A novel human detection approach based on Depth map via Kinect
MetadataShow full item record
In this paper, a new method of human detection based on depth map from 3D sensor Kinect is proposed. First, the pixel filtering and context filtering are employed to roughly repair defects on the depth map due to information inaccuracy captured by Kinect. Second, a dataset consisting of depth maps with various indoor human poses is constructed as benchmark. Finally, by introducing Kirsch mask and three-value codes to Local Binary Pattern, a novel Local Ternary Direction Pattern (LTDP) feature descriptor is extracted and is used for human detection with SVM as classifier. The performance for the proposed approach is evaluated and compared with other five existing feature descriptors using the same SVM classifier. Experiment results manifest the effectiveness of the proposed approach.
Showing items related by title, author, creator and subject.
Lindfield, S.; Harvey, Euan; Halford, A.; McIlwain, Jennifer (2016)Coral reefs are subjected to unprecedented levels of disturbance with population growth and climate change combining to reduce standing coral cover and stocks of reef fishes. Most of the damage is concentrated in shallow ...
“You shouldn’t have to suffer for being who you are”: An examination of the Human Library strategy for challenging prejudice and increasing respect for differenceWatson, Gregory John (2015)This qualitative research examines the Human Library method of engaging people in dialogue to challenge prejudice and increase respect for difference and human rights. Its data, collected via participant-observation and ...
Amirshahi, Mirahmad (1997)The main purpose of this research is to identify the value systems and decision-making styles of Iranian managers. The relationships between their value systems and decision styles, and between their value systems and ...