Towards Silhouette-Aware Human Detection in Depth Images

2021 ◽  
Author(s):  
Huan Luo ◽  
Shuiwang Li ◽  
Qijun Zhao
Keyword(s):  
Human Detection ◽  
Depth Images

POSE ROBUST HUMAN DETECTION IN DEPTH IMAGES USING MULTIPLY-ORIENTED 2D ELLIPTICAL FILTERS

2010 ◽  
Vol 24 (05) ◽  
pp. 691-717 ◽  
Author(s):  
SANG-HO CHO ◽  
TAEWAN KIM ◽  
DAIJIN KIM
Keyword(s):  
Human Identification ◽  
Human Detection ◽  
Stereo Images ◽  
Bhattacharyya Distance ◽  
Identification Method ◽  
Depth Images ◽  
Detection And Identification ◽  
The Face ◽  
Human Pose ◽  
Spatial Depth

This paper proposes a pose robust human detection and identification method for sequences of stereo images using multiply-oriented 2D elliptical filters (MO2DEFs), which can detect and identify humans regardless of scale and pose. Four 2D elliptical filters with specific orientations are applied to a 2D spatial-depth histogram, and threshold values are used to detect humans. The human pose is then determined by finding the filter whose convolution result was maximal. Candidates are verified by either detecting the face or matching head-shoulder shapes. Human identification employs the human detection method for a sequence of input stereo images and identifies them as a registered human or a new human using the Bhattacharyya distance of the color histogram. Experimental results show that (1) the accuracy of pose angle estimation is about 88%, (2) human detection using the proposed method outperforms that of using the existing Object Oriented Scale Adaptive Filter (OOSAF) by 15–20%, especially in the case of posed humans, and (3) the human identification method has a nearly perfect accuracy.

ROBUST HUMAN DETECTION WITH OCCLUSION HANDLING BY FUSION OF THERMAL AND DEPTH IMAGES FROM MOBILE ROBOT

2016 ◽  
Vol 78 (6-13) ◽  
Author(s):  
Saipol Hadi Hasim ◽  
Rosbi Mamat ◽  
Usman Ullah Sheikh ◽  
Shamsuddin Mohd Amin
Keyword(s):  
Mobile Robot ◽  
Surveillance System ◽  
Object Classification ◽  
Human Detection ◽  
Experimental Results ◽  
Indoor Environments ◽  
Occlusion Handling ◽  
Illumination Variations ◽  
Depth Images ◽  
Three Stages

In this paper, a robust surveillance system to enable robots to detect humans in indoor environments is proposed. The proposed method is based on fusing information from thermal and depth images which allows the detection of human even under occlusion. The proposed method consists of three stages; pre-processing, ROI generation and object classification. A new dataset was developed to evaluate the performance of the proposed method. The experimental results show that the proposed method is able to detect multiple humans under occlusions and illumination variations.  

Multiple human detection in depth images

2016 ◽  
Author(s):  
Muhammad Hassan Khan ◽  
Kimiaki Shirahama ◽  
Muhammad Shahid Farid ◽  
Marcin Grzegorzek
Keyword(s):  
Human Detection ◽  
Depth Images ◽  
Multiple Human Detection

scholarly journals Human Detection by Fourier Descriptors and Fuzzy Color Histograms with Fuzzyc-Means Method

2016 ◽  
Vol 28 (4) ◽  
pp. 491-499 ◽  
Author(s):  
Shohei Akimoto ◽  
◽  
Tomokazu Takahashi ◽  
Masato Suzuki ◽  
Yasuhiko Arai ◽  
...  
Keyword(s):  
Human Detection ◽  
Color Histogram ◽  
Fourier Descriptors ◽  
Person Detection ◽  
Depth Images ◽  
Histograms Of Oriented Gradients ◽  
Outdoor Environments ◽  
Person Search ◽  
Fuzzy Color Histogram ◽  
P Type

[abstFig src='/00280004/07.jpg' width='300' text='Result of specific person detection in Tsukuba Challenge' ] It is difficult to use histograms of oriented gradients (HOG) or other gradient-based features to detect persons in outdoor environments given that the background or scale undergoes considerable changes. This study involved the segmentation of depth images. Additionally, P-type Fourier descriptors were extracted as shape features from two-dimensional coordinates of a contour in the segmentation domains. With respect to the P-type Fourier descriptors, a person detector was created with the fuzzyc-means method (for general person detection). Furthermore, a fuzzy color histogram was extracted in terms of color features from the RGB values of the domain surface. With respect to the fuzzy color histogram, a detector of a person wearing specific clothes was created with the fuzzyc-means method (specific person detection). The study includes the following characteristics: 1) The general person detection requires less number of images used for learning and is robust against a change in the scale when compared to that in cases in which HOG or other methods are used. 2) The specific person detection gives results close to those obtained by human color vision when compared to the color indices such as RGB or CIEDE. This method was applied for a person search application at the Tsukuba Challenge, and the obtained results confirmed the effectiveness of the proposed method.

Human detection from still depth images

2016 ◽  
Vol 2016 (21) ◽  
pp. 1-9 ◽  
Author(s):  
Gulsum Nurdan Can ◽  
Helin Dutagaci
Keyword(s):  
Human Detection ◽  
Depth Images
Sign in / Sign up

Export Citation Format

Share Document