AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

Fang, Haoshu; Li, Jiefeng; HongYang, Tang; Chen, Xu; Zhu, Hua; Xiu, Yuliang; Li, Yong-Lu; Lu, Cewu

doi:10.48550/arxiv.2211.03375

Cited by 12 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various libraries built on these frameworks intended for 2D and 3D human pose estimation have been proposed in the literature. Openpose, DensePose, Alphapose, and HRNET (High-Resolution Net) are among the most discussed libraries for the marker-less human pose estimation system discussed in the literature [5][6][7]14]. These libraries have been used to develop the prediction model by utilizing various publicly available datasets.…”

Section: Related Workmentioning

confidence: 99%

“…This approach has the potential to outperform traditional methods that rely on handcrafted features and model-based algorithms [4]. A number of libraries have been developed and proposed for the task of human pose estimation, including OpenPose [5], Dense Pose [6], Alpha-Pose [7], HRNet [8], and others. These libraries use deep learning frameworks [9] for developing, training, and deploying the model for the task.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Human Key Point Identification: A Comparative Study of the High-Resolution VICON Dataset and COCO Dataset Using BPNET

Lee,

Lama,

Joo

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Accurately identifying human key points is crucial for various applications, including activity recognition, pose estimation, and gait analysis. This study introduces a high-resolution dataset formed via the VICON motion capture system and three diverse 2D cameras. It facilitates the training of neural networks to estimate 2D key joint positions from images and videos. The study involved 25 healthy adults (17 males, 8 females), executing normal gait for 2 to 3 s. The VICON system captured 3D ground truth data, while the three 2D cameras collected images from different perspectives (0°, 45°, and 135°). The dataset was used to train the Body Pose Network (BPNET), a popular neural network model developed by NVIDIA TAO. Additionally, a comparison entails another BPNET model trained on the COCO 2017 dataset, featuring over 118,000 annotated images. Notably, the proposed dataset exhibited a higher level of accuracy (14.5%) than COCO 2017, despite comprising one-fourth of the image count (23,741 annotated image). This substantial reduction in data size translates to improvements in computational efficiency during model training. Furthermore, the unique dataset’s emphasis on gait and precise prediction of key joint positions during normal gait movements distinguish it from existing alternatives. This study has implications ranging from gait-based person identification, and non-invasive concussion detection through sports temporal analysis, to pathologic gait pattern identification.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing Human Key Point Identification: A Comparative Study of the High-Resolution VICON Dataset and COCO Dataset Using BPNET

Lee,

Lama,

Joo

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Pose estimation is a computer vision task that aims to encode the relative position of individual body parts of a moving animal to derive its location and orientation. This task can be carried out by deep learning models such as AlphaPose ( Fang et al, 2022 ), a state-of-the-art whole-body pose estimation tool that can concurrently be used with many people. Deep learning-based pose estimation technology can be applied to other animals, including rodents, to facilitate behavior detection and categorization.…”

Section: General Capabilitymentioning

confidence: 99%

Open-source software for automated rodent behavioral analysis

Isik

Ünal

2023

Front. Neurosci.

View full text Add to dashboard Cite

Rodent behavioral analysis is a major specialization in experimental psychology and behavioral neuroscience. Rodents display a wide range of species-specific behaviors, not only in their natural habitats but also under behavioral testing in controlled laboratory conditions. Detecting and categorizing these different kinds of behavior in a consistent way is a challenging task. Observing and analyzing rodent behaviors manually limits the reproducibility and replicability of the analyses due to potentially low inter-rater reliability. The advancement and accessibility of object tracking and pose estimation technologies led to several open-source artificial intelligence (AI) tools that utilize various algorithms for rodent behavioral analysis. These software provide high consistency compared to manual methods, and offer more flexibility than commercial systems by allowing custom-purpose modifications for specific research needs. Open-source software reviewed in this paper offer automated or semi-automated methods for detecting and categorizing rodent behaviors by using hand-coded heuristics, machine learning, or neural networks. The underlying algorithms show key differences in their internal dynamics, interfaces, user-friendliness, and the variety of their outputs. This work reviews the algorithms, capability, functionality, features and software properties of open-source behavioral analysis tools, and discusses how this emergent technology facilitates behavioral quantification in rodent research.

show abstract

“…Although the bottom-up method has proved its good performance because it mainly considers the local area of the image, their body part detectors may not be able to meet this challenge when the number of human objects in the image is small. The top-down methods have two stages, represented by AlphaPose (Fang et al, 2022). They first detect the human object in the image and mark the rectangular bounding box of each human area to eliminate the interference of non-human entities; Then, the skeleton points of each human body region are detected.…”

Section: Human Pose Estimationmentioning

confidence: 99%

A Lightweight Multi-Person Pose Estimation Scheme Based on Jetson Nano

Liu¹,

Blancaflor

Abisado

2023

acs

View full text Add to dashboard Cite

As the basic technology of human action recognition, pose estimation is attracting more and more researchers' attention, while edge application scenarios pose a higher challenge. This paper proposes a lightweight multi-person pose estimation scheme to meet the needs of real-time human action recognition on the edge end. This scheme uses AlphaPose to extract human skeleton nodes, and adds ResNet and Dense Upsampling Revolution to improve its accuracy. Meanwhile, we use YOLO to enhance AlphaPose’s support for multi-person pose estimation, and optimize the proposed model with TensorRT. In addition, this paper sets Jetson Nano as the Edge AI deployment device of the proposed model and successfully realizes the model migration to the edge end. The experimental results show that the speed of the optimized object detection model can reach 20 FPS, and the optimized multi-person pose estimation model can reach 10 FPS. With the image resolution of 320×240, the model’s accuracy is 73.2%, which can meet the real-time requirements. In short, our scheme can provide a basis for lightweight multi-person action recognition scheme on the edge end.

show abstract

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

Cited by 12 publications

References 0 publications

Enhancing Human Key Point Identification: A Comparative Study of the High-Resolution VICON Dataset and COCO Dataset Using BPNET

Enhancing Human Key Point Identification: A Comparative Study of the High-Resolution VICON Dataset and COCO Dataset Using BPNET

Open-source software for automated rodent behavioral analysis

A Lightweight Multi-Person Pose Estimation Scheme Based on Jetson Nano

Contact Info

Product

Resources

About