首页> 外文会议>Chinese Intelligent Systems Conference >Salient Object Detection Based on RGBD Images
【24h】

Salient Object Detection Based on RGBD Images

机译:基于RGBD图像的显着目标检测

获取原文

摘要

Salient object detection is very important in many image and vision-related applications. We add the depth clue into the detection method to extract salient objects. In low-level feature extract part, we extract the depth edge and corner clue, combining with color image features to form a 55 dimensions' vector. In the high-level prior part, the depth prior is used to predict the probability together with the other three priors. The experiment result showed that with the depth clue, the salient detection result is improved.
机译:显着物体检测在许多与图像和视觉相关的应用中非常重要。我们将深度线索添加到检测方法中以提取显着物体。在低级特征提取部分,我们提取深度边缘和拐角线索,并与彩色图像特征结合以形成55维向量。在高级先验部分中,深度先验与其他三个先验一起用于预测概率。实验结果表明,通过深度线索,显着性检测结果得到了改善。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号