Minimum Barrier Salient Object Detection at 80 FPS
Minimum Barrier Salient Object Detection at 80 FPS
复制标题
DOI：
10.1109/iccv.2015.165
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Jianming Zhang;S. Sclaroff;Zhe L. Lin;Xiaohui Shen;Brian L. Price;R. Mech
中科院分区：
文献类型：
--
作者：
Jianming Zhang;S. Sclaroff;Zhe L. Lin;Xiaohui Shen;Brian L. Price;R. Mech
提出了一种基于最小障碍距离(MBD)变换的高效、高效、高效的显著目标检测方法。MBD变换对像素值波动具有较强的鲁棒性，因此可以在不进行区域提取的情况下有效地应用于原始像素。我们提出了一种近似的MBD变换算法，其加速比为精确算法的100倍。文中还提供了误差界分析。在这种快速MBD变换算法的支持下，提出的显著目标检测方法的运行速度为80FPS，在四个大型基准数据集上的性能明显优于相同速度的已有方法，并获得了与最新方法相当或更好的性能。此外，还提出了一种基于颜色白化的技术来扩展我们的方法，以利用基于外观的背景线索。这个扩展版本进一步提高了性能，同时仍然比所有其他领先方法快一个数量级。
We propose a highly efficient, yet powerful, salient object detection method based on the Minimum Barrier Distance (MBD) Transform. The MBD transform is robust to pixel-value fluctuation, and thus can be effectively applied on raw pixels without region abstraction. We present an approximate MBD transform algorithm with 100X speedup over the exact algorithm. An error bound analysis is also provided. Powered by this fast MBD transform algorithm, the proposed salient object detection method runs at 80 FPS, and significantly outperforms previous methods with similar speed on four large benchmark datasets, and achieves comparable or better performance than state-of-the-art methods. Furthermore, a technique based on color whitening is proposed to extend our method to leverage the appearance-based backgroundness cue. This extended version further improves the performance, while still being one order of magnitude faster than all the other leading methods.