Efficient Object Detection and Classification Approach Using an Enhanced Moving Object Detection Algorithm in Motion Videos
DOI:
https://doi.org/10.51983/ijiss-2024.14.1.3895Keywords:
Object Detection, Video Processing, Convolution Neural NetworkAbstract
Object detection and classification have become prominent research topics in computer vision due to their applications in areas such as visual tracking. Despite advancements, vision-based methods for detecting smaller targets and densely packed objects with high accuracy in complex dynamic environments still encounter challenges. This paper introduces a novel and enhanced approach for hyperbolic shadow detection and object classification based on the Enhanced Moving Object Detection (EMOD) algorithm and an improved manta ray-based convolutional neural network optimized for search. In the preprocessing phase, the video data transforms into a sequence of frames, with polynomial adaptive antialiasing applied to maintain frame size and reduce noise. Additionally, an enhanced boundary area preservation algorithm improves the contrast of noise-free edited image sequences. To achieve high-precision detection of smaller objects, the Grib profile of each detected object is also tracked. Finally, a convolutional neural network method employing an enhanced Manta search optimization is deployed for target detection and classification. Comparative