Localization Of A Mobile Fastening Robot

<div>The goal of this research is to develop a localization system for a mobile fastening robot using a camera and ultrasonic sensors. Localization is performed by using triangulation methods on three target fastener heads. Camera calibration parameters are determined and used to obtain a corrected image on which a Circular Hough Transform algorithm is used to determine the location of the three target fastener heads relative to the camera. The distance to the fastener heads is determined using readings from two ultrasonic sensors. A Kalman Filter is developed and used to reduce the noise of the ultrasonic sensor readings. In addition to filtering, calibration techniques are used to correct the readings of the final localization system. Testing of the complete system is done using a coordinate measuring machine. </div>

Localization Of A Mobile Fastening Robot

<div>The goal of this research is to develop a localization system for a mobile fastening robot using a camera and ultrasonic sensors. Localization is performed by using triangulation methods on three target fastener heads. Camera calibration parameters are determined and used to obtain a corrected image on which a Circular Hough Transform algorithm is used to determine the location of the three target fastener heads relative to the camera. The distance to the fastener heads is determined using readings from two ultrasonic sensors. A Kalman Filter is developed and used to reduce the noise of the ultrasonic sensor readings. In addition to filtering, calibration techniques are used to correct the readings of the final localization system. Testing of the complete system is done using a coordinate measuring machine. </div>

LOCALIZATION OF A MOBILE FASTENING ROBOT

<div>The goal of this research is to develop a localization system for a mobile fastening robot using a camera and ultrasonic sensors. Localization is performed by using triangulation methods on three target fastener heads. Camera calibration parameters are determined and used to obtain a corrected image on which a Circular Hough Transform algorithm is used to determine the location of the three target fastener heads relative to the camera. The distance to the fastener heads is determined using readings from two ultrasonic sensors. A Kalman Filter is developed and used to reduce the noise of the ultrasonic sensor readings. In addition to filtering, calibration techniques are used to correct the readings of the final localization system. Testing of the complete system is done using a coordinate measuring machine. </div>

Uji Deteksi Objek Bentuk Bola Dengan Menerapkan Metode Circular Hough Transform

Abstrak— Deteksi objek bentuk bola merupakan salah satu penerapan dari teknologi image processing yang saat ini banyak digunakan untuk teknologi robotika. Kemampuan dalam mengenali objek tertentu dalam berbagai kondisi lingkungan merupakan salah satu syarat teknologi image processing ini disebut handal. Untuk mengetahui kehandalannya maka perlu dilakukan pengujian. Uji deteksi objek berwarna bentuk bola dilakukan dengan melakukan pengujian terhadap perubahan kondisi lingkungan dimana objek tersebut berada, diantaranya dengan pengujian deteksi objek bentuk bola dengan variasi ukuran bola, pengujian deteksi objek bentuk bola dengan variasi perubahan intensitas cahaya dan pengujian deteksi objek bentuk bola dengan variasi perubahan jarak objek terhadap kamera. Dengan tiga pengujian yang telah dilakukan dengan metode hough transform yang diterapkan pada deteksi objek bentuk bola ini, diperoleh kesimpulan bahwa deteksi objek mampu mengenali variasi ukuran bola dengan diameter 16,9mm, 31mm, 63,7mm dan 95,8mm. Deteksi objek mampu mengenali bola dengan baik pada intensitas cahaya antara 80lux – 117lux. Dan deteksi objek mampu mengenali bola pada jarak 30cm – 140cm.

Content Based Image Retrieval System for Lung Cancer Detection Using Neural Network and Circular Hough Transform

Computer Aided Detection (CAD) systems that automatic detection and localize lung nodules in CT scans. A major problem in this system is a large number of false positives because of no provision for comparison of the predicted output. This paper recommends a new system with a combination of CBIR and neural network to full fill the gap in the area of early detection of lung cancer. From the preprocessed CT scan image, the system identifies whether it contains nodules using Circular Hough Transform and classifies into benign or malignant nodule using Probabilistic Neural Network. Then, it searched for the most identical pictures and retrieved it from the database. From the retrieved image, it is easy to identify the present cancer stage of the patient. Experiments have done based on both LIDC database and the locally collected database. The performance evaluation of the system is done by using both. The experimental results show that the present study easily differentiates benign and malignant nodules with an efficiency of 97 % accuracy on LIDC dataset, 95 % accuracy on Local dataset and similar images are retrieved with its present stage from the available database with a higher precision and recall rate.

Embedding Convolution Neural Network-Based Defect Finder for Deployed Vision Inspector in Manufacturing Company Frontec

In collaboration with Frontec, which produces parts such as bolts and nuts for the automobile industry, Kyung Hee University and Benple Inc. develop and deploy AI system for automatic quality inspection of weld nuts. Various constraints to consider exist in adopting AI for the factory, such as response time and limited computing resources available. Our convolutional neural network (CNN) system using large-scale images must classify weld nuts within 0.2 seconds with accuracy over 95%. We designed Circular Hough Transform based preprocessing and an adjusted VGG (Visual Geometry Group) model. The system showed accuracy over 99% and response time of about 0.14 sec. We use TCP / IP protocol to communicate the embedded classification system with an existing vision inspector using LabVIEW. We suggest ways to develop and embed a deep learning framework in an existing manufacturing environment without a hardware change.