Self-localization based on image features of omni-directional image

Hibino, Fuminori; Yuta,; Takahashi, Yasutake; Maeda, Yoichiro

doi:10.1109/scis-isis.2012.6505325

Cited by 4 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Su menggunakan deskriptor global untuk melakukan lokalisasi. Lokalisasi diri berdasarkan data citra arena sepak bola robot dilakukan oleh Hibino (Hibino, Yuta, Takahashi, & Maeda, 2012). Fitur citra yang diambil dari kamera omni dibandingkan dengan citra acuan.…”

Section: Pendahuluanunclassified

Lokalisasi Mobile Robot berdasarkan Citra Kamera OMNI menggunakan Fitur Surf

Rasmana¹,

Harianto²,

Susanto³

et al. 2020

JTIIK

View full text Add to dashboard Cite

Deteksi lokasi diri atau lokalisasi diri adalah salah satu kemampuan yang harus dimiliki oleh mobile robot. Kemampuan lokalisasi diri digunakan untuk menentukan posisi robot di suatu daerah dan sebagai referensi untuk menentukan arah perjalanan selanjutnya. Dalam penelitian ini, lokalisasi robot didasarkan pada data citra yang ditangkap oleh kamera omnidirectional tipe catadioptric. Jumlah fitur terdekat antara citra 360o yang ditangkap oleh kamera Omni dan citra referensi menjadi dasar untuk menentukan prediksi lokasi. Ekstraksi fitur gambar menggunakan metode Speeded-Up Robust Features (SURF). Kontribusi pertama dari penelitian ini adalah optimasi akurasi deteksi dengan memilih nilai Hessian Threshold dan jarak maksimum fitur yang tepat. Kontribusi kedua optimasi waktu deteksi menggunakan metode yang diusulkan. Metode ini hanya menggunakan fitur 3 gambar referensi berdasarkan hasil deteksi sebelumnya. Optimasi waktu deteksi, untuk lintasan dengan 28 gambar referensi, dapat mempersingkat waktu deteksi sebesar 8,72 kali. Pengujian metode yang diusulkan dilakukan menggunakan omnidirectional mobile robot yang berjalan di suatu daerah. Pengujian dilakukan dengan menggunakan metode recall, presisi, akurasi, F-measure, G-measure, dan waktu deteksi. Pengujian deteksi lokasi juga dilakukan berdasarkan metode SIFT untuk dibandingkan dengan metode yang diusulkan. Berdasarkan pengujian, kinerja metode yang diusulkan lebih baik daripada SIFT untuk pengukuran dengan recall 89,67%, akurasi 99,59%, F-measure 93,58%, G-measure 93,87%, dan waktu deteksi 0,365 detik. Metode SIFT hanya lebih baik pada presisi 98,74%. AbstractSelf-location detection or self-localization is one of the capabilities that must be possessed by the mobile robot. The self-localization ability is used to determine the robot position in an area and as a reference to determine the next trip direction. In this research, robot localization was by vision-data based, which was captured by catadioptric-types omnidirectional cameras. The number of closest features between the 360o image captured by the Omni camera and the reference image was the basis for determining location predictions. Image feature extraction uses the Speeded-Up Robust Features (SURF) method. The first contribution of this research is the optimization of detection accuracy by selecting the Hessian Threshold value and the maximum distance of the right features. The second contribution is the optimization of detection time using the proposed method. This method uses only the features of 3 reference images based on the previous detection results. Optimization of detection time, for trajectories with 28 reference images, can shorten the detection time by 8.72 times. Testing the proposed method was done using an omnidirectional mobile robot that walks in an area. Tests carried out using the method of recall, precision, accuracy, F-measure, G-measure, and detection time. Location detection testing was also done based on the SIFT method to be compared with the proposed method. Based on testing, the proposed method performance is better than SIFT for measurements with recall 89.67%, accuracy 99.59%, F-measure 93.58%, G-measure 93.87%, and detection time 0.365 seconds. The SIFT method is only better at precision 98.74%.

