Human detection using depth information by Kinect

By Lu Xia, Chia-Chih Chen, Jake K. Aggarwal. CVPR 2011 WORKSHOPS, 2011

606 citations recorded by the source corpus.

Conventional human detection is mostly done in images taken by visible-light cameras. These methods imitate the detection process that human use. They use features based on gradients, such as histograms of oriented gradients (HOG), or extract interest points in the image, such as scale-invariant feature transform (SIFT), etc. In this paper, we present a novel human detection method using depth information taken by the Kinect for Xbox 360. We propose a model based approach, which detects humans using a 2-D head contour model and a 3-D head surface model. We propose a segmentation scheme to segment the human from his/her surroundings and extract the whole contours of the figure based on our detection point. We also explore the tracking algorithm based on our detection result. The methods are tested on our database taken by the Kinect in our lab and present superior results.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9fb6623d30478df59b0e87326ce7fa2861b4e91a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos (2017, methodology): “Different from the existing point cloud projection-based [10], [36] or depth-template-based [7], [10] proposal generation methods, our approach quickly and directly finds possible head-tops from depth images so that more computationally intensive classification process needs to be applied to only a ”
Efficient Interaction Recognition through Positive Action Representation (2013, positive): “In [19], the UTKinect-human detection dataset was created: there are 98 frames with two people appearing in the scene at different depths in a variety of poses, including several simple interactions.”
Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor (2012, methodology): “[6] proposed a model based approach which detects humans using a 2-D head contour model and a 3-D head surface model.”
Online RGB-D gesture recognition with extreme learning machines (2013, background): “Several algorithms have been developed to extract the human skeleton from the depth images in realtime [24, 30].”
50 Years of object recognition: Directions forward (2013, background): “Within the context of more recent work, the success of Kinect-based systems [296, 297, 298, 299] demonstrates how combined active and passive sensing systems improve recognition.”
Video-Based Human Behavior Understanding: A Survey (2013, methodology): “[67] perform detection by using a 2-D head contour model and a 3-D head surface model, in a constrained office area.”