智能系统学报
智能繫統學報
지능계통학보
CAAI TRANSACTIONS ON INTELLIGENT SYSTEMS
2014年
4期
454-460
,共7页
三维景物中平表面%重建%单应矩阵%约束条件%智能算法%遗传算法
三維景物中平錶麵%重建%單應矩陣%約束條件%智能算法%遺傳算法
삼유경물중평표면%중건%단응구진%약속조건%지능산법%유전산법
3-D scene plane%reconstruction%homography%constraint condition%intelligent algorithm%genetic algo-rithm
针对使用传统的三维景物重建方法用于三维景物中平表面重建而出现的精度低等问题,提出了2种基于多视图的三维景物中平表面重建模型:最小化反投影误差的平表面重建模型和最小化转移误差的平表面重建模型。第1种模型利用反投影线应与空间平面相交且交于一点,从而将误差转移到空间平面上进行最小化反投影误差;第2种模型利用二维空间平面与二维图像平面之间的单应转移关系,从而将误差转移到空间平面上最小化转移误差。这2种模型都采用遗传算法进行优化求解,从而获得平表面重建结果。实际上,2种平表面重建方法的基本原理相同,只是计算复杂度不同。实验结果表明,2种平表面重建方法的精度基本一致,而平表面重建的精度大大提高。
針對使用傳統的三維景物重建方法用于三維景物中平錶麵重建而齣現的精度低等問題,提齣瞭2種基于多視圖的三維景物中平錶麵重建模型:最小化反投影誤差的平錶麵重建模型和最小化轉移誤差的平錶麵重建模型。第1種模型利用反投影線應與空間平麵相交且交于一點,從而將誤差轉移到空間平麵上進行最小化反投影誤差;第2種模型利用二維空間平麵與二維圖像平麵之間的單應轉移關繫,從而將誤差轉移到空間平麵上最小化轉移誤差。這2種模型都採用遺傳算法進行優化求解,從而穫得平錶麵重建結果。實際上,2種平錶麵重建方法的基本原理相同,隻是計算複雜度不同。實驗結果錶明,2種平錶麵重建方法的精度基本一緻,而平錶麵重建的精度大大提高。
침대사용전통적삼유경물중건방법용우삼유경물중평표면중건이출현적정도저등문제,제출료2충기우다시도적삼유경물중평표면중건모형:최소화반투영오차적평표면중건모형화최소화전이오차적평표면중건모형。제1충모형이용반투영선응여공간평면상교차교우일점,종이장오차전이도공간평면상진행최소화반투영오차;제2충모형이용이유공간평면여이유도상평면지간적단응전이관계,종이장오차전이도공간평면상최소화전이오차。저2충모형도채용유전산법진행우화구해,종이획득평표면중건결과。실제상,2충평표면중건방법적기본원리상동,지시계산복잡도불동。실험결과표명,2충평표면중건방법적정도기본일치,이평표면중건적정도대대제고。
With consideration to the problems including low accuracy of the 3-D scene plane reconstruction by using the traditional 3-D reconstruction method , two kinds of 3-D scene plane reconstruction models based on multiple views are presented .One is the model of a scene plane reconstruction based on minimizing the reverse projection er -ror .The other is the model of a scene plane reconstruction based on minimizing the transfer error .The first model u-ses the knowledge that the reverse projection lines should not only intersect with a scene plane but should also meet at one point in a scene plane , so as to minimize the reverse projection error in the scene plane .The second model uses the transfer relationship between the image plane and the scene plane , so as to minimize the transfer error in the scene plane.Finally, the optimized value is computed by the genetic algorithm .The basic principles of the two methods are the same , and the difference between them is in regard to the computational complexity .The experi-mental results show that the accuracy of the two methods is almost the same and the accuracy of the 3-D scene plane reconstruction is improved greatly .