Measuring the Objectness of Image Windows
Measuring the Objectness of Image Windows
复制标题
DOI：
10.1109/tpami.2012.28
复制
发表时间：
2012-11-01
影响因子：
23.6
通讯作者：
Ferrari, Vittorio
中科院分区：
文献类型：
--
作者：
Alexe, Bogdan;Deselaers, Thomas;Ferrari, Vittorio
我们提出了一种通用的对象性度量，量化图像窗口包含任何类别的对象的可能性。我们明确地训练它区分空间中具有明确边界的物体（例如牛和电话）与无定形的背景元素（例如草和道路）。该措施在贝叶斯框架中结合了几个测量物体特征的图像线索，例如看起来与周围环境不同以及具有封闭的边界。其中包括测量封闭边界特征的创新提示。在具有挑战性的 PASCAL VOC 07 数据集上的实验中，我们展示了这种新线索优于最先进的显着性度量，并且组合的客观性度量比任何单独的线索表现得更好。我们还与兴趣点算子、HOG 检测器以及最近三项旨在自动对象分割的作品进行了比较。最后，我们提出了对象性的两个应用。首先，我们根据窗口的对象概率对少量窗口进行采样，并给出一种算法，将它们用作现代特定类对象检测器的位置先验。正如我们通过实验表明的，这大大减少了昂贵的特定类模型评估的窗口数量。在第二个应用程序中，除了特定于类的模型之外，我们还使用客观性作为补充分数，这会减少误报。正如最近的几篇论文所示，在图像窗口上运行的许多其他应用程序中，对象性可以充当有价值的注意力机制，包括对象类别的弱监督学习、无监督像素分割和视频中的对象跟踪。计算对象性非常高效，只需要大约 4 秒。每张图像。
We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. The measure combines in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary. These include an innovative cue to measure the closed boundary characteristic. In experiments on the challenging PASCAL VOC 07 dataset, we show this new cue to outperform a state-of-the-art saliency measure, and the combined objectness measure to perform better than any cue alone. We also compare to interest point operators, a HOG detector, and three recent works aiming at automatic object segmentation. Finally, we present two applications of objectness. In the first, we sample a small numberof windows according to their objectness probability and give an algorithm to employ them as location priors for modern class-specific object detectors. As we show experimentally, this greatly reduces the number of windows evaluated by the expensive class-specific model. In the second application, we use objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. As shown in several recent papers, objectness can act as a valuable focus of attention mechanism in many other applications operating on image windows, including weakly supervised learning of object categories, unsupervised pixelwise segmentation, and object tracking in video. Computing objectness is very efficient and takes only about 4 sec. per image.