Despite the rapid advances in deep learning (DL) for object detection, existing techniques still face several challenges. In particular, object detection in adverse weather conditions (AWCs) requires complex and computationally costly models to achieve high accuracy rates. Furthermore, the generalization capabilities of these methods struggle to show consistent performance under different conditions. This work focuses on improving object detection using You Only Look Once (YOLO) versions 5, 7, and 9 in AWCs for autonomous vehicles. Although the default values of the hyperparameters are successful for images without AWCs, there is a need to find the optimum values of the hyperparameters in AWCs. Given the many numbers and wide range of hyperparameters, determining them through trial and error is particularly challenging. In this study, the Gray Wolf Optimizer (GWO), Artificial Rabbit Optimizer (ARO), and Chimpanzee Leader Selection Optimization (CLEO) are independently applied to optimize the hyperparameters of YOLOv5, YOLOv7, and YOLOv9. The results show that the preferred method significantly improves the algorithms’ performances for object detection. The overall performance of the YOLO models on the object detection for AWC task increased by 6.146%, by 6.277% for YOLOv7 + CLEO, and by 6.764% for YOLOv9 + GWO.

In this article, a novel pitch determination algorithm based on harmonic differences method (HDM) is proposed. Most of the algorithms today rely on autocorrelation, cepstrum, and lastly convolutional neural networks, and they have some limitations (small datasets, wideband or narrowband, musical sounds, temporal smoothing, etc.), accuracy, and speed problems. There are very rare works exploiting the spacing between the harmonics. HDM is designed for both wideband and exclusively narrowband (telephone) speech and tries to find the most repeating difference between the harmonics of speech signal. We use three vowel databases in our experiments, namely, Hillenbrand Vowel Database, Texas Vowel Database, and Vowels from the TIMIT corpus. We compare HDM with autocorrelation, cepstrum, YIN, YAAPT, CREPE, and FCN algorithms. Results show that harmonic differences are reliable and fast choice for robust pitch detection. Also, it is superior to others in most cases.

Feature extraction is a crucial stage in speech emotion recognition applications, and filter banks with their related statistical functions are widely used for this purpose. Although Mel filters and MFCCs achieve outstanding results, they do not perfectly model the structure of the human ear, as they use a simplified mechanism to simulate the functioning of human cochlear structures. The Mel filters system is not a perfect representation of human hearing, but merely an engineering shortcut to suppress the pitch and low-frequency components, which have little use in traditional speech recognition applications. However, speech emotion recognition classification is heavily related to pitch and low-frequency component features. The newly tailored CARFAC 24 model is a sophisticated system for analyzing human speech and is designed to best simulate the functionalities of the human cochlea. In this study, we use the CARFAC 24 system for speech emotion recognition and compare it with state-of-the-art systems using speaker-independent studies conducted with Time-Distributed Convolutional LSTM networks and Support Vector Machines, with the use of the ASED and the NEMO emotional speech dataset. The results demonstrate that CARFAC 24 is a valuable alternative to Mel and MFCC features in speech emotion recognition applications.

This study sheds light on the daunting task of single-object tracking using state-of-the-art BoT-SORT, DeepSORT, SORT, and ByteTrack tracking algorithms with YOLO-NAS and YOLO11 object detectors. Object tracking is a step further of object detection and tries to detect the movement of objects in video files and it has enormous range of real-world application fields. Object tracking also assigns unique identifiers to each tracked object and tries to maintain the identity throughout the entire sequence. Current models can achieve great success in object tracking, however there are still too many obstacles and challenges lying ahead to resolve. YOLO-NAS and YOLO11 are the latest and most used object detection models. YOLO can be combined with different tracking methods such as ByteTrack, BoT-SORT, SORT, and DeepSORT for object tracking. The advantage of YOLO is its extremely fast implementation compared to the other methods. When accompanied by specialized tracking algorithms, YOLO achieves the best scores in object tracking. This study focuses on the implementation of YOLO-NAS and YOLO11 in tracking and results demonstrate that YOLO11 is more accurate and stable with BoT-SORT, however, it is faster using ByteTrack method.

This study focuses on the performance evaluation of mainstream object detection model, namely, YOLO12, Mask-RCNN, RT-DETR, and RF-DETR on the Open Images (Multi-Object) and LaSOT (Single-Object) datasets. Object detection is one of the key technologies in computer vision tasks and very significant developments have been made during the last decades. Current cutting-edge trend applications involve CNN-based and transformer-based object detection models. CNN-based models can use one-pass (YOLO family) or two-pass (R-CNN family) implementations. One-pass object detection models can be faster but suffer from accuracy compared to the two-pass models. Transformer-based models can use Detection Transformers or Vision Transformers. Transformer-based models are gaining popularity, and their performance surpasses CNN-based models. Transformer-based models are also improving their speed. This study evaluates YOLO12 and Mask R-CNN from CNN-based family, and RT-DETR and RF-DETR transformer-based architectures in terms of accuracy and time on the Open Images and LaSOT datasets. All models are the largest models provided by the owners and pretrained on COCO dataset. Transformer-based models incorporate special types of self-attention and pose significant improvement both on accuracy and speed. The experimental results demonstrate that attention and transformer-based models perform better than the traditional CNN-based object detectors.