- 博客(1)
- 资源 (6)
- 收藏
- 关注
转载 自然科学基金本子撰写
拟解决的关键科学问题和关键技术的区别在这里出现的常见问题是:往往把研究内容作为关键问题,或者说关键问题就是研究内容的翻版。这里要注意的是,关键问题是从研究内容中提炼出来的。举一个不太恰当的例子,但可以说明问题。例如,盖一栋房子,打地基是其内容之一,但关键问题可能是由于盖房子的地方下面土质太软,因此要解决的关键问题是打地基时如何解决土质太软的问题。------------------
2013-01-27 21:07:34 3434
A self-calibrated photo-geometric depth camera
In this paper, we present a practical 3D imaging system by combining the near-light photometric stereo and the speckle-based stereo matching method. The system is compact in structure and suitable for multi-albedo targets. The parameters (including position and intensity) of the light sources can be self-calibrated. To realize the auto-calibration, we first use the distant lighting model to estimate the initial surface albedo map, and then with the estimated albedo map and the normal vector field fixed, the parameters of the near lighting model are optimized. Next, with the optimized lighting model, we use the near-light photometric stereo method to re-compute the surface normal and fuse it with the coarse depth map from stereo vision to achieve high-quality depth map.
2018-06-09
EdgeFlow code
Edgeflow matlab source code.
参考论文. Wei-Ying Ma. EdgeFlow: a technique for boundary detection and image segmentation. IEEE IP 2000
2013-05-14
Efficient Human Pose Estimation from Single Depth Images
微软研究院的最新大作。
We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body jointsfromasingledepthimage,withoutusinganytemporalinformation.Thekeytobothapproachesistheuseofalarge,realistic, and highly varied synthetic set of training images. This allows us to learn models that are largely invariant to factors such as pose, body shape, field-of-view cropping, and clothing. Our first approach employs an intermediate body parts representation, designed so
that an accurate per-pixel classification of the parts will localize the joints of the body. The second approach instead directly regresses the positions of body joints. By using simple depth pixel comparison features, and parallelizable decision forests, both approaches can run super-realtime on consumer hardware. Our evaluation investigates many aspects of our methods, and compares the approaches to each other and to the state of the art. Results on silhouettes suggest broader applicability to other imaging modalities.
2012-12-24
Scene Reconstruction and Visualization from Internet Photo Collections
Doctor of Philosophy, University of Washington
华盛顿大学博士论文
作者为Bundler的开发者
2012-11-23
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人