Mirror reflection invariant HOG descriptors for object detection
Mirror reflection invariant HOG descriptors for object detection
复制标题
DOI：
10.1109/icip.2014.7025319
复制
发表时间：
2014-10
期刊：
影响因子：
--
通讯作者：
Asako Kanezaki;Yusuke Mukuta;T. Harada
中科院分区：
文献类型：
--
作者：
Asako Kanezaki;Yusuke Mukuta;T. Harada
定向梯度直方图 (HOG) [1] 描述符已广泛用于对象检测。一个重要的限制是，当对象水平翻转时，这些描述符往往会发生很大的变化，这是常见的情况。我们提出了新颖的 MI-HOG 描述符，这些描述符是通过将 HOG 描述符变换为对镜面反射不变的而获得的。在它们的提取过程中，我们不仅考虑独立元素的变换，还考虑不同位置和方向的元素的组合，从而产生更好的性能。与 HOG 描述符相比，我们的平均精度提高了 10% 以上。
Histogram of Oriented Gradients (HOG) [1] descriptors have been widely used for object detection. An important limitation is that these descriptors tend to vary considerably when objects are horizontally flipped, as is often the case. We propose novel MI-HOG descriptors that are obtained by transforming HOG descriptors to be invariant to mirror reflection. In their extraction process, we consider not only the transform of independent elements but also the combination of those in different location and in orientation, which yields better performance. We showed a greater than 10 % increase in average precision compared to HOG descriptors.