Segmentation of Stereo-Camera Depth Image into Planar Regions based on Evolving Principal Component Clustering

This paper presents an approach of depth image segmentation based on the Evolving Principal Component Clustering (EPCC) method, which exploits data locality in an ordered data stream. The parameters of linear prototypes, which are used to describe different clusters, are estimated in a recursive manner. The main contribution of this work is the extension and application of the EPCC to 3D space for recursive and real-time detection of flat connected surfaces based on linear segments, which are all detected in an evolving way. To obtain optimal results when processing homogeneous surfaces, we introduced two-step filtering for outlier detection within a clustering framework and considered the noise model, which allowed for the compensation of characteristic uncertainties that are introduced into the measurements of depth sensors. The developed algorithm was compared with well-known methods for point cloud segmentation. The proposed approach achieves better segmentation results over longer distances for which the signal-to-noise ratio is low, without prior filtering of the data. On the given database, an average rate higher than 90% was obtained for successfully detected flat surfaces, which indicates high performance when processing huge point clouds in a non-iterative manner.

Download Full-text

Outdoor Localization in Mobile Robot with 3D LiDAR Based on Principal Component Analysis and K-Nearest Neighbors Algorithm

Engineering and Technology Journal ◽

10.30684/etj.v39i6.2032 ◽

2021 ◽

Vol 39 (6) ◽

pp. 965-976

Author(s):

Hanan A. Atiyah ◽

Mohammed Y. Hassan

Keyword(s):

Mobile Robot ◽

Principal Component ◽

Light Sensitivity ◽

Training Data ◽

Depth Image ◽

Lidar Data ◽

K Nearest Neighbor ◽

Training Time ◽

Outdoor Localization ◽

3D Lidar

Localization is one of the potential challenges for a mobile robot. Due to the inaccuracy of GPS systems in determining the location of the moving robot alongside weathering effects on sensors such as RGBs (e.g. rain and light-sensitivity(. This paper aims to improve the localization of mobile robots by combining the 3D LiDAR data with RGB-D images using deep learning algorithms. The proposed approach is to design an outdoor localization system. It is divided into three stages. The first stage is the training stage where 3D LiDAR scans the city and then reduces the dimensions of 3D LiDAR data to 2.5D image. This is based on PCA method where these data are used as training data. The second stage is the testing data stage. RGB and depth image in IHS method are combined to generate 2.5D fusion image. The training and testing of these datasets are based on using Convolution Neural Network. The third stage consists of using the K-Nearest Neighbor algorithm. This is the classification stage to get high accuracy and reduces the training time. The experimental results obtained prove the superiorly of the proposed approach with accuracy up to 97.52%, Mean Square of Error of 0.057568, and Mean error in distance equals 0.804 meters.

Download Full-text

Merging of Depth Image Between Stereo Camera and Structure Sensor on Robot “FloW” Vision

International Journal on Advanced Science Engineering and Information Technology ◽

10.18517/ijaseit.7.2.2176 ◽

2017 ◽

Vol 7 (3) ◽

pp. 1014

Author(s):

Dadet Pramadihanto ◽

Ardiansyah Alfarouq ◽

Suryo Aji Waskitho ◽

Sritrusta Sukaridhoto

Keyword(s):

Depth Image ◽

Stereo Camera ◽

Structure Sensor

Download Full-text

3-D People Counting with a Stereo Camera on GPU Embedded Board

Applied Sciences ◽

10.3390/app8112017 ◽

2018 ◽

Vol 8 (11) ◽

pp. 2017 ◽

Cited By ~ 1

Author(s):

Gyu-cheol Lee ◽

Sang-ha Lee ◽

Jisang Yoo

Keyword(s):

Real Time ◽

Stereo Matching ◽

Depth Image ◽

Depth Information ◽

People Detection ◽

Real Time Processing ◽

Stereo Camera ◽

People Counting ◽

Time Operation ◽

Real Time Operation

People counting in surveillance cameras is a key technology for understanding the flow population and generating heat maps. In recent years, people detection performance has been greatly improved with the development of object detection algorithms using deep learning. However, in places where people are crowded, the detection rate is low as people are often occluded by other people. We proposed a people-counting method using a stereo camera to resolve the non-detection problem due to the occlusion. We applied stereo matching to extract the depth image and convert the camera view to top view using depth information. People were detected using a height map and an occupancy map, and people were tracked and counted using a Kalman filter-based tracker. We operated the proposed method on the NVIDIA Jetson TX2 to check the real-time operation possibility on the embedded board. Experimental results showed that the proposed method had higher accuracy than the existing methods and that real-time processing is possible.

Download Full-text

Edge Detection from RGB-D Image Based on Structured Forests

Journal of Sensors ◽

10.1155/2016/5328130 ◽

2016 ◽

Vol 2016 ◽

pp. 1-10 ◽

Cited By ~ 4

Author(s):

Heng Zhang ◽

Zhenqiang Wen ◽

Yanli Liu ◽

Gang Xu

Keyword(s):

Random Forest ◽

Edge Detection ◽

Random Forests ◽

Information Gain ◽

Fundamental Problem ◽

Principal Component ◽

Bilateral Filter ◽

Depth Image ◽

Image Information ◽

Pca Method

This paper looks into the fundamental problem in computer vision: edge detection. We propose a new edge detector using structured random forests as the classifier, which can make full use of RGB-D image information from Kinect. Before classification, the adaptive bilateral filter is used for the denoising processing of the depth image. As data sources, information of 13 channels from RGB-D image is computed. In order to train the random forest classifier, the approximation measurement of the information gain is used. All the structured labels at a given node are mapped to a discrete set of labels using the Principal Component Analysis (PCA) method. NYUD2 dataset is used to train our structured random forests. The random forest algorithm is used to classify the RGB-D image information for extracting the edge of the image. In addition to the proposed methodology, the quantitative comparisons of different algorithms are presented. The results of the experiments demonstrate the significant improvements of our algorithm over the state of the art.

