Point Cloud-Based Automatic Assessment of 3D Computer Animation Courseworks

Computer-supported assessment tools can bring significant benefits to both students and teachers. When integrated in traditional education workflows, they may help to reduce the time required to perform the evaluation and consolidate the perception of fairness of the overall process. When integrated within on-line intelligent tutoring systems, they could provide students with a timely feedback and support self-assessment activities. The current work presents an alternative approach (and not just a “yet-another-implementation”) to the problem of automatically evaluating technical skills needed to create 3D computer animations. Although some solutions have been reported already in the literature, their applicability is partially constrained, as they require the teaching staff to define evaluation criteria that are strictly linked to the particular animation technique being assessed. Students are forced to operate in environments where they can only perform a part of the required animation steps, by using a pre-defined set of techniques and tools. To address such limitations, the proposed system exploits shapeand time-based features extracted from the 3D point clouds (i.e., the set of data points) describing animated geometries, which are independent of the particular animation techniques used. Experimental observations collected in the evaluation of course assignments in which students were asked to recreate 3D animations of deformable meshes prepared by the teaching staff showed a good correlation between automatic and manual evaluations. Obtained results confirmed the ability of the proposed approach to cope with heterogeneous evaluation tasks in which the relevant learning outcomes can be properly considered.

1 Introduction

Automatic assessment of learning assignments is a topic of increasing interest today. A number of approaches have been experimented already in different education domains, including mathematics [1] , physics [2], [3], biology [4] and literature [5], though the majority of solutions reported in the literature have been developed in the area of computer science [6], [7], [8], [9], [10], [11]. It is worth observing that the importance of computer-supported assessment is not to be regarded as strictly limited to the education domain. For instance, there exist use cases where automatic assessment tools have been used, e.g., to implement hiring procedures in software development companies [12], to design intelligent platforms for physical rehabilitation [13], [14], to score sport and art performances [15], [16], etc.