Designing a camera placement assistance system for human
motion capture based on a guided genetic algorithm
Received: 1 August 2015 / Accepted: 24 March 2017 / Published online: 4 April 2017
Ó Springer-Verlag London 2017
Abstract In multi-camera motion capture systems, deter-
mining the optimal camera conﬁguration (camera positions
and orientations) is still an unresolved problem. At present,
conﬁgurations are primarily guided by a human operator’s
intuition, which requires expertise and experience, espe-
cially with complex, cluttered scenes. In this paper, we
propose a solution to automate camera placement for
motion capture applications in order to assist a human
operator. Our solution is based on the use of a guided
genetic algorithm to optimize camera network placement
with an appropriate number of cameras. In order to
improve the performance of the genetic algorithm (GA),
two techniques are described. The ﬁrst is a distribution and
estimation technique, which reduces the search space and
generates camera positions for the initial GA population.
The second technique is an error metric, which is inte-
grated at GA evaluation level as an optimization function
to evaluate the quality of the camera placement in a camera
network. Simulation experiments show that our approach is
more efﬁcient than other approaches in terms of compu-
tation time and quality of the ﬁnal camera network.
Keywords Multi-camera-based motion capture systems Á
Optimal camera conﬁgurations Á Genetic algorithm Á
Human motion capture using markers (active or passive)
requires cameras to be positioned around the volume of
interest so that at least two cameras can view each marker.
Three-dimensional marker positions are then calculated by
triangulation, and subject movements can thus be deﬁned.
When the movement is complex or is produced in the pres-
ence of obstacles, it is more difﬁcult to capture markers.
Consequently, a human operator tries to ﬁnd camera con-
ﬁgurations that minimize marker occlusion. This task
remains difﬁcult and requires time as well as many validation
tests, even in the case of an experienced expert.
Camera conﬁguration has a critical impact on the overall
motion capture performance. The conﬁguration quality to
determine the marker in 3D is strongly affected by two
sources of error: marker visibility and triangulation accu-
racy. In order to address these error sources, the following
points should be taking into consideration:
1. A Marker should not be occluded by any obstacle.
2. A Marker should be within the camera’s ﬁeld of view.
3. A Marker must be visible given a camera’s resolution,
the marker’s size, and its distance from the camera.
4. At least two cameras are required to reconstruct a
5. Cameras should be arranged sufﬁciently non-parallel
so that triangulation calculations are well conditioned.
6. Incorporating additional cameras leads to over condi-
tioned triangulation. However, it involves a higher
To assist human operators in conﬁguring camera networks
and improving human motion capture, we developed a
computer tool using a guided genetic algorithm to simulate
the best camera network conﬁguration. Our approach looks
& Azeddine Aissaoui
LESIA Laboratory, Biskra University, BP 145 RP,
07000 Biskra, Algeria
UVHC, LAMIH, 59313 Valenciennes, France
CNRS, UMR 8201, 59313 Valenciennes, France
University Lille Nord de France, 59000 Lille, France
Virtual Reality (2018) 22:13–23