Comparing the Quality of Human Pose Estimation with BlazePose or OpenPose

Mroz, Sarah; Baddour, Natalie; McGuirk, Connor; Juneau, Pascale; Tu, Albert; Cheung, Kevin; Lemaire, Edward D.

doi:10.1109/biosmart54244.2021.9677850

Cited by 33 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the comparison with the MoCap system, Docekal et al [23] reported a similar result considering AlphaPose and MMPose.The results that we obtained were in line with the literature: BZ -MP performed worse [21,24] FP-AP and TCF-MMP were similar in the evaluation of the human whole-body pose. However, our results reported that FP-AP, trained on Halpe Fullbody, suffered from self-occlusion during the midstance phase.…”

Section: Resultssupporting

confidence: 91%

“…In 2020, Moro et al [19] used DeepLabCut [20] as a deep-learning pipeline and evaluated joint centres trajectories on chronic stroke survivors during walking, reporting a maximum error of 20 mm. In 2021, Mroz et al [21] compared Blazepose [22] to OpenPose. They found the first algorithm to be often poorly accurate, due to self-occlusion issues.…”

Section: Introductionsmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of video-based algorithms for 2D human kinematics estimation: a preliminary study

Ceriola,

Mileti,

Donati

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Many research efforts have been spent developing robust video-based algorithms for human pose estimation. Our goal was to compare video-based algorithms for pose estimation for gait analysis. We conducted an experiment with a healthy subject performing walking sessions on a treadmill at three different speeds: slow (3.6 km/h), medium (5 km/h), and high (7 km/h). An RGB 4k camera was placed laterally on the sagittal plane. Four algorithms were compared: (i) colour threshold filtering with blob-analysis, and three Deep Learning-based markerless algorithms (ii) TC-Former, (iii) FastPose and (iv) Blazepose. For colour threshold filtering with the blob-analysis algorithm, six magenta passive markers were placed over the joint centres of the subject’s lower limb. All selected deep learning-based markerless algorithms are supported by various open-source pose estimation toolboxes and are pre-trained on several whole-body keypoint datasets. The 2D trajectories of the joint centres were compared considering the root mean square error and Pearson’s coefficient. Preliminary results showed high correlations between marker and markerless algorithms for all walking speeds. TC-Former generally performed better with root mean square error on trajectories below 35 mm and did not suffer from self-occlusion issues.

show abstract

Section: Resultssupporting

confidence: 91%

Section: Introductionsmentioning

confidence: 99%

Comparison of video-based algorithms for 2D human kinematics estimation: a preliminary study

Ceriola,

Mileti,

Donati

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…We instructed each participant to record a video of the STS test using a smartphone placed or held vertically. We processed all videos using OpenPose (Cao, 2018), a widely used 44 , and high-performing 45,46 neural network-based software for pose estimation. For each person present in an RGB image, OpenPose returns the 2D position of 25 body landmarks: the nose, neck, and midpoint of the hips, and bilateral shoulders, elbows, wrists, hips, knees, ankles, eyes, ears, first metatarsals, fifth metatarsals, and heels.…”

Section: Video Analysismentioning

confidence: 99%

Smartphone videos of the sit-to-stand test predict osteoarthritis and health outcomes in a nationwide study

Boswell

Kidziński

Hicks

et al. 2022

Preprint

View full text Add to dashboard Cite

Physical function decline due to aging or disease can be assessed with quantitative motion analysis, but this currently requires expensive laboratory equipment. We introduce a self-guided quantitative motion analysis of the widely used five-repetition sit-to-stand test using a smartphone. Across 35 US states, 405 participants recorded a video performing the test in their homes. We found novel relationships not detectable in a clinical implementation of this test. Trunk angle during the sit-to-stand transition was greater in individuals with osteoarthritis and differed across ethnicities. In individuals 50 years of age or older, those with greater trunk angular acceleration had a higher mental health score. We also detected known associations between longer time to complete the five repetitions and lower physical health scores, higher BMI, and older age. Our findings demonstrate that at-home movement analysis goes beyond established clinical metrics to provide objective and inexpensive digital outcome metrics for nationwide studies.

show abstract

“…BlazePose is a low-powered markerless pose estimation technique and has recently demonstrated the ability to run on inexpensive hardware (Pixel 2 smartphone) [ 27 ]. The approach has been shown to provide a tradeoff relationship with OpenPose, sacrificing some anatomical accuracy for a significant reduction in computational cost in clinical environments [ 28 ]. Consequently, the approach could augment assessments within low-resource settings through deployment on low-powered hardware such as a smartphone.…”

Section: Introductionmentioning

confidence: 99%

Internet-of-Things-Enabled Markerless Running Gait Assessment from a Single Smartphone Camera

Young

Mason

Morris

et al. 2023

Sensors

View full text Add to dashboard Cite

Running gait assessment is essential for the development of technical optimization strategies as well as to inform injury prevention and rehabilitation. Currently, running gait assessment relies on (i) visual assessment, exhibiting subjectivity and limited reliability, or (ii) use of instrumented approaches, which often carry high costs and can be intrusive due to the attachment of equipment to the body. Here, the use of an IoT-enabled markerless computer vision smartphone application based upon Google’s pose estimation model BlazePose was evaluated for running gait assessment for use in low-resource settings. That human pose estimation architecture was used to extract contact time, swing time, step time, knee flexion angle, and foot strike location from a large cohort of runners. The gold-standard Vicon 3D motion capture system was used as a reference. The proposed approach performs robustly, demonstrating good (ICC(2,1) > 0.75) to excellent (ICC(2,1) > 0.90) agreement in all running gait outcomes. Additionally, temporal outcomes exhibit low mean error (0.01–0.014 s) in left foot outcomes. However, there are some discrepancies in right foot outcomes, due to occlusion. This study demonstrates that the proposed low-cost and markerless system provides accurate running gait assessment outcomes. The approach may help routine running gait assessment in low-resource environments.

show abstract

Comparing the Quality of Human Pose Estimation with BlazePose or OpenPose

Cited by 33 publications

References 12 publications

Comparison of video-based algorithms for 2D human kinematics estimation: a preliminary study

Comparison of video-based algorithms for 2D human kinematics estimation: a preliminary study

Smartphone videos of the sit-to-stand test predict osteoarthritis and health outcomes in a nationwide study

Internet-of-Things-Enabled Markerless Running Gait Assessment from a Single Smartphone Camera

Contact Info

Product

Resources

About