Deep probabilistic human pose estimation

Petrov, Ilia A.; Shakhuro, Vlad; Konushin, Anton

doi:10.1049/iet-cvi.2017.0382

Cited by 32 publications

(24 citation statements)

References 18 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy results are confirmed with the PCK ones in Table 2, where the scores are reported for each key joint separately and for the whole body. HPE algorithms can be useful for various tasks in many areas, such as action recognition, human detection, human attribute recognition, and various gait processing tasks [57]. We chose the HAR task as it represents many challenges due to occlusions and overlapping scenes.…”

Section: Results Of J-hmdb Datasetmentioning

confidence: 99%

Deep Full-Body HPE for Activity Recognition from RGB Frames Only

Boualia

Amara

2021

Informatics

View full text Add to dashboard Cite

Human Pose Estimation (HPE) is defined as the problem of human joints’ localization (also known as keypoints: elbows, wrists, etc.) in images or videos. It is also defined as the search for a specific pose in space of all articulated joints. HPE has recently received significant attention from the scientific community. The main reason behind this trend is that pose estimation is considered as a key step for many computer vision tasks. Although many approaches have reported promising results, this domain remains largely unsolved due to several challenges such as occlusions, small and barely visible joints, and variations in clothing and lighting. In the last few years, the power of deep neural networks has been demonstrated in a wide variety of computer vision problems and especially the HPE task. In this context, we present in this paper a Deep Full-Body-HPE (DFB-HPE) approach from RGB images only. Based on ConvNets, fifteen human joint positions are predicted and can be further exploited for a large range of applications such as gesture recognition, sports performance analysis, or human-robot interaction. To evaluate the proposed deep pose estimation model, we apply it to recognize the daily activities of a person in an unconstrained environment. Therefore, the extracted features, represented by deep estimated poses, are fed to an SVM classifier. To validate the proposed architecture, our approach is tested on two publicly available benchmarks for pose estimation and activity recognition, namely the J-HMDBand CAD-60datasets. The obtained results demonstrate the efficiency of the proposed method based on ConvNets and SVM and prove how deep pose estimation can improve the recognition accuracy. By means of comparison with state-of-the-art methods, we achieve the best HPE performance, as well as the best activity recognition precision on the CAD-60 dataset.

show abstract

Section: Results Of J-hmdb Datasetmentioning

confidence: 99%

Deep Full-Body HPE for Activity Recognition from RGB Frames Only

Boualia

Amara

2021

Informatics

View full text Add to dashboard Cite

show abstract

“…If there is interference from moving objects in the field of view of the sports camera, the visual odometer will have a large estimation error or even fail. Aiming at the problem of moving objects in the scene interfering with the visual odometer, the random sampling consensus algorithm is currently the most mature and effective method [7]. is method fits the model and eliminates the data points that are inconsistent with the model as outliers.…”

Section: Related Workmentioning

confidence: 99%

Research on Moving Target Detection and Tracking Technology in Sports Video Based on SIFT Algorithm

Mei

Wang

2022

Advances in Multimedia

View full text Add to dashboard Cite

Sports video moving target detection and tracking play an important role in enhancing the popularity of sports and the promotion of sports events. This paper combines the SIFT algorithm to carry out the research of sports video moving target detection and tracking technology, to identify sports features, and to improve the sports feature detection algorithm. Moreover, this paper divides the point cloud data into multiple cube grids under the coordinate system where it is located, and then finds the center of gravity of the data points in each grid, and replaces the coordinates of all points in the grid with the coordinates of the center of gravity. In addition, this paper combines data analysis to verify the algorithm and build a sports video moving target detection system. The experimental research results verify that the sports video target detection and tracking technology based on the SIFT algorithm proposed in this paper has good results.

show abstract

“…The sparse coding model provides a more elegant calculation model for the formation mechanism of simple cell structures. Literature [ 4 ] uses the independent component analysis method to simulate the receptive field structure of simple cells. Studies have shown that the 2D receptive field profile of simple cells in the visual cortex is very similar to the core of the 2DGabor function.…”

Section: Related Workmentioning

confidence: 99%

The Visual Movement Analysis of Physical Education Teaching considering the Generalized Hough Transform Model

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to promote the effect of college physical education reform, this paper combines the generalized Hough transform model to analyze the visual movement of physical education teaching. The idea proposed in this paper uses the position information of the edge image itself and the direction information of the curve segment to directly eliminate the impossible targets, which fundamentally alleviates the problem of invalid sampling and accumulation. Moreover, this paper greatly constrains the parameter space based on the results of each segment of the curve, which greatly reduces the search burden of high-dimensional parameters, and combines the improved algorithm to construct a sports teaching video action analysis system. The experimental research shows that the visual movement analysis system of physical education teaching considering the generalized Hough transform model proposed in this paper can effectively analyze the sports teaching actions and improve the efficiency of physical education.

show abstract

Deep probabilistic human pose estimation

Cited by 32 publications

References 18 publications

Deep Full-Body HPE for Activity Recognition from RGB Frames Only

Deep Full-Body HPE for Activity Recognition from RGB Frames Only

Research on Moving Target Detection and Tracking Technology in Sports Video Based on SIFT Algorithm

The Visual Movement Analysis of Physical Education Teaching considering the Generalized Hough Transform Model

Contact Info

Product

Resources

About