Object re-identification (reID) plays a pivotal role in traffic surveillance systems for matching objects like people, cars, and motorcycles across multiple cameras. This is an active area of research in both industry and academia due to the ever-growing population and need for smart surveillance, public safety, and traffic management. Most current reID methods use deep convolutional neural networks as the backbone that are manually designed, which does not have the optimum settings as the network complexity increases. This paper introduces MNASreID, an automated approach for designing deep convolutional neural networks designed specifically for motorcycle reID. Key contributions include proposing a NAS based optimization framework and designing a comprehensive search space covering backbone architectures and hyperparameters. Grasshopper optimization algorithm used as NAS search strategy to find the optimal DNN model. Experimental results on two motorcycle datasets, MoRe and BPReID, demonstrate MNASreID’s ability to automatically identify efficient DNN models for reID tasks. Comparative evaluation against existing algorithms reveals significant performance enhancements. Specifically, MNASreID achieves a notable improvement of +1.14% and +1.24% in r1 and mAP metrics, respectively, on the MoRe dataset. On the BPReID dataset, it outperforms existing approaches by +26.82% and +29.56% in r1 and mAP metrics, respectively.

Accurately classifying medical images with multiple labels is essential for early disease detection and enhancing clinical decision-making. In contrast to singlelabel classification, multi- label approaches allow for the simultaneous identification of multiple co- existing pathologies in a single image. Deep learning approaches, including convolutional neural networks and transformer- based models, have shown promising results, but they often suffer from high computational costs and lack of explainability, making them impractical for many medical applications. To address these challenges, this study introduces a novel lightweight transformer- based neural network optimized for multi- label medical image classification, reducing computational complexity while preserving strong feature extraction capabilities. Evaluations on the ChestX- ray11 dataset show superior classification accuracy and computational efficiency compared to existing methods. Furthermore, Grad- CAM++ visualizations enhance interpretability by highlighting disease- relevant regions, fostering trust in medical AI applications.

The growing reliance on automobiles as the most common form of transportation and the increase in traffic has led to the need to implement essential safety measures. The driver's alertness is critical to the safety of passengers in the vehicle. Existing methods for driver distraction detection face significant challenges as they rely on manually crafted features using traditional machine learning approaches, which are time-consuming to design, require domain expertise, and often fail to adapt to diverse real-world conditions. Although deep learning models have addressed some of these limitations by automatically extracting discriminative features, manually designed deep learning models struggle to handle complex driver distraction scenarios such as texting, yawning, and talking on the phone. The Deep Neural Network (DNN) models are well-known for their effectiveness across various computer vision tasks, including object localization and classification. However, manually designing efficient DNN models requires expertise. Even this may not always lead to an optimal model. To overcome this limitation, we propose the utilization of Neural Architecture Search (NAS) to design an automated method for generating DNN models. This work presents a framework for building a single-stage object detection model based on a NAS using an improved Genetic Algorithm (GA) for search strategy. The improved GA consists of Evaluation Correction based Selection (ECS) and Species Protection based Next Generation Population (SPNGP) to efficiently explore the search space and identify optimal backbone and training parameters. The designed search space includes the You Only Look Once (YOLO) backbone architecture parameters and associated training parameters. The experimental results suggest that the DNN model identified by the proposed approach has a smaller size and achieved better performance than the existing one-stage and two-stage object detection models, demonstrating the efficacy of our approach in designing driver distraction detection systems.

Automobiles are the primary means of transportation and increased traffic leads to the emphasis on techniques for safe transportation. Vehicle brake light detection is essential to avoid collisions among vehicles. Even though motorcycles are a common mode of transportation in many developing countries, little research has been done on motorcycle brake light detection. The effectiveness of Deep Neural Network (DNN) models has led to their adoption in different domains. The efficiency of the manually designed DNN architecture is dependent on the expert's insight on optimality, which may not lead to an optimal model. Recently, Neural Architecture Search (NAS) has emerged as a method for automatically generating a task-specific backbone for object detection and classification tasks. In this work, we propose a genetic algorithm based NAS approach to construct a Mask R-CNN based object detection model. We designed the search space to include the architecture of the backbone in Mask R-CNN along with attributes used in training the object detection model. Genetic algorithm is used to explore the search space to find the optimal backbone architecture and training attributes. We achieved a mean accuracy of 97.14% and 89.44% for detecting brake light status for two-wheelers (on NITW-MBS dataset) and four-wheelers (on CaltechGraz dataset) respectively. The experimental study suggests that the architecture obtained using the proposed approach exhibits superior performance compared to existing models.

Recognition of brake light status in vehicles is crucial for anticipating speed changes and preventing rear-end collisions for autonomous driving systems. Existing literature presents two types of methods for brake light detection: hand-crafted feature-based methods and deep learning-based methods. However, hand-crafted methods often struggle to capture brake light characteristics accurately in real-life conditions. In contrast, deep learning-based systems can adapt to diverse brake light variations across different vehicle types and environments. Nevertheless, manually designing Deep Neural Network (DNN) models requires expertise and is prone to errors. To address this limitation, we propose a novel approach that leverages Neural Architecture Search (NAS) to automatically generate optimal DNN architectures for object detection tasks, specifically for brake light detection. In contrast to the existing NAS approaches that focus on classification models, our technique explores NAS for object detection tasks. We employ a modified Differential Evolution algorithm, incorporating evaluation correction-based selection for mutation and species protection-based selection to identify the optimal DNN backbone architecture with optimal training parameters. The proposed approach achieved mean accuracy of 89.73 %, and 88.90 % on four-wheeler datasets CaltechGraz and UC Merced Vehicle Rear Signal datasets, respectively, and it has achieved 97.97 % on the proposed two-wheeler NITW-MBS dataset. The proposed approach's generalization capability and practical applicability are ascertained through cross-dataset evaluation and experiments on real-world traffic video.

The detection of brake light plays an important role in applications such as autonomous driving, to avoid rear-end collision. In this work, we propose a frame work to identify the location of two-wheelers and their brake lights in traffic visual data using a deep learning-based approach. The system uses the Yolo object detection model for multi-class detection and localization. The experimental study was conducted on a new dataset of two-wheeler vehicles in traffic.