Adam Mahir Mohammed Sharif, AlEisa Hussah Nasser, Zanin Samah Al, Marzouk Radwa
Department of Computer and Self Development, Preparatory Year Deanship, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia.
Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
Sci Rep. 2025 Jul 1;15(1):20759. doi: 10.1038/s41598-025-04959-5.
A significant challenge for many visually impaired people is they cannot be entirely independent and are restricted by their vision. They face problems with such actions and object detection should be an essential feature they can rely on a regular basis. Object detection is applied to discover objects in the real world from an image of the world, like chairs, bicycles, tables, or doors, that are normal in the scenes of a blind predicated on their places. Computer vision (CV) involves the automated extraction, understanding, and analysis of valuable information from a sequence of images or a single image. Machine learning (ML) and deep learning (DL) are significant and robust learning architectures broadly established, especially for CV applications. This study proposes a novel Advanced Object Detection for Smart Accessibility using the Marine Predator Algorithm to aid visually challenged people (AODSA-MPAVCP) model. The main intention of the AODSA-MPAVCP model is to enhance object detection techniques using advanced models for disabled people. Initially, the image pre-processing stage applies adaptive bilateral filtering (ABF) to eliminate the unwanted noise in input image data. Furthermore, the proposed AODSA-MPAVCP model utilizes the YOLOv10 model for object detection. Moreover, the feature extraction process employs the VGG19 method to transform raw data into meaningful and informative features. The deep belief network (DBN) technique is used for the classification process. Finally, the marine predator algorithm (MPA)-based hyperparameter selection process is performed to optimize the classification results of the DBN technique. The experimental evaluation of the AODSA-MPAVCP approach is examined under the Indoor object detection dataset. The performance validation of the AODSA-MPAVCP approach portrayed a superior accuracy value of 99.63% over existing models.
对许多视障人士来说，一个重大挑战是他们无法完全独立，行动受到视力限制。他们在诸如此类的行动中面临问题，物体检测应该是他们可以经常依赖的一项基本功能。物体检测用于从世界图像中发现现实世界中的物体，如椅子、自行车、桌子或门，这些在盲人场景中根据其位置来看是常见的。计算机视觉（CV）涉及从一系列图像或单幅图像中自动提取、理解和分析有价值的信息。机器学习（ML）和深度学习（DL）是广泛确立的重要且强大的学习架构，尤其适用于计算机视觉应用。本研究提出了一种使用海洋捕食者算法辅助视障人士的新型智能无障碍高级物体检测（AODSA - MPAVCP）模型。AODSA - MPAVCP模型的主要目的是使用先进模型增强针对残疾人的物体检测技术。最初，图像预处理阶段应用自适应双边滤波（ABF）来消除输入图像数据中的不必要噪声。此外，所提出的AODSA - MPAVCP模型利用YOLOv10模型进行物体检测。而且，特征提取过程采用VGG19方法将原始数据转换为有意义且信息丰富的特征。深度信念网络（DBN）技术用于分类过程。最后，执行基于海洋捕食者算法（MPA）的超参数选择过程以优化DBN技术的分类结果。在室内物体检测数据集下对AODSA - MPAVCP方法进行了实验评估。AODSA - MPAVCP方法的性能验证显示出比现有模型更高的准确率值，为99.63%。
