【摘要】 车道线检测是车载视觉系统研究领域的一项重要内容,而图像分割则是车道线检测的关键和首要步骤。遗传算法在图像的阈值分割领域已经得到了广泛应用,笔者提出了基于激素调节机制的遗传算法,并与二维最大熵阈值法结合使用。应用结果表明:此算法对图像的分割效果优于传统遗传算法,它有效地克服了传统遗传算法的早熟、进化缓慢的问题,符合车载视觉系统的要求。更多还原

【Abstract】 Lane detection is important for a vehicle vision system,and image segmentation is a key and initial step of lane detection.Genetic algorithm has been widely used in image segmentation.An improved genetic algorithm(IGA) based on hormone modulation mechanism is proposed in this paper,and it is combined with two-dimensional maximum entropy.The results of experiments show that the proposed algorithm is better than the traditional genetic algorithm.It effectively overcomes the problems of premature phenomenon,slow evolution of traditional genetic algorithm and can match the requirements of vehicle vision systems in lane partition.更多还原