“…To do so, we plan to employ the circular 25 mm cue card added to the scene -as a reference for physical scale-, as well as realistic anatomical models (e.g. MakeHuman [75]). Based on them, camera pose estimation algorithms (e.g.…”
“…To do so, we plan to employ the circular 25 mm cue card added to the scene -as a reference for physical scale-, as well as realistic anatomical models (e.g. MakeHuman [75]). Based on them, camera pose estimation algorithms (e.g.…”
“…The sequence of a 3D body processed with point-to-point correspondence can be rigged with an internal skeleton and exported in standard FBX format compatible with many CAD environments such as the open-source software Blender. Scripts can be used to modify the body posture using the internal skeleton (Figure 5) to perform virtual ergonomic assessments of spaces and workstations (Briceno & Paul, 2019; Sanchez-Riera et al, 2021). Figure 5.Rigged 3D body avatar created with generated models.…”
Section: Potential Applications Related To 4d Body Datamentioning
Anthropometrics have been crucial in the development of ergonomics. Traditionally, anthropometric data were summarized in statistical tables (means, percentiles, etc.,) that were then applied in the design process of products and environments. The emergence of 3D body scanners ushered in a new age for anthropometric research by providing, in addition to digital body measurements, a 3D representation of the body. Nowadays, the latest 4D scanning technology is able to capture the 3D body in motion. The complexity of these captures entails new challenges related to the processing, analysis, and synthesis of body data used to support ergonomics in design.
“…MakeHuman can be used to create parameterized 3D face models with detailed morphological characteristics, such as skin color and hair style. Blender, on the other hand, can be used to manipulate the 3D models according to selected ic values [7]. Since a 3D model is basically a textured polygonal mesh (i.e., a collection of nodes and edges in 3D) that defines the shape of a polyhedral object, an engineer can mark the actual positions of key-points in the model by selecting the corresponding nodes in the textured mesh.…”
Automatically detecting the positions of key-points (e.g., facial keypoints or finger key-points) in an image is an essential problem in many applications, such as driver's gaze detection and drowsiness detection in automated driving systems. With the recent advances of Deep Neural Networks (DNNs), Key-Points detection DNNs (KP-DNNs) have been increasingly employed for that purpose. Nevertheless, KP-DNN testing and validation have remained a challenging problem because KP-DNNs predict many independent key-points at the same time-where each individual key-point may be critical in the targeted application-and images can vary a great deal according to many factors.In this paper, we present an approach to automatically generate test data for KP-DNNs using many-objective search. In our experiments, focused on facial key-points detection DNNs developed for an industrial automotive application, we show that our approach can generate test suites to severely mispredict, on average, more than 93% of all key-points. In comparison, random search-based test data generation can only severely mispredict 41% of them. Many of these mispredictions, however, are not avoidable and should not therefore be considered failures. We also empirically compare state-of-the-art, many-objective search algorithms and their variants, tailored for test suite generation. Furthermore, we investigate and demonstrate how to learn specific conditions, based on image characteristics (e.g., head posture and skin color), that lead to severe mispredictions. Such conditions serve as a basis for risk analysis or DNN retraining.
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.
