CAJ | 학술논문

摄像机标定是计算机视觉中非常重要的一环,传统标定方法需要求解内外参数,非常繁琐.通过建立自适应神经网络直接学习图像坐标与空间坐标间的关系.该方法对Harris角点提取结果进行增加约束的改进,从而提高网络训练样本精度,通过程序实现隐层神经元的自适应选取,并综合运用正则化、提前终止策略,使网络的泛化能力得到极大的改善.最后通过与经典标定方法进行对比的实验证明基于自适应神经网络具有很好的双摄像机标定精度.
섭상궤표정시계산궤시각중비상중요적일배,전통표정방법수요구해내외삼수,비상번쇄.통과건립자괄응신경망락직접학습도상좌표여공간좌표간적관계.해방법대Harris각점제취결과진행증가약속적개진,종이제고망락훈련양본정도,통과정서실현은층신경원적자괄응선취,병종합운용정칙화、제전종지책략,사망락적범화능력득도겁대적개선.최후통과여경전표정방법진행대비적실험증명기우자괄응신경망락구유흔호적쌍섭상궤표정정도.
Camera calibration is an important step in computer vision,the traditional calibration methods need to acquire the in-trinsic and extrinsic parameters and the process is quite complicated,so self-adaptive neural network is used to learn the rela-tionship between the image coordinates and the space coordinates.The generalization ability is improved a lot by the following methods:modify Harris comer extraction algorithm to improve the training data accuracy,choose the number of the middle layer cells adaptively through program,and combine normalization and stopped training strategies.At last,comparing with the traditional calibration method,the test result shows that this method is available and has higher precision for binocular camera calibration.