Human Detection in Top-View Depth Image
نویسندگان
چکیده
The paper presents an efficient and reliable feature descriptor for human detection in a top-view depth image that uses two statistical values of mean and standard deviation. Human detection performance of our descriptor outperform Rauter that use mean value and Simplified Local Ternary Pattern (SLTP). To evaluate the human detection performance using our descriptor, we capture 559 positive and 2382 negative top-view depth images. We get 98.1% precision and 94.2% recall rates. Run-time performance of our descriptor is reasonably fast. Human detection using the proposed descriptor can be applicable in detecting multiple human and tracking real time in top-view depth images.
منابع مشابه
Persian sign language detection based on normalized depth image information
There are many reports of using the Kinect to detect hand and finger gestures after release of device by Microsoft. The depth information is mostly used to separate the hand image in the two-dimension of RGB domain. This paper proposes a method in which the depth information plays a more dominant role. Using a threshold in depth space first the hand template is extracted. Then in 3D domain the ...
متن کاملMulti-View Face Detection in Open Environments using Gabor Features and Neural Networks
Multi-view face detection in open environments is a challenging task, due to the wide variations in illumination, face appearances and occlusion. In this paper, a robust method for multi-view face detection in open environments, using a combination of Gabor features and neural networks, is presented. Firstly, the effect of changing the Gabor filter parameters (orientation, frequency, standard d...
متن کامل3D Human Tracking in a Top View Using Depth Information Recorded by the Xtion Pro-Live Camera
This paper addresses the problem of the tracking of 3D human body pose from depth image sequences given by a Xtion Pro-Live camera. Human body poses could be estimated through model fitting using dense correspondences between depth data and an articulated human model. Although, most of the time for the video surveillance, the camera is placed above the persons, all the tracking methods use the ...
متن کاملEvaluation of the role of system matrix in SPECT images reconstructed by OSEM technique
Introduction: Ordered subset expectation maximization (OSEM), is an effective iterative method for SPECT image reconstruction. The aim of this study is the evaluation of the role of system matrix in OSEM image reconstruction method using four different physical beam radiation models with three detection configurations. Methods: SPECT was done with an arc of 180 deg...
متن کاملDepth Improvement for FTV Systems Based on the Gradual Omission of Outliers
Virtual view synthesis is an essential part of computer vision and 3D applications. A high-quality depth map is the main problem with virtual view synthesis. Because as compared to the color image the resolution of the corresponding depth image is low. In this paper, an efficient and confided method based on the gradual omission of outliers is proposed to compute reliable depth values. In the p...
متن کامل