A probabilistic bitwise genetic algorithm for B-spline based image deformation estimation

Abstract

We propose a novel genetic algorithm to solve the image deformation estimation problem by preserving the genetic diversity. As a classical problem, there is always a trade-off between the complexity of deformation models and the difficulty of parameters search in image deformation. 2D cubic B-spline surface is a highly free-form deformation model and is able to handle complex deformations such as fluid image distortions. However, it is challenging to estimate an apposite global solution.To tackle this problem, we develop a genetic operation named probabilistic bitwise operation (PBO) to replace the crossover and mutation operations, which can preserve the diversity during generation iteration and achieve better coverage ratio of the solution space. Furthermore, a selection strategy named annealing selection is proposed to control the convergence. Qualitative and quantitative results on synthetic data show the effectiveness of our method.

Image Deformation Estimation via Multiobjective Optimization

“…To the best of our knowledge, exploiting evolutionary algorithms [29] or multi-objective optimization approaches [30], [31] to deal with deformable surfaces have been sparsely treated so far. Our previous work appearing in GECCO2019 addressed this problem by using a modified single-objective GA [32]. Different from the previous work, in this paper, we attempt to adopt evolutionary algorithms for solving this problem by casting it as a multi-objective optimization problem.…”

Evolutionary Rear-Lamp Tracking at Nighttime

“…Hence, preserving genetic diversity during the evolution process is a crucial factor for effective solution search [36]. We adopt PBO [16], which is an individualindependent bit flip operation calculated according to the fitness and bit order, to replace crossover and mutation. PBO flips each bit in the chromosome with the probability…”

“…To tackle the problems described above, in this paper, a robust evolutionary rear-lamp tracking method at nighttime is proposed. The main framework is powered by a variant of genetic algorithm (GA) embedded with probabilistic bit-wise operation (PBO) [16], which replaces the traditional genetic operations such as crossover and mutation, to increase the ability to prevent the algorithm from falling into local optimum. In order to adopt PBO to our problem, we propose a balanced fitness function by considering color information, symmetry, consistency of tracking results between adjacent frames, and rigidity.…”

Image Deformation Estimation via Multi-Objective Optimization

“…To the best of our knowledge, exploiting evolutionary algorithms (Klein et al, 2007) or multi-objective optimization approaches (Alderliesten et al, 2012;Pirpinia et al, 2019) to deal with deformable surfaces have been sparsely treated so far. Our previous work appearing in GECCO2019 addressed this problem by using a modified single-objective GA (Nakane et al, 2019). Different from the previous work, in this paper, we attempt to adopt evolutionary algorithms for solving this problem by casting it as a multi-objective optimization problem.…”