Download Full-text

Multi process matching depth image between stereo camera and structure sensor in realtime

2017 International Electronics Symposium on Engineering Technology and Applications (IES-ETA) ◽

10.1109/elecsym.2017.8240391 ◽

2017 ◽

Author(s):

Rimsya Anjarlistiawan ◽

Ardiansyah Al Farouq ◽

Sritrusta Sukaridhoto ◽

Raden Sanggar Dewanto ◽

Dadet Pramadihanto

Keyword(s):

Depth Image ◽

Stereo Camera ◽

Structure Sensor

Download Full-text

Digital Processing of STEM Images

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100097752 ◽

1981 ◽

Vol 39 ◽

pp. 236-237

Author(s):

A. V. Crewe ◽

M. Ohtsuki

Keyword(s):

High Resolution ◽

Low Dose ◽

Assembly Language ◽

Processing System ◽

Principal Component ◽

Digital Processing ◽

Image Analysis System ◽

Black And White ◽

Analysis System ◽

Dose Imaging

We have assembled an image processing system for use with our high resolution STEM for the particular purpose of working with low dose images of biological specimens. The system is quite flexible, however, and can be used for a wide variety of images.The original images are stored on magnetic tape at the microscope using the digitized signals from the detectors. For low dose imaging, these are “first scan” exposures using an automatic montage system. One Nova minicomputer and one tape drive are dedicated to this task.The principal component of the image analysis system is a Lexidata 3400 frame store memory. This memory is arranged in a 640 x 512 x 16 bit configuration. Images are displayed simultaneously on two high resolution monitors, one color and one black and white. Interaction with the memory is obtained using a Nova 4 (32K) computer and a trackball and switch unit provided by Lexidata.The language used is BASIC and uses a variety of assembly language Calls, some provided by Lexidata, but the majority written by students (D. Kopf and N. Townes).

Download Full-text

Scanning x-ray fluorescence microscopy and principal component analysis

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100133394 ◽

1992 ◽

Vol 50 (2) ◽

pp. 1752-1753

Author(s):

Brian Cross

Keyword(s):

Principal Component Analysis ◽

Fluorescence Microscopy ◽

Spatial Resolution ◽

High Speed ◽

Image Acquisition ◽

Principal Component ◽

Fluorescence Microscope ◽

Acquisition Rate ◽

X Ray ◽

Speed Up

A relatively new entry, in the field of microscopy, is the Scanning X-Ray Fluorescence Microscope (SXRFM). Using this type of instrument (e.g. Kevex Omicron X-ray Microprobe), one can obtain multiple elemental x-ray images, from the analysis of materials which show heterogeneity. The SXRFM obtains images by collimating an x-ray beam (e.g. 100 μm diameter), and then scanning the sample with a high-speed x-y stage. To speed up the image acquisition, data is acquired "on-the-fly" by slew-scanning the stage along the x-axis, like a TV or SEM scan. To reduce the overhead from "fly-back," the images can be acquired by bi-directional scanning of the x-axis. This results in very little overhead with the re-positioning of the sample stage. The image acquisition rate is dominated by the x-ray acquisition rate. Therefore, the total x-ray image acquisition rate, using the SXRFM, is very comparable to an SEM. Although the x-ray spatial resolution of the SXRFM is worse than an SEM (say 100 vs. 2 μm), there are several other advantages.

Download Full-text

Quantitative Analysis Of X-Ray Images From Geological Materials

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s042482010013482x ◽

1990 ◽

Vol 48 (2) ◽

pp. 244-245

Author(s):

J. M. Paque ◽

R. Browning ◽

P. L. King ◽

P. Pianetta

Keyword(s):

Quantitative Analysis ◽

Bulk Composition ◽

Principal Component ◽

Analytical Description ◽

Bulk Sample ◽

Geological Samples ◽

X Ray ◽

Software And Hardware ◽

And Storage ◽

Insight Into

Geological samples typically contain many minerals (phases) with multiple element compositions. A complete analytical description should give the number of phases present, the volume occupied by each phase in the bulk sample, the average and range of composition of each phase, and the bulk composition of the sample. A practical approach to providing such a complete description is from quantitative analysis of multi-elemental x-ray images.With the advances in recent years in the speed and storage capabilities of laboratory computers, large quantities of data can be efficiently manipulated. Commercial software and hardware presently available allow simultaneous collection of multiple x-ray images from a sample (up to 16 for the Kevex Delta system). Thus, high resolution x-ray images of the majority of the detectable elements in a sample can be collected. The use of statistical techniques, including principal component analysis (PCA), can provide insight into mineral phase composition and the distribution of minerals within a sample.

Download Full-text