图 书 馆
用于深度图像中3D对象检测的滑动形状Sliding Shapes for 3D Object Detection in Depth Images |
|
| 课程网址: | http://videolectures.net/eccv2014_song_depth_images/ |
| 主讲教师: | Song Shuran |
| 开课单位: | 普林斯顿大学 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  RGB D传感器的深度信息极大地简化了计算机视觉中的一些常见挑战，并实现了多项任务的突破。在本文中，我们建议使用深度图进行物体检测，并设计3D检测器以克服识别的主要困难，即纹理，照明，形状，视点，杂波，遮挡，自遮挡和传感器噪声的变化。我们收集3D CAD模型的集合，并从数百个视点渲染每个CAD模型，以获得合成深度图。对于每个深度渲染，我们从3D点云中提取特征并训练一个示例SVM分类器。在测试和硬负片挖掘过程中，我们在3D空间中滑动3D检测窗口。实验结果表明，对于RGB和RGB D图像，我们的3D检测器明显优于现有算法，与DPM和R CNN相比，其平均精度提高了约1.7倍。所有源代码和数据都可以在线获得。 |
| 课程简介: | The depth information of RGB-D sensors has greatly simplified some common challenges in computer vision and enabled breakthroughs for several tasks. In this paper, we propose to use depth maps for object detection and design a 3D detector to overcome the major difficulties for recognition, namely the variations of texture, illumination, shape, viewpoint, clutter, occlusion, self-occlusion and sensor noises. We take a collection of 3D CAD models and render each CAD model from hundreds of viewpoints to obtain synthetic depth maps. For each depth rendering, we extract features from the 3D point cloud and train an Exemplar-SVM classifier. During testing and hard-negative mining, we slide a 3D detection window in 3D space. Experiment results show that our 3D detector significantly outperforms the state-of-the-art algorithms for both RGB and RGB-D images, and achieves about ×1.7 improvement on average precision compared to DPM and R-CNN. All source code and data are available online. |
| 关 键 词: | 计算机视觉; RGB-D传感器; 3D |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-06-11：吴淑曼 |
| 最后编审: | 2020-06-15：cxin |
| 阅读次数: | 38 |