body mesh are promising, but often brittle and produce implausible estimates. A custom neural network allows accurately detecting temporal gait parameters of rehabilitation participants. <h3>Conclusions</h3> The performance of HPE is advancing rapidly, but more tools will be developed to widely disseminate this to the clinical and research communities. Additionally, these algorithms need validation on clinical populations, who can be different than the population the algorithms are trained upon. <h3>Author(s) Disclosures</h3> None

Adaptive data augmentation network for human pose estimation

With the rapid development of convolutional neural networks (CNNs), the performance of human pose estimation has been significantly improved. However, state-of-the-art methods still face specific challenges, such as occluded keypoints and nearby persons. Unlike the classical network improvement strategy, our approach obtains adaptive data to obtain more accurate keypoints through data augmentation. In this paper, we propose Adaptive Data Augmentation Network (ADA-Net), which brings more adaptive training data by adding occlusion and interleaving information to the original image. First, we introduce Active Transmission Network (ATNet), which actively learns the transformation matrix from the original image and uses the matrix to synthesize new images for training. Second, we adopt an adversarial training strategy combined with the ATNet that allows us to capture more challenging cases. Extensive experiments show that our approach achieves comparable or even better results than most state-of-the-art methods. In particular, our ADA-Net outperforms High-Resolution Network (HRNet) by 1.1 and 0.7 points on the COCO test-dev set and MPII validation set, respectively.

FasterPose: A Faster Simple Baseline for Human Pose Estimation

The performance of human pose estimation depends on the spatial accuracy of keypoint localization. Most existing methods pursue the spatial accuracy through learning the high-resolution (HR) representation from input images. By the experimental analysis, we find that the HR representation leads to a sharp increase of computational cost, while the accuracy improvement remains marginal compared with the low-resolution (LR) representation. In this article, we propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose. Whereas the LR design largely shrinks the model complexity, how to effectively train the network with respect to the spatial accuracy is a concomitant challenge. We study the training behavior of FasterPose and formulate a novel regressive cross-entropy (RCE) loss function for accelerating the convergence and promoting the accuracy. The RCE loss generalizes the ordinary cross-entropy loss from the binary supervision to a continuous range, thus the training of pose estimation network is able to benefit from the sigmoid function. By doing so, the output heatmap can be inferred from the LR features without loss of spatial accuracy, while the computational cost and model size has been significantly reduced. Compared with the previously dominant network of pose estimation, our method reduces 58% of the FLOPs and simultaneously gains 1.3% improvement of accuracy. Extensive experiments show that FasterPose yields promising results on the common benchmarks, i.e., COCO and MPII, consistently validating the effectiveness and efficiency for practical utilization, especially the low-latency and low-energy-budget applications in the non-GPU scenarios.

Deep Layer and Spatial Aggregation neural network for human pose estimation

The simplebaseline model achieves high performance of human pose estimation with simple network structure. But the model lacks the layer and spatial information fusion. In this paper, we propose DLSAnet, which fuse layers and spatial information efficetively. DLSAnet uses DLA as backbone which has excellent feature extraction capabilities in the field of object detection. In addition, a modified spatial pyramid pooling is introduced to pool and connect multi-scale local area features, allowing the network to learn object features more comprehensively. Using a four-branch SPP module instead of a single-branch SPP module connected by a single hopping layer. This method is effective in alleviating the problem of slow loss drop late in training. Experiments show that DLSAnet can achieve better accuracy.

Stacked Hourglass Network with Additional Skip Connection for Human Pose Estimation

The human pose estimation is a problem of localizing human joints in a single image, and that is still a challenge in the field of computer vision. The hourglass network has been used in many researches to achieve good performance in human pose estimation problems. For human pose estimation problem, not only high-level features but also low-level features are important for understanding the whole human body. However, the vanilla hourglass network has the problem of passing only high-level features to the next stack. Therefore, we propose a network structure that can solve the problems of the vanilla hourglass by using an additional skip connection. The proposed skip connection improves network performance by passing relative low-level features to the next stack. In addition, the skip connection is a simple element-wise Sum operation, so there is no increase in the number of parameters. In this work, we use the well-known human pose estimation data set, MPII, to evaluate the proposed method. We conducted experiments to evaluate the objective performance of the proposed method, and it was confirmed through this evaluation that the proposed method improves the performance of human pose estimation of the vanilla hourglass network.

Improving Human Pose Estimation With Self-Attention Generative Adversarial Networks

Human pose estimation in images is challenging and important for many computer vision applications. Large improvements in human pose estimation have been achieved with the development of convolutional neural networks. Even though, when encountered some difficult cases even the state-of-the-art models may fail to predict all the body joints correctly. Some recent works try to refine the pose estimator. GAN (Generative Adversarial Networks) has been proved to be efficient to improve human pose estimation. However, GAN can only learn local body joints structural constrains. In this paper, we propose to apply Self-Attention GAN to further improve the performance of human pose estimation. With attention mechanism in the framework of GAN, we can learn long-range body joints dependencies, therefore enforce the entire body joints structural constrains to make all the body joints to be consistent. Our method outperforms other state-of-the-art methods on two standard benchmark datasets MPII and LSP for human pose estimation. Our code is available at: https://github.com/idotc/Hg-SAGAN.