International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

Visual points of interest have various application in different fields of engineering and applied sciences. In example they are used to estimate position and orientation of the scanning device, whether it is a camera, LIDAR or sonar, which is crucial in environment, lacking inertial navigation system. Also are heavily used in Simultaneous Localization And Mapping (SLAM), as well in scene reconstruction and other applications in robotics. The current paper explore the performance of different image descriptors in underwater environment. The lack of navigation system in such environment requires use of said descriptors to estimate the position and orientation of the camera in respect to not moving object.

Automatic classification of seismic sources finds vast application security domain. Due to restricted computational power in the edge devices a robust and less complex features need to be extracted and sent to appropriate classifier. Such features are histograms of oriented gradients. It represented the relative spectral distribution of derivative of amplitude against frequency instead of average spectral envelope.

Decision making in conflict data is a problem that plague the information fusion. It is usually resolved by the use of probabilistic methods such as Bayes. Still Bayes becomes impractical in strong presence of conflicts or lack of data. In that case Dempster–Shafer (DS) evidence theory is applied, because of its ability to handle conflicting sensor inputs. Because of that, DS-based information fusion is very popular in decision-making applications, although the classic combinatorial rule may produce counter intuitive results, especially when combining evidences with high level of conflict. The paper present a method which can be applied to the decision making process, thus resolving this problem.

The paper addresses the problem of acoustic signal classification and report the current state of the art in the field. More specifically the paper sheds light on the mathematical apparatus behind one specific method used for classification of sound sources – SVM (support vector machines). As well we propose use of histogram of oriented gradients (HOG) as features descriptor and explain how they work.