Recent advancements in the field of machine learning (ML) provide opportunity to conduct research on autonomous devices for a variety of applications. Intelligent decision-making is a critical task for self-driving systems. An attempt is made in this study to use a deep learning (DL) approach for the early detection of road cracks, potholes, and the yellow lane. The accuracy is not sufficient after training with the default model. To enhance accuracy, a convolutional neural network (CNN) model with 13 convolutional layers, a softmax layer as an output layer, and two fully connected layers (FCN) are constructed. In order to achieve the deeper propagation and to prevent saturation in the training phase, mish activation is employed in the first 12 layers with a rectified linear unit (ReLU) activation function. The upgraded CNN model performs better than the default CNN model in terms of accuracy. For the varied situation, a revised and enriched dataset for road cracks, potholes, and the yellow lane is created. The yellow lane is detected and tracked in order to move the unmanned aerial vehicle (UAV) autonomously by following yellow lane. After identifying a yellow lane, the UAV performs autonomous navigation while concurrently detecting road cracks and potholes using the robot operating system within the UAV. The performance model is benchmarked using performance measures, such as accuracy, sensitivity, F1-score, F2-score, and dice-coefficient, which demonstrate that the suggested technique produces better outcomes.

This study proposes an intelligent approach to identifying an injured soldier on blockchain-integrated internet-of-battlefield things (IoBT) employing unmanned aerial vehicles (UAVs). The intelligent approach combines a unique deep learning (DL) model with a smartwatch-based heart-rate (HR) data collection technique. Different activation functions (i.e., MISH and Leaky rectified linear unit) are used in the proposed DL model to enhance the identification task by extracting the in-depth features from the images. Furthermore, a smart-watch-based HR data analyzing technique is introduced to confirm the injury of a soldier. However, due to the UAV’s low battery capacity, the identification task is offloaded to the neighboring edge computing server to improve system performance. Moreover, to restrict the access of registered IoT devices (e.g., UAV, smartwatch, etc.) and protect the sensitive data leakage on IoBT, a blockchain-integrated access control (ACL) mechanism is utilized. Detailed experimental results are provided for the proposed DL model that outperforms existing DL models. Besides, implementing a smartwatch-based HR data analysis technique for the soldiers improves the outcome of the proposed DL model. To provide a fine-grained data protection mechanism in the proposed system, a private blockchain-based ACL management policy is constructed utilizing hyperledger, and various assessment metrics have been scrutinized.