CAJ | 학술논문

针对基于传统梯度方向直方图特征的目标识别算法(HOG+SVM)在目标发生仿射变化时识别效果较差的问题,该文提出一种基于仿射梯度方向直方图特征的目标识别算法(AHOG+SVM).通过提取多尺度金字塔梯度图像的 HOG 特征,提高了算法的尺度不变性;通过将平面 HOG 栅格拓展至3维 HOG 栅格,并根据目标的世界坐标系与图像坐标系的映射关系将3维 HOG 栅格映射为2维 HOG 仿射栅格,最后对仿射栅格内的 HOG 特征进行仿射逆变换,以达到增强算法旋转不变性与错切不变性的目的.多组实验结果表明,该文提出的算法能够解决在目标识别过程中由尺度变化、旋转变化和错切变化(3D 视角变化)所造成的识别率较低的问题,性能优于 HOG+SVM算法.
침대기우전통제도방향직방도특정적목표식별산법(HOG+SVM)재목표발생방사변화시식별효과교차적문제,해문제출일충기우방사제도방향직방도특정적목표식별산법(AHOG+SVM).통과제취다척도금자탑제도도상적 HOG 특정,제고료산법적척도불변성;통과장평면 HOG 책격탁전지3유 HOG 책격,병근거목표적세계좌표계여도상좌표계적영사관계장3유 HOG 책격영사위2유 HOG 방사책격,최후대방사책격내적 HOG 특정진행방사역변환,이체도증강산법선전불변성여착절불변성적목적.다조실험결과표명,해문제출적산법능구해결재목표식별과정중유척도변화、선전변화화착절변화(3D 시각변화)소조성적식별솔교저적문제,성능우우 HOG+SVM산법.
A kind of object recognition algorithm based on Affine Histogram of Oriented Gradient (AHOG+SVM) is proposed to solve the poor effect of object recognition algorithm based on HOG (HOG+SVM). In order to have scale invariance, this paper builds multi-scale pyramid gradient images, and then computes HOG feature on them. In order to increase the rotational invariance and shear invariance, this method firstly expands 2D HOG grid to 3D HOG grid, then maps 3D grid to 2D affine grid according to the relationship between the world coordinate and image coordinate. Finally, inverse transformation of HOG feature in affine grid is carried out to remove the influence of affine transformation. The experimental results show that, the proposed method has the ability to solve the low recognition rate because of scale changes, rotation changes and shear changes (3D perspective changes) of object, and its performance is better than HOG+SVM.