Augmented Projectors. In this project we investigate novel handheld projector systems for indoor spaces. These projection-based devices are “aware” of their environment in ways not demonstrated previously. They offer both spatial awareness, where the system infers location and orientation of the device in 3D space, and geometry awareness, where the system constructs the 3D structure of the world around it, which can encompass the user as well as other physical objects, such as furniture and walls.
This paper presents two novel handheld projector systems for indoor pervasive computing spaces. These projection-based devices are “aware” of their environment in ways not demonstrated previously. They offer both spatial awareness, where the system infers location and orientation of the device in 3D space, and geometry awareness, where the system constructs the 3D structure of the world around it, which can encompass the user as well as other physical objects, such as furniture and walls.
D-IMager | Panasonic. Www.omekinteractive.com/content/Datasheet-Omek-BeckonDevelopmentSuite.pdf. CHALEARN Gesture Challenge. FREE Face Recognition API, Face Recognition Software Apps for the masses – face.com. Are there any open source facial recognition systems. Which open libraries exist to do facial recognition (rather than face detection) What are some publicly available labelled datasets using the Kinect for use in Computer Vision research.
Zicheng Liu. MSR Action Recognition Datasets and Codes HON4D Code and MSRActionPairs Dataset MSRGesture3D (28MB): The dataset was captured by a Kinect device. There are 12 dynamic American Sign Language (ASL) gestures, and 10 people. Each person performs each gesture 2-3 times. . {7,8,9} ->"ASL_Where"; {10,11,12} ->"ASL_Store"; {13,14,15} ->"ASL_Pig"; {16,17,18} ->"ASL_Past"; {19,20,21}->"ASL_Hungary"; {22.23,24}->"ASL_Green"; {25.26.27}->"ASL_Finish"; {28,29,30}->"ASL_Blue"; {31,32,33}->"ASL_Bathroom"; {34,35,36}->"ASL_Milk"; Each file is a MAT file which can be loaded with 64bit MATLAB.
X=load('sub_depth_01_01'); width = size(x.depth_part,1); height = size(x.depth_part,2); nFrames = size(x.depth_part,3); for(i=1:width) for(j=1:height) for(k=1:nFrames) depthval = x.depth_part(i,j,k); end end end The following two papers reported experiment results on this dataset: Alexey Kurakin, Zhengyou Zhang, Zicheng Liu, A Real-Time System for Dynamic Hand Gesture Recognition with a Depth Sensor, EUSIPCO, 2012. Part 1 (440 MB) Senior Home Monitoring. English 中文 Senior Home Monitoring The current video database containing twelve types of human actions (drinking, eating meals, eating snacks,getting out of bed, going to bed, sleeping, smoking, walking, playing mahjong, washing face, washing feet and watching TV) performed by 6 seniors in their own rooms.
We have collected this dataset of 4 month long (the location is not disclosed here to avoid exposing the identities of the authors). Daily activities in senior homes were recorded by using one SONY DCR-SR68E camera per room. The recording lasts for 10 days foreach senior. The total size of the record data is approximately 1.8TB with 25f/s. Some example images from the recorded video dataset are illustrated below. All samples were downsampled and compressed (Xvid MPEG-4 Codec )to the spatial resolution of 360x288 pixels. Fig 1.Different actions of seniors Fig 2.Activity distribution of one day Fig 3.Activity recognition results on our Senior Activity recognition dataset.