Swarm-Based Identification of Animation Key Points from 2D-medialness Maps Prashant Aparajeya 1(B ) , Frederic Fol Leymarie 2 , and Mohammad Majid al-Rifaie 3 1 Headers Ltd., London, UK p.aparajeya@headers-dev.com 2 Department of Computing, Goldsmiths, University of London, London, UK 3 School of Computing and Mathematical Sciences, University of Greenwich, London, UK Abstract. In this article we present the use of dispersive flies optimi- sation (DFO) for swarms of particles active on a medialness map – a 2D field representation of shape informed by perception studies. Optimis- ing swarms activity permits to efficiently identify shape-based keypoints to automatically annotate movement and is capable of producing mean- ingful qualitative descriptions for animation applications. When taken together as a set, these keypoints represent the full body pose of a char- acter in each processed frame. In addition, such keypoints can be used to embody the notion of the Line of Action (LoA), a well known classic technique from the Disney studios used to capture the overall pose of a character to be fleshed out. Keypoints along a medialness ridge are local peaks which are efficiently localised using DFO driven swarms. DFO is optimised in a way so that it does not need to scan every image pixel and always tend to converge at these peaks. A series of experimental trials on different animation characters in movement sequences confirms the promising performance of the optimiser over a simpler, currently-in-use brute-force approach. Keywords: Line of Action · Medialness · Dispersive flies optimisation · Swarm intelligence · Dominant points · Animation 1 Introduction We consider the problem that faces an animator when drawing a succession of frames to generate the illusion of movement of a character (e.g. Mickey Mouse). A now classic technique, which emerged in the Disney studios in the 1930s is to indicate the main pose via a single curve and redraw and deform this curve to indicate how the character to animate shall change its main allure and position [2]. This technique, often referred to as the “Line of Action” (or LoA) is also used to draw 3D characters, but in this initial work, we focus on using the LoA c  Springer Nature Switzerland AG 2019 A. Ek´art et al. (Eds.): EvoMUSART 2019, LNCS 11453, pp. 69–83, 2019. https://doi.org/10.1007/978-3-030-16667-0_5