show abstract

Section: Pendahuluanunclassified

Lokalisasi Mobile Robot berdasarkan Citra Kamera OMNI menggunakan Fitur Surf

Rasmana¹,

Harianto²,

Susanto³

et al. 2020

JTIIK

View full text Add to dashboard Cite

show abstract

“…Each robot must comprise a completely independent vision system as well as self-contained powering and motoring mechanisms, and autonomously accomplish certain behaviors; for example, navigating the game field and following the ball. Therefore, the omni-vision system is generally used to acquire environmental information around an autonomous mobile robot for it to accomplish self-localization [4][5][6]. Fig.…”

Section: Introductionmentioning

confidence: 99%

“…θ m1 +θ m2 ) •sin(θ m2 +θ m3 ) sin θ m2 •sin(θ m1 +θ m2 +θ m3 )(5) CR c = sin(θ c1 +θ c2 ) •sin(θ c2 +θ c3 ) sin θ c2 •sin(θ c1 +θ c2 +θ c3 )(6) To locate the robot (Point O), on the map, the CR principle was applied twice. First, A was used as a focus to determine the CR(A) for both the camera and map, indicated as CR c (A) and CR m (A), respectively, indicated by the blue lines inFigs.…”

mentioning

confidence: 99%

Self-localization for an autonomous mobile robot based on an omni-directional vision system

2014

View full text Add to dashboard Cite

In this study, we designed an autonomous mobile robot based on the rules of the Federation of International Robotsoccer Association (FIRA) RoboSot category, integrating the techniques of computer vision, real-time image processing, dynamic target tracking, wireless communication, self-localization, motion control, path planning, and control strategy to achieve the contest goal. The self-localization scheme of the mobile robot is based on the algorithms featured in the images from its omni-directional vision system. In previous works, we used the image colors of the field goals as reference points, combining either dual-circle or trilateration positioning of the reference points to achieve selflocalization of the autonomous mobile robot. However, because the image of the game field is easily affected by ambient light, positioning systems exclusively based on color model algorithms cause errors. To reduce environmental effects and achieve the self-localization of the robot, the proposed algorithm is applied in assessing the corners of field lines by using an omni-directional vision system. Particularly in the mid-size league of the RobotCup soccer competition, selflocalization algorithms based on extracting white lines from the soccer field have become increasingly popular. Moreover, white lines are less influenced by light than are the color model of the goals.Therefore, we propose an algorithm that transforms the omni-directional image into an unwrapped transformed image, enhancing the extraction features. The process is described as follows: First, radical scan-lines were used to process omni-directional images, reducing the computational load and improving system efficiency. The lines were radically arranged around the center of the omni-directional camera image, resulting in a shorter computational time compared with the traditional Cartesian coordinate system. However, the omni-directional image is a distorted image, which makes it difficult to recognize the position of the robot. Therefore, image transformation was required to implement self-localization. Second, we used an approach to transform the omni-directional images into panoramic images. Hence, the distortion of the white line can be fixed through the transformation. The interest points that form the corners of the landmark were then located using the features from accelerated segment test (FAST) algorithm. In this algorithm, a circle of sixteen pixels surrounding the corner candidate is considered and is a high-speed feature detector in real-time frame rate applications. Finally, the dual-circle, trilateration, and cross-ratio projection algorithms were implemented in choosing the corners obtained from the FAST algorithm and localizing the position of the robot. The results demonstrate that the proposed algorithm is accurate, exhibiting a 2-cm position error in the soccer field measuring 600 cm 2 x 400 cm 2 .

show abstract

Real time self-localization of omni-vision robot by pattern match system

Chiang

Guo

2014

2014 International Conference on Advanced Robotics and Intelligent Systems (ARIS)

View full text Add to dashboard Cite

Self-localization based on image features of omni-directional image

Cited by 4 publications

References 6 publications

Lokalisasi Mobile Robot berdasarkan Citra Kamera OMNI menggunakan Fitur Surf

Lokalisasi Mobile Robot berdasarkan Citra Kamera OMNI menggunakan Fitur Surf

Self-localization for an autonomous mobile robot based on an omni-directional vision system

Real time self-localization of omni-vision robot by pattern match system

Contact Info

Product

Resources

About