博文
- Visual Ego-motion
- Vehicle Ego-motion it becomes that feasible to determin the camera orientation from observed scenes by resectioning. Ego-motion is same to visual odometry. Ego-motion needs to be estimatedin order to recover the position and orientation at each frame in a commoncoordinate system. ...
- Random Decision Tree Body Part Recognition Using FPGAs
- 摘要 Decision tree 被用于kinect vision pipeline，来识别body part和gesture。这种tree-based classification占有极大的computational load和memory bandwidth。这让highly-optimized hardware implementation非常有吸引力，特别是在strict power和form factor limitation。我们呈现了一个complete architecture，它 ...
- Image Segmentation Using Hardware Forest Classifiers
- 摘要 图像分割就是分割图像到segments或者subset，目的是进行further analysis，分隔开foreground上interesting objects和background上的un-interesting objects。在很多image processing application，这个process需要对每个像素基础上进行一序列的computational step，因此binding 图像的size和resolution与系统perf ...
- Tracking the articulated motion of two strongly interacting
- http://users.ics.forth.gr/~argyros/research/twohands.htm
- Motion Capture of Hands in Action using Discriminative Salie
- Motion Capture of Hands in Action using Discriminative Salient Points Luca Ballan, Aparna Taneja, Jurgen Gall, Luc Van Gool, and Marc Pollefeys
- Efficient Human Pose Estimation from Single Depth Images
- Jonathan Taylor, Jamie Shotton, Toby Sharp, andAndrew Fitzgibbon, The Vitruvian Manifold: Inferring Dense Correspondences forOne-Shot Human Pose Estimation, in Proc. CVPR, IEEE, June 2012 Jamie Shotton, Ross Girshick, Andrew Fitzgibbon, Toby Sharp, Mat Cook, MarkFinocchio, Richard Mo ...
- [论文阅读]Histogram of Oriented gradient for human detection
- 2005年由Navneet Dalal和Bill Triggs的发表的Histograms of Oriented Gradients for Human Detection是pedestrian detection的最著名的经典算法，必须仔细拜读： 摘要 该文主要研究用于visual object recognition的feature set，并采用基于linear SVM的human detection作为test case。通过review现 ...
本页有 3 篇博文因作者的隐私设置或未通过审核而隐藏
