TY - JOUR
T1 - Particle swarm optimization and differential evolution for model-based object detection
AU - Ugolotti, Roberto
AU - Nashed, Youssef S.G.
AU - Mesejo, Pablo
AU - Ivekovic, Spela
AU - Mussi, Luca
AU - Cagnoni, Stefano
PY - 2013
Y1 - 2013
N2 - Automatically detecting objects in images or video sequences is one of the most relevant and frequently tackled tasks in computer vision and pattern recognition. The starting point for this work is a very general model-based approach to object detection. The problem is turned into a global continuous optimization one: given a parametric model of the object to be detected within an image, a function is maximized, which represents the similarity between the model and a region of the image under investigation. In particular, in this work, the optimization problem is tackled using Particle Swarm Optimization (PSO) and Differential Evolution (DE). We compare the performances of these optimization techniques on two real-world paradigmatic problems, onto which many other real-world object detection problems can be mapped: hippocampus localization in histological images and human body pose estimation in video sequences. In the former, a 2D deformable model of a section of the hippocampus is fit to the corresponding region of a histological image, to accurately localize such a structure and analyze gene expression in specific sub-regions. In the latter, an articulated 3D model of a human body is matched against a set of images of a human performing some action, taken from different perspectives, to estimate the subject's posture in space. Given the significant computational burden imposed by this approach, we implemented PSO and DE as parallel algorithms within the nVIDIATM CUDA computing architecture.
AB - Automatically detecting objects in images or video sequences is one of the most relevant and frequently tackled tasks in computer vision and pattern recognition. The starting point for this work is a very general model-based approach to object detection. The problem is turned into a global continuous optimization one: given a parametric model of the object to be detected within an image, a function is maximized, which represents the similarity between the model and a region of the image under investigation. In particular, in this work, the optimization problem is tackled using Particle Swarm Optimization (PSO) and Differential Evolution (DE). We compare the performances of these optimization techniques on two real-world paradigmatic problems, onto which many other real-world object detection problems can be mapped: hippocampus localization in histological images and human body pose estimation in video sequences. In the former, a 2D deformable model of a section of the hippocampus is fit to the corresponding region of a histological image, to accurately localize such a structure and analyze gene expression in specific sub-regions. In the latter, an articulated 3D model of a human body is matched against a set of images of a human performing some action, taken from different perspectives, to estimate the subject's posture in space. Given the significant computational burden imposed by this approach, we implemented PSO and DE as parallel algorithms within the nVIDIATM CUDA computing architecture.
KW - Articulated models
KW - Deformable models
KW - Differential Evolution
KW - Global continuous optimization
KW - Object detection
KW - Particle Swarm Optimization
KW - Pose estimation
UR - http://www.scopus.com/inward/record.url?scp=84881544657&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84881544657&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2012.11.027
DO - 10.1016/j.asoc.2012.11.027
M3 - Article
AN - SCOPUS:84881544657
VL - 13
SP - 3092
EP - 3105
JO - Applied Soft Computing
JF - Applied Soft Computing
SN - 1568-4946
IS - 6
ER -