×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerIn recent times, artificial intelligence has become an essential part of our lives, particularly in tasks involving object recognition. This paper explores the use of convolutional neural networks (CNNs) for enhancing underwater search and rescue operations by classifying images of humans, fish, and plants. Leveraging the OpenCV library for preprocessing and the Keras library with a TensorFlow backend for recognition, this study utilizes a dataset captured through field experiments. The methodology involved preprocessing the images for segmentation, followed by training a CNN model to classify these images with high accuracy. The CNN model demonstrated a remarkable classification accuracy of 99.6 %, significantly outperforming other modern machine-learning methods. This work suggests that CNNs can greatly improve the speed and effectiveness of underwater search and rescue operations by accurately identifying and locating submerged persons, which is critical for timely rescue missions.
The autonomous navigation of robots is an important area of research. It can intelligently navigate itself from source to target within an environment without human interaction. Recently, algorithms and techniques have been made and developed to improve the performance of robots. It’s more effective and has high precision tasks than before. This work proposed to solve a maze using a Flood fill algorithm based on real time camera monitoring the movement on its environment. Live video streaming sends an obtained data to be processed by the server. The server sends back the information to the robot via wireless radio. The robot works as a client device moves from point to point depends on server information. Using camera in this work allows voiding great time that needs it to indicate the route by the robot.