This work presents a new approach to speech recognition, based on the specific coding of time and frequency characteristics of speech. The research proposed the use of convolutional neural networks because, as we know, they show high resistance to cross-spectral distortions and differences in the length of the vocal tract. Until now, two layers of time convolution and frequency convolution were used. A novel idea is to weave three separate convolution layers: traditional time convolution and the introduction of two different frequency convolutions (mel-frequency cepstral coefficients (MFCC) convolution and spectrum convolution). This application takes into account more details contained in the tested signal. Our idea assumes creating patterns for sounds in the form of RGB (Red, Green, Blue) images. The work carried out research for isolated words and continuous speech, for neural network structure. A method for dividing continuous speech into syllables has been proposed. This method can be used for symmetrical stereo sound.
The paper presents the generalization of the almost forty years of experience in the field of setting and solving the multiple criteria decision-making (MCDM) problems in various branches of a human activity under different types of uncertainties that inevitably accompany such problems. Based only on the pragmatic intentions, the authors avoid the detailed descriptions of the known methods for the decision-making, while instead focusing on the most frequently used mathematical tools and methodologies in the decision-making practice. Therefore, the paper may be classified as a special kind of illustrative review of the mathematical tools that are focused on applications and are the most used in the solutions of MCDM problems. As an illustrative example, a complete user-friendly computer implementation of such tools and methodology is presented with application to the simple “buying a cat” problem, which, however, possesses all the attributes of the hierarchical fuzzy MCDM task.
The subject of the work described in this article is the detection of false synchronization in the transmission of digital stereo images. Until now, the synchronization problem was solved by using start triggers in the recording. Our proposal checks the discrepancy between the received pairs of images, which allows you to detect delays in transferring images between the left camera and the right camera. For this purpose, a deep network is used to classify the analyzed pairs of images into five classes: MuchFaster, Faster, Regular, Slower, and MuchSlower. As can be seen as a result of the conducted work, satisfactory research results were obtained as the correct classification. A high percentage of average probability in individual classes also indicates a high degree of certainty as to the correctness of the results. An author’s base of colorful stereo images in the number of 3070 pairs is used for the research.
Horizontal road markings are crucial for safe driving and for the operation of advanced driver-assistance systems (ADAS), but they have been investigated less thoroughly than vertical signs or lane boundaries. This paper focuses on the detection and classification of horizontal road markings in digital images using modern deep learning techniques. Three YOLO models (YOLOv7, YOLOv8n, YOLOv9t) were trained and tested on a new dataset comprising 6250 images with 13,360 annotated horizontal road-marking objects across nine classes collected on Polish roads in sunny and cloudy conditions. The dataset covers nine classes of markings recorded on urban streets, rural roads and highways. It includes many difficult cases: small markings visible only from long distance or side entry roads, and markings with different levels of wear, from new and bright to faded, dirty or partially erased. YOLOv7 achieved Precision = 0.95, Recall = 0.91 and mAP@0.5 = 0.98. YOLOv8n and YOLOv9t obtained lower Recall but higher mAP@0.5:0.95 (>0.77). The results confirm that YOLO-based detectors can handle horizontal road markings under varied road conditions and degrees of visibility, and the dataset with baseline results may serve as a reference for further studies in intelligent transport systems.
This research aimed to develop a system for classifying horizontal road signs as correct or with poor visibility. In Poland, road markings are applied by using a specialized white, reflective paint and require periodic repainting. Our developed system is designed to assist in the decision-making process regarding the need for repainting. It operates by analyzing images captured by a standard car camera or driving recorder. The image data undergo initial segmentation and classification processes, facilitated by the utilization of the YOLOv4-Tiny neural network model. The input data to the network consist of frames extracted from the video stream. To train the model, we established our proprietary database, which comprises 6250 annotated images and video frames captured during driving. The annotations provide detailed information about object types, their locations within the image, and their sizes. The trained neural network model effectively identifies and classifies objects within our dataset. Subsequently, based on the classification results, the identified image fragments are subjected to further analysis. The analysis relies on assessing pixel-level contrasts within the images. Notably, the road surface is intentionally designed to be dark, while road signs exhibit relatively lighter colors. In conclusion, the developed system serves the purpose of determining the correctness or visibility quality of horizontal road signs. It achieves this by leveraging computer vision techniques, deep learning with YOLOv4-Tiny, and a meticulously curated database. Ultimately, the system provides valuable information regarding the condition of specific horizontal road signs, aiding in the decision-making process regarding potential repainting needs.
1 December 2022 in Journal of Applied Mathematics and Computational Mechanics
Journal of Applied Mathematics and Computational Mechanics, Prace Naukowe Instytutu Matematyki i Informatyki, Politechnika Częstochowska, Scientific Research of the Institute of Mathematics and Computer Science, Czestochowa University of Technology