Adobe Boxes: Locating Object Proposals using Object Adobes

• Main Authors: Xiao, Yang, Fang, Zhiwen, Cao, Zhiguo, Zhu, Lei, Yuan, Junsong
• 其他作者: School of Electrical and Electronic Engineering
• 格式: Article
• 語言: English
• 出版: 2017
• 主題: Object Proposal; Adobe Boxes
• 在線閱讀: https://hdl.handle.net/10356/86004; http://hdl.handle.net/10220/43908
• 機構: Nanyang Technological University

Despite the previous efforts of object proposals, the detection rates of the existing approaches are still not satisfactory enough. To address this, we propose Adobe Boxes to efficiently locate the potential objects with fewer proposals, in terms of searching the object adobes that are the salient object parts easy to be perceived. Because of the visual difference between the object and its surroundings, an object adobe obtained from the local region has a high probability to be a part of an object, which is capable of depicting the locative information of the proto-object. Our approach comprises of three main procedures. First, the coarse object proposals are acquired by employing randomly sampled windows. Then, based on local-contrast analysis, the object adobes are identified within the enlarged bounding boxes that correspond to the coarse proposals. The final object proposals are obtained by converging the bounding boxes to tightly surround the object adobes. Meanwhile, our object adobes can also refine the detection rate of most state-of-the-art methods as a refinement approach. The extensive experiments on four challenging datasets (PASCAL VOC2007, VOC2010, VOC2012, and ILSVRC2014) demonstrate that the detection rate of our approach generally outperforms the state-of-the-art methods, especially with relatively small number of proposals. The average time consumed on one image is about 48 ms, which nearly meets the real-time requirement.