“…The technology used in previous studies has shown some limitations, since it is normally developed for and applied to the analysis of adults’ or children’s movements [ 33 ]. Markerless methods for the analysis of human motion have opened new possibilities for movement analysis, although initially it was mainly in two dimensions [ 20 , 21 , 34 ]. The analysis of infants’ movements may benefit substantially from markerless methods given the problems normally encountered in securely and safely positioning markers on their small body segments.…”
Section: Discussionmentioning
confidence: 99%
“…3D recordings, however, may provide added value through higher spatial resolution, depth information, and higher accuracy and reliability; however, exploration has been limited by high technology cost and computational overhead [ 19 ]. Markerless computer vision systems have the ability to implement a kinematic model [ 20 , 21 ] and have been presented as a promising alternative to marker-based systems [ 22 ].…”
Cerebral palsy, the most common childhood neuromotor disorder, is often diagnosed through visual assessment of general movements (GM) in infancy. This skill requires extensive training and is thus difficult to implement on a large scale. Automated analysis of GM performed using low-cost instrumentation in the home may be used to estimate quantitative metrics predictive of movement disorders. This study explored if infants’ GM may be successfully evaluated in a familiar environment by processing the 3D trajectories of points of interest (PoI) obtained from recordings of a single commercial RGB-D sensor. The RGB videos were processed using an open-source markerless motion tracking method which allowed the estimation of the 2D trajectories of the selected PoI and a purposely developed method which allowed the reconstruction of their 3D trajectories making use of the data recorded with the depth sensor. Eight infants’ GM were recorded in the home at 3, 4, and 5 months of age. Eight GM metrics proposed in the literature in addition to a novel metric were estimated from the PoI trajectories at each timepoint. A pediatric neurologist and physiatrist provided an overall clinical evaluation from infants’ video. Subsequently, a comparison between metrics and clinical evaluation was performed. The results demonstrated that GM metrics may be meaningfully estimated and potentially used for early identification of movement disorders.
“…The technology used in previous studies has shown some limitations, since it is normally developed for and applied to the analysis of adults’ or children’s movements [ 33 ]. Markerless methods for the analysis of human motion have opened new possibilities for movement analysis, although initially it was mainly in two dimensions [ 20 , 21 , 34 ]. The analysis of infants’ movements may benefit substantially from markerless methods given the problems normally encountered in securely and safely positioning markers on their small body segments.…”
Section: Discussionmentioning
confidence: 99%
“…3D recordings, however, may provide added value through higher spatial resolution, depth information, and higher accuracy and reliability; however, exploration has been limited by high technology cost and computational overhead [ 19 ]. Markerless computer vision systems have the ability to implement a kinematic model [ 20 , 21 ] and have been presented as a promising alternative to marker-based systems [ 22 ].…”
Cerebral palsy, the most common childhood neuromotor disorder, is often diagnosed through visual assessment of general movements (GM) in infancy. This skill requires extensive training and is thus difficult to implement on a large scale. Automated analysis of GM performed using low-cost instrumentation in the home may be used to estimate quantitative metrics predictive of movement disorders. This study explored if infants’ GM may be successfully evaluated in a familiar environment by processing the 3D trajectories of points of interest (PoI) obtained from recordings of a single commercial RGB-D sensor. The RGB videos were processed using an open-source markerless motion tracking method which allowed the estimation of the 2D trajectories of the selected PoI and a purposely developed method which allowed the reconstruction of their 3D trajectories making use of the data recorded with the depth sensor. Eight infants’ GM were recorded in the home at 3, 4, and 5 months of age. Eight GM metrics proposed in the literature in addition to a novel metric were estimated from the PoI trajectories at each timepoint. A pediatric neurologist and physiatrist provided an overall clinical evaluation from infants’ video. Subsequently, a comparison between metrics and clinical evaluation was performed. The results demonstrated that GM metrics may be meaningfully estimated and potentially used for early identification of movement disorders.
“…However, the Edinburgh Visual Gait Score requires manual processing, making it time-consuming [24,[27][28][29][30]. In recent years, two-dimensional markerless (2D ML) gait analysis methods have been developed and validated in both healthy individuals and children with CP [31][32][33][34][35]. With advances in video and depth technology (RGBD) and by incorporating automated processing algorithms, this methodology has become less time-consuming and does not require expensive hardware.…”
Section: Gait Analysismentioning
confidence: 99%
“…A previously developed 2D ML analysis system was used [31,32,35]. The measurement system consisted of a single RGB (red green blue) camera combined with a depth-infrared sensor (RGB-D) (Kinect 2 for Xbox One, RGB images with resolution 1920×1080 pixels at 30 frames/second and depth image of 512×424 pixels at 30 frames/second).…”
Background
Gait analysis aids in evaluation, classification and follow-up of gait pattern over time in children with cerebral palsy (CP). The sagittal plane is of special interest to assess flexed knee gait and ankle joint deviations that commonly progress with age and indicate deterioration of gait. Although most children with CP are ambulatory, no objective quantification of gait is currently included in any of the known international follow-up programs.
Can video-based 2-dimensional markerless (2D ML) gait analysis with automated processing be feasible for evaluation and classification of gait in children with CP?
Methods
Twenty children with bilateral CP with Gross Motor Function Classification Scale (GMFCS) levels I–III, from five regions in Sweden, were included from the national CP registry. A single RGB-Depth video camera, sensitive to depth and contrast, was positioned laterally to a green walkway and background, with four light sources. A previously validated markerless method was employed to estimate hip, knee and ankle kinematics in the sagittal plane, together with foot orientation in relation to the room, gait speed and step length.
Results
Mean age was 10.4 (range 6.8–16.1) years. Eight children were classified as GMFCS level I, eight as II and four as III. Setup took 15 minutes, acquisition 5–15 minutes and processing 10–15 minutes per child. With the 2D ML method deviations from normal could be determined and used to implement the classification of gait pattern, proposed by Rodda et al. 2001.
Conclusion
2D ML assessment is feasible, since it is accessible, easy to perform and well tolerated by the children. The 2D ML adds consistency and quantifies objectively important gait variables. It is both relevant and reasonable to include 2D ML gait assessment in the evaluation of children with CP.
“…With the popularization of inexpensive depth acquisition equipment, detecting human with the help of depth information has become an effective and feasible scheme. Unlike traditional RGB cameras, depth sensors in RGB-D cameras [ 14 , 15 ] do not rely on natural light sources and show strong robustness to changes in illumination. Depth images capture the distance from each people to the camera, thereby allowing the position relationships between objects to be calculated.…”
In recent years, human detection in indoor scenes has been widely applied in smart buildings and smart security, but many related challenges can still be difficult to address, such as frequent occlusion, low illumination and multiple poses. This paper proposes an asymmetric adaptive fusion two-stream network (AAFTS-net) for RGB-D human detection. This network can fully extract person-specific depth features and RGB features while reducing the typical complexity of a two-stream network. A depth feature pyramid is constructed by combining contextual information, with the motivation of combining multiscale depth features to improve the adaptability for targets of different sizes. An adaptive channel weighting (ACW) module weights the RGB-D feature channels to achieve efficient feature selection and information complementation. This paper also introduces a novel RGB-D dataset for human detection called RGBD-human, on which we verify the performance of the proposed algorithm. The experimental results show that AAFTS-net outperforms existing state-of-the-art methods and can maintain stable performance under conditions of frequent occlusion, low illumination and multiple poses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.