Person Following Robot with Vision-based and Sensor Fusion Tracking Algorithm

Sonoura, Takafumi; Yoshimi, Takashi; Nishiyama, Masayoshi; Nakamoto, Hideichi; Tokura, Seiji; Matsuhira, Nobuto

doi:10.5772/6161

Cited by 25 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There have been various personal identification methods using face detection system [16]- [19]. However, if the face cannot be seen, these methods cannot be used.…”

Section: Introductionmentioning

confidence: 99%

Improved personal identification method for guide robots using dress color information via KINECT

Sato

Wada

2013

2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)

View full text Add to dashboard Cite

In this paper, a Simple Personal Identification (SPI) method using Dress Color Information (DCI) for guide robots is proposed. The DCI is a small number of color information that is only calculated at narrow areas around a user's (guided person's) joint positions obtained via KINECT on a mobile robot. The SPI method includes not only the person's skeletal information but also the DCI. This method can identify the specific user in real time. As a result, even if the mobile robot loses the user temporarily when there are many people present, it can find the user properly and promptly. Our previous research had four problems as follows: 1) there is a position error between skeletal joint positions and pixel positions in RGBA camera image, 2) the narrow areas around joint positions often overflows from the dress areas, 3) changing lighting environments causes wrong results, and 4) the personal conformity is unstable. To cope with these difficulties, an improved calculating method using correction functions and color information of all joint points as a vector different from previous method is proposed in this research. The experimental results show the accuracy of our new method.

show abstract

“…There have been various personal identification methods using face detection system [16]- [19]. However, if the face cannot be seen, these methods cannot be used.…”

Section: Introductionmentioning

confidence: 99%

Improved personal identification method for guide robots using dress color information via KINECT

Sato

Wada

2013

2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)

View full text Add to dashboard Cite

show abstract

“…Robot bisa mendapatkan gambar resolusi tinggi secara real time. [2] Pintu dan benda umum yang berada dalam lingkungan didalam ruangan, dapat di deteksi oleh sebuah robot dengan menggunakan sistem navigasi untuk memetakan bangunan. Paper ini menyajikan pendekatan baru untuk mendeteksi pintu di dalam ruangan yang berda pada lingkungan dengan menggunakan visi komputer.…”

unclassified

Penerapan Metode Hough Line Transform Untuk Mendeteksi Pintu Ruangan Menggunakan Kamera

Muharom

2017

Media Komunikasi Teknologi

View full text Add to dashboard Cite

The camera is often used to identify an object in the field of view of the camera. The ABSTRAKKamera sering digunakan untuk mengenali suatu benda dalam bidang pandang kamera. Pintu adalah salah satu bagian terpenting dari suatu ruangan, dimana pintu adalah akses keluar dam masuknya seseorang dalam ruangan tersebut. Dalam penelitian ini kamera difungsikan untuk mendeteksi keberadaan pintu sebuah ruangan. Proses untuk pendeteksian pintu adalah dengan pengenalan ciri-ciri dari pintu ruangan, citra pintu yang di capture kamera diubah menjadi citra gray, dengan edge detection citra menjadi bentuk biner, dan hough-transform. Dari hasil pengolahan citra menggunkan hough-transform, citra menjadi pola garis-garis pada bagian bingkai pintu, garis-garis inilah yang dijadikan parameter dalam mendeteksi pintu ruangan. Sistem dapat mendeteksi pintu dengan nilai rata-rata 81.3%, dimana nilai luminasi sangat mempengaruhi pendeteksian pintu ruangan. Dengan nilai liminasi kurang dari 120 dan lebih dari 350, tingkat akurasi sistem sebesar 73.3%, dan dengan nilai luminasi 224-230, tingkat akurasi sistem sebesar 93.3%. Dapat disimpulkan bahwa nilai luminasi sangat mempengaruhi dalam pendeteksian pintu ruangan, dan dengan nilai luminasi sebesar 120-349 tingkat keberhasilan sebesar 80-93.3%.Kata Kunci: Kamera, Pintu Ruangan, Hough lineTransform PENDAHULUAN Kamera sering digunakan untuk melacak benda bergerak yang berada dalam bidang pandang mereka, ini menjelaskan desain dan pengembangan kamera yang digunakan di dalam sebuah robot. Pelacakan berbasis kamera yang dilakukan terus-menerus dapat menangkap obyek bergerak tanpa perlunya kalibrasi kamera. [1]. Robot mendapatkan gambar dari target dengan menggunakan kamera yang akan menjadi referensi robot. Robot bisa mendapatkan gambar resolusi tinggi secara real time. [2] Pintu dan benda umum yang berada dalam lingkungan didalam ruangan, dapat di deteksi oleh sebuah robot dengan menggunakan sistem navigasi untuk memetakan bangunan. Paper ini menyajikan pendekatan baru untuk mendeteksi pintu di dalam ruangan yang berda pada lingkungan dengan menggunakan visi komputer. Pintu yang akan dicari dalam gambar yang telah diolah menjadi gray-level, kamera akan mendeteksi segmen yang membentuk kusen. Hough-

show abstract

“…They describe their solutions to following in a cluttered, domestic environment. Sonoura et al [16] fuse laser range data with vision data to implement a personfollowing robot. As with most HRI applications, their control handles both following the person and obstacle avoidance.…”

Section: Introductionmentioning

confidence: 99%

In Situ Motion Capture of Speed Skating: Escaping the Treadmill

Boyd

Godbout

Thornton

2012

2012 Ninth Conference on Computer and Robot Vision

View full text Add to dashboard Cite

Abstract-The advent of the Kinect depth imager has opened the door to motion capture applications that would have been much more costly with previous technologies. In part, the Kinect achieves this by focusing on a very specific application domain, thus narrowing the requirement for the motion capture system. Specifically, Kinect motion capture works best within a small physical space while the camera is stationary. We seek to extend Kinect motion capture for use in athletic training -speed skating in particular -by placing the Kinect on a mobile, robotic platform to capture motion in situ. Athletes move over large distances, so the mobile platform addresses the limited viewing area of the Kinect. As the platform moves, we must also account for the now dynamic background against which the athlete performs. The result is a novel, visuallyguided robotic platform that follows athletes, allowing us to capture motion and images that would not be possible with a treadmill. We describe the system in detail and give examples of the system capturing the motion of a speed skater at typical training speeds.

show abstract

Person Following Robot with Vision-based and Sensor Fusion Tracking Algorithm

Cited by 25 publications

References 13 publications

Improved personal identification method for guide robots using dress color information via KINECT

Improved personal identification method for guide robots using dress color information via KINECT

Penerapan Metode Hough Line Transform Untuk Mendeteksi Pintu Ruangan Menggunakan Kamera

In Situ Motion Capture of Speed Skating: Escaping the Treadmill

Contact Info

Product

Resources

About