Search

In this paper, we present our investigation of the 2D Hand Gesture Recognition (HGR) which may be suitable for the control of the Automated Guided Vehicle (AGV). In real conditions, we deal with, among others, a complex background, changing lighting conditions, and different distances of the operator from the AGV. For this reason, in the article, we describe the database of 2D images created during the research. We tested classic algorithms and modified them by us ResNet50 and MobileNetV2 which were retrained partially using the transfer learning approach, as well as proposed a simple and effective Convolutional Neural Network (CNN). As part of our work, we used a closed engineering environment for rapid prototyping of vision algorithms, i.e., Adaptive Vision Studio (AVS), currently Zebra Aurora Vision, as well as an open Python programming environment. In addition, we shortly discuss the results of preliminary work on 3D HGR, which seems to be very promising for future work. The results show that, in our case, from the point of view of implementing the gesture recognition methods in AGVs, better results may be expected for RGB images than grayscale ones. Also using 3D imaging and a depth map may give better results.

The moisture of bulk material has a significant impact on the energetic efficiency of dry grinding, resultant particle size distribution and particle shape, and conditions of powder transport. This research aims to develop computer vision and thermovision techniques for the on-site estimation of moisture content in copper ore, for use, e.g., in dry grinding installations. The influence of particle size on the results of moisture estimation is also studied. The tested granular material was copper ore of particle size 0-2 mm and relative moisture content of 0.5-11%. Both vision and thermovision images were taken at standard and macro scales. The results suggest that median-intensity vision images monotonically reflect copper ore moisture in the range of about 0.5-5%. Suitable models were identified and cross-validated here. In contrary, thermograms should not be analyzed simply for their mean temperature but treated with computer vision processing algorithms.

Moisture of bulk material has a significant impact on energetic efficiency of dry grinding, resultant particle size distribution and particle shape, and conditions of powder transport. As a consequence, moisture needs to be measured or estimated (modelled) in many points. This research investigates mutual relations between material moisture and particle classification process in a grinding installation. The experimental setup involves an inertial-impingement classifier and cyclone being part of dry grinding circuit with electromagnetic mill and recycle of coarse particles. The tested granular material is copper ore of particle size 0-1.25 mm and relative moisture content 0.5-5%, fed to the installation at various rates. Higher moisture of input material is found to change the operation of the classifier. Computed correlation coefficients show increased content of fine particles in lower product of classification. Additionally, drying of lower and upper classification products with respect to moisture of input material is modelled. Straight line models with and without saturation are estimated with recursive least squares method accounting for measurement errors in both predictor and response variables. These simple models are intended for use in automatic control system of the grinding installation.

Analysis of the structural vibration, under the sound excitation is an important part of the quality assurance during the design process of devices. One of the most commonly used method is Laser Doppler Vibrometry (LDV). However, under the rapid fluctuations of temperature, structural resonances are shifted into the other frequencies. In such situation LDV method may be inconvenient, due to the scanning time. In this paper the authors proposed Chladni figures to modal analysis of the double-panel structure, excited by the loudspeaker enclosed inside the casing with a rigid frame. Double-panel structure has been proven to be particularly useful for noise and vibration reduction applications. Vision images, obtained during the experiments are converted to binary patterns, using GLCM matrix, and compared with simulations performed in ANSYS.

This paper presents a machine vision method for detection and classification of copper ore grains. We proposed a new method that combines both seeded regions growing segmentation and edge detection, where region growing is limited only to grain boundaries. First, a 2D Fast Fourier Transform (2DFFT) and Gray-Level Co-occurrence Matrix (GLCM) are calculated to improve the detection results and processing time by eliminating poor quality samples. Next, detection of copper ore grains is performed, based on region growing, improved by the first and second derivatives with a modified Niblack's theory and a threshold selection method. Finally, all the detected grains are characterized by a set of shape features, which are used to classify the grains into separate fractions. The efficiency of the algorithm was evaluated with real copper ore samples of known granularity. The proposed method generates information on different granularity fractions at a time with a number of grain shape features., Competing Interests: The authors declare no conflict of interest.