Evaluation of Keypoint Descriptors for Flight Simulator Cockpit Elements: WrightBroS Database

The goal of the WrightBroS project is to design a system supporting the training of pilots in a flight simulator. The desired software should work on smart glasses supplementing the visual information with augmented reality data, displaying, for instance, additional training information or descriptions of visible devices in real time. Therefore, the rapid recognition of observed objects and their exact positioning is crucial for successful deployment. The keypoint descriptor approach is a natural framework that is used for this purpose. For this to be applied, the thorough examination of specific keypoint location methods and types of keypoint descriptors is required first, as these are essential factors that affect the overall accuracy of the approach. In the presented research, we prepared a dedicated database presenting 27 various devices of flight simulator. Then, we used it to compare existing state-of-the-art techniques and verify their applicability. We investigated the time necessary for the computation of a keypoint position, the time needed for the preparation of a descriptor, and the classification accuracy of the considered approaches. In total, we compared the outcomes of 12 keypoint location methods and 10 keypoint descriptors. The best scores recorded for our database were almost 96% for a combination of the ORB method for keypoint localization followed by the BRISK approach as a descriptor.

Detection of Glaucoma using ORB (Oriented FAST and Rotated BRIEF) Feature Extraction

This research was utilized to identify glaucoma, a type of eye illness. This endeavor necessitates the use of pictures from the fundus camera for image processing. This study reflects the effort done to detect glaucoma-affected eyes utilizing image feature extraction using Oriented FAST and Rotated BRIEF (ORB). ORB is a binary descriptor approach that is based on BRIEF and is highly fast. This technique is insensitive to picture noise and is invariant to any rotation. ORB is two orders of magnitude faster than SURF and performs similarly to SIFT. It is more efficient than other texture analysis methods. It is less computationally difficult than other approaches in the literature. This technique extracts features and detects texture by inspecting each pixel of the retina picture. It was trained on 160 fundus pictures of normal and glaucoma-affected retinas. After that, any healthy or glaucoma-affected eye may be easily recognized by obtaining an accurate eye picture. The results reveal that this technique has a precision and accuracy of more than 90%.

Rearranged Descriptor Approach based on Radon Transform to Digits Recognition

In this paper, the Radon transform method is used to generate a set of rotation invariant characteristics. Experiments of our approach were carried out on a database of ten decimal digits (0 to 9) in 24 different orientations from 0° to 360 ° by a step of 15 °. A multilayer perceptron neural network is used in the classification phase to test the effectiveness of our approach. The proposed approach is noise-effective and leads to a classification rate equal to 100 % for images without noise and a classification rate equal to 95.2 for images with noise.

A Fourier Descriptor Approach to Integrated Type and Dimensional Synthesis of Coupled Serial Mechanism for Motion Generation

Coupled serial mechanism is a class of mechanisms that couple the relative rotation of successive links utilizing gears or cable-pulley systems. They can be used to generate complex end-effector trajectories or motions with a single actuator. With the employment of Fourier descriptors, a novel approach to integrate type synthesis and dimensional synthesis of such mechanisms is proposed in this paper. Through the Fourier analysis of two arbitrary trajectories from the given motion, the simplest trajectory that contains the least number of harmonic components is identified. Then, characteristic information of those harmonics such as their numbers, amplitudes and initial phases are used to determine the topology and dimensions of the corresponding coupled serial mechanism, thus effectively solving the motion synthesis problem of this type of mechanisms. Finally, three examples are given to demonstrate the validity of the proposed method.