Techniques for the detection and recognition of objects have experienced continuous development over recent years, as their application and benefits are so very obvious. Whether they are involved in driving a car, environment surveillance and security, or assistive living for people with different disabilities, not to mention advanced robotic surgery, these techniques are almost indispensable. This article presents the research results of a distance assessment using object detection and recognition techniques. The first is a new technique based on low-cost photo cameras and special sign detection. The second is a classic approach based on a LIDAR sensor and an HQ photo camera. Its novelty, in this case, consists of the concept and prototype of the hardware subsystem for high-precision distance measurement, as well as fast and accurate object recognition. The experimentally obtained results are used for the motion control strategy (directional inverse kinematics) of the robotic arm (virtual prototype) component in special assistive devices designed for visually impaired persons. The advantages of the original technical solution, experimentally validated by a prototype system with modern equipment, are the precision and the short time required for the identification and recognition of objects at relatively short distances. The research results obtained, in both the real and virtual experiments, stand as a basis for the further development of the visually impaired mechatronic system prototype using additional ultrasonic sensors, stereoscopic or multiple cameras, and the implementation of machine-learning models for safety-critical tasks.

An introduction of the sonification theory and its applications to the medical imaging is presented in this paper. The sonification theory is known in the literature as the transformation of the image into sound by means of a linear operator based on the linear theory of sound propagation. By reversing back to image, an inverse problem has to be solved in order to find if the sound discovers or not new details in the original image. When the classical sonification operator is applied in the inverse problem, no image enhancement is achieved and no details are discovered. This is probably because the classical operator is based on the linear theory of sound propagation. In this paper a new sonification algorithm is advanced based on the Burgers equation of sound propagation. The new algorithm is able to bring improvements in the medical image by inversion. It earns gains in improvement of the medical image by capturing hardly detectable details in the unclear original images. The approach is exercised on fictive ultrasound images of human and rat livers.