arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.04048cs.CV
收藏

基于深度特征的目标检测上下文模型

Deep Feature Based Contextual Model for Object Detection

Zhejiang University(浙江大学)

Wenqing Chu, Deng Cai

摘要:

目标检测是计算机视觉中最活跃的领域之一,近年来取得了显著的进展。现有的目标检测方法大多采用基于卷积神经网络(R-CNN)的区域框架,仅利用目标边界框内的局部外观特征。由于这些方法忽略了对象建议周围的上下文信息,因此这些检测器的结果可能会生成输入图像的语义不一致的解释。在本文中,我们提出了一个集成的目标检测系统,它结合了本地外观,上下文信息的关系,对象和全局场景的上下文特征由卷积神经网络产生。该系统被公式化为一个完全连接的条件随机场(CRF)定义的对象建议和对象建议之间的上下文约束建模为边缘自然。此外,一个快速平均场近似方法被用来在这个CRF模型有效地推理。实验结果表明,与基线算法Faster R-CNN相比,我们的方法在PASCAL VOC 2007数据集上实现了更高的平均精度(mAP)。

英文摘要:

Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years. Current state-of-the-art object detection methods mostly adhere to the framework of regions with convolutional neural network (R-CNN) and only use local appearance features inside object bounding boxes. Since these approaches ignore the contextual information around the object proposals, the outcome of these detectors may generate a semantically incoherent interpretation of the input image. In this paper, we propose an ensemble object detection system which incorporates the local appearance, the contextual information in term of relationships among objects and the global scene based contextual feature generated by a convolutional neural network. The system is formulated as a fully connected conditional random field (CRF) defined on object proposals and the contextual constraints among object proposals are modeled as edges naturally. Furthermore, a fast mean field approximation method is utilized to inference in this CRF model efficiently. The experimental results demonstrate that our approach achieves a higher mean average precision (mAP) on PASCAL VOC 2007 datasets compared to the baseline algorithm Faster R-CNN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