图 书 馆
当你看到一个好的HOG过滤器时就知道它：检测过滤器的有效选择Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection |
|
| 课程网址: | http://videolectures.net/eccv2014_ahmed_efficient_selection/ |
| 主讲教师: | Ejaz Ahmed |
| 开课单位: | 马里兰大学 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  基于定向梯度直方图（HOG）的过滤器集合在几种检测方法中很常见，尤其是小波和样本SVM。训练此类系统的主要瓶颈是从大量可能的选择中选择好滤波器的子集。我们表明，人们可以根据可以从过滤器本身计算出的属性来学习零件“优良”的通用模型。直觉是，跨类别的良好过滤器具有共同的特征，例如低杂波和与空间相关的梯度。这使我们能够快速丢弃那些没有希望的过滤器，从而加快了训练过程。我们的自动选择程序适用于训练姿势模型，使我们能够在PASCAL VOC数据集上提高其检测性能，同时将训练速度提高一个数量级。对于示例性SVM，报道的结果相似。 |
| 课程简介: | Collections of filters based on histograms of oriented gradients (HOG) are common for several detection methods, notably, poselets and exemplar SVMs. The main bottleneck in training such systems is the selection of a subset of good filters from a large number of possible choices. We show that one can learn a universal model of part “goodness” based on properties that can be computed from the filter itself. The intuition is that good filters across categories exhibit common traits such as, low clutter and gradients that are spatially correlated. This allows us to quickly discard filters that are not promising thereby speeding up the training procedure. Applied to training the poselet model, our automated selection procedure allows us to improve its detection performance on the PASCAL VOC data sets, while speeding up training by an order of magnitude. Similar results are reported for exemplar SVMs. |
| 关 键 词: | 过滤器; 梯度直方图 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-11-22：zyk |
| 最后编审: | 2020-11-22：zyk |
| 阅读次数: | 65 |