In video-based fish surveys, species recognition plays a vital role in stock assessments, ecosystem analysis, production management, and protection of endangered species. However, implementing fish species detection algorithms in underwater environments presents significant challenges due to factors such as varying lighting conditions, water turbidity, and the diverse appearances of fish species. In this work, a transformer-enhanced YOLOv8 (YOLOv8-TF) is proposed for underwater fish species recognition. The YOLOv8-TF enhances the performance of YOLOv8 by adjusting depth scales, incorporating a transformer block into the backbone and neck, and introducing a class-aware loss function to address class imbalance in the dataset. The class-aware loss considers the count of instances within each species and assigns a higher weight to species with fewer instances. This approach enables fish species recognition through object detection, encompassing the classification of each fish species and localization to estimate their position and size within an image. Experiments were conducted using the 2021 Southeast Area Monitoring and Assessment Program (SEAMAPD21) dataset, a detailed and extensive reef fish dataset from the Gulf of Mexico. The experimental results on SEAMAPD21 demonstrate that the YOLOv8-TF model, with a mean Average Precision (mAP)_0.5 of 87.9% and mAP_0.5–0.95 of 61.2%, achieves better detection results for underwater fish species recognition compared to state-of-the-art YOLO models. Additionally, experimental results on the publicly available datasets, such as Pascal VOC and MS COCO datasets demonstrate that the model outperforms existing approaches.

Accurate traffic light detection and classification are fundamental for autonomous vehicle (AV) navigation and real-time traffic management in complex urban environments. Existing systems often fall short of reliably identifying and classifying traffic light states in real-time, including their flashing modes. This study introduces FlashLightNet, a novel end-to-end deep learning framework that integrates the nano version of You Only Look Once, version 10m (YOLOv10n) for traffic light detection, Residual Neural Networks 18 (ResNet-18) for feature extraction, and a Long Short-Term Memory (LSTM) network for temporal state classification. The proposed framework is designed to robustly detect and classify traffic light states, including conventional signals (red, green, and yellow) and flashing signals (flash red and flash yellow), under diverse and challenging conditions such as varying lighting, occlusions, and environmental noise. The framework has been trained and evaluated on a comprehensive custom dataset of traffic light scenarios organized into temporal sequences to capture spatiotemporal dynamics. The dataset has been prepared by taking videos of traffic lights at different intersections of Starkville, Mississippi, and Mississippi State University, consisting of red, green, yellow, flash red, and flash yellow. In addition, simulation-based video datasets with different flashing rates—2, 3, and 4 s—for traffic light states at several intersections were created using RoadRunner, further enhancing the diversity and robustness of the dataset. The YOLOv10n model achieved a mean average precision (mAP) of 99.2% in traffic light detection, while the ResNet-18 and LSTM combination classified traffic light states (red, green, yellow, flash red, and flash yellow) with an F1-score of 96%.

Reliable perception of roadway signals is critical for autonomous vehicles operating in complex urban environments, particularly when traffic lights convey safety-critical instructions through flashing and arrow indications that extend beyond conventional red, yellow, and green states. However, most existing vision-based approaches focus primarily on static traffic-light recognition and lack robust mechanisms for interpreting temporal behaviors such as flashing signals. To address this limitation, this paper proposes a unified real-time perception framework, termed HybridSignalNet, for multi-class recognition of traffic lights, road signs, and lane-related roadway elements. The framework combines spatial detection with temporal state reasoning to interpret both steady and flashing signal patterns in video streams. Experimental evaluation demonstrates strong performance across multiple object classes, achieving an average detection F1-score of 91.3%, while traffic-light state classification reaches 96.7%, including reliable identification of flashing and arrow-based signals. The proposed system operates in real-time and provides an interpretable and deployable solution for intelligent transportation systems and autonomous driving applications, particularly at signalized intersections where temporal signal understanding is essential for safe decision-making.

Tracking underwater fish species is crucial for population monitoring, stock assessments, ecological balance, and endangered species protection. While image processing and computer vision have advanced fish detection and classification, tracking remains a more challenging and less-explored task, particularly in natural underwater environments. This work utilizes the GFISHERD24 dataset, collected from the Gulf of Mexico in 2024, which contains frame-annotated videos of fish species in their natural habitats. This dataset presents real-world challenges, including multiple fish in a single frame, low-light conditions, and occlusions from other fish or vertical structures, making detection and tracking highly difficult. To address these challenges, we adopt YOLOX, an anchor-free and high-performance object detector, and adapt the ByteTrack algorithm for robust multi-object tracking. Unlike traditional methods, ByteTrack retains and associates both high and low confidence detections, enabling more accurate tracking of occluded or low-visibility fish. Our dataset was converted to MS COCO format for detection training and MOT17 format for tracking evaluation. On the test set, the adapted ByteTrack achieved a MOTA of 60.6% and MOTP of 0.303 for 983 ground truth objects across 45 videos. Given the dataset's complexity, we emphasize the importance of filtering out low-quality videos and enhancing image frames of these poor videos via image quality assessment (IQA) for tuning ByteTrack's hyperparameters. This improves detection reliability and boosts tracking accuracy by enhancing visual features used for data association. In conclusion, with targeted preprocessing and tuned hyperparameters, ByteTrack proves effective for large-scale underwater fish tracking in challenging environments.