Open Access

ARTICLE

Meyer Wavelet Transform and Jaccard Deep Q Net for Small Object Classification Using Multi-Modal Images

Mian Muhammad Kamal^1,*, Syed Zain Ul Abideen², M. A. Al-Khasawneh^3,4, Alaa M. Momani⁴, Hala Mostafa⁵, Mohammed Salem Atoum⁶, Saeed Ullah⁷, Jamil Abedalrahim Jamil Alsayaydeh^8,*, Mohd Faizal Bin Yusof⁹, Suhaila Binti Mohd Najib⁸

1 School of Electronic and Communication Engineering, Quanzhou University of Information Engineering, Quanzhou, 362000, China
2 College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, 518060, China
3 Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, 19111, Jordan
4 School of Computing, Skyline University College, University City Sharjah, Sharjah, 1797, United Arab Emirates
5 Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
6 Computer Science Department, King Abdullah II Faculty of Information Technology, University of Jordan, Amman, 11942, Jordan
7 School of Software, Northwestern Polytechnical University, Xi’an, 710072, China
8 Department of Engineering Technology, Fakulti Teknologi Dan Kejuruteraan Elektronik Dan Komputer (FTKEK), Universiti Teknikal Malaysia Melaka (UTeM), Melaka, 76100, Malaysia
9 Research Section, Faculty of Resilience, Rabdan Academy, Abu Dhabi, 22401, United Arab Emirates

* Corresponding Authors: Mian Muhammad Kamal. Email: ; Jamil Abedalrahim Jamil Alsayaydeh. Email:

Computer Modeling in Engineering & Sciences 2025, 144(3), 3053-3083. https://doi.org/10.32604/cmes.2025.067430

Received 03 May 2025; Accepted 15 July 2025; Issue published 30 September 2025

Abstract

Accurate detection of small objects is critically important in high-stakes applications such as military reconnaissance and emergency rescue. However, low resolution, occlusion, and background interference make small object detection a complex and demanding task. One effective approach to overcome these issues is the integration of multimodal image data to enhance detection capabilities. This paper proposes a novel small object detection method that utilizes three types of multimodal image combinations, such as Hyperspectral–Multispectral (HS-MS), Hyperspectral–Synthetic Aperture Radar (HS-SAR), and HS-SAR–Digital Surface Model (HS-SAR-DSM). The detection process is done by the proposed Jaccard Deep Q-Net (JDQN), which integrates the Jaccard similarity measure with a Deep Q-Network (DQN) using regression modeling. To produce the final output, a Deep Maxout Network (DMN) is employed to fuse the detection results obtained from each modality. The effectiveness of the proposed JDQN is validated using performance metrics, such as accuracy, Mean Squared Error (MSE), precision, and Root Mean Squared Error (RMSE). Experimental results demonstrate that the proposed JDQN method outperforms existing approaches, achieving the highest accuracy of 0.907, a precision of 0.904, the lowest normalized MSE of 0.279, and a normalized RMSE of 0.528.

---

Keywords

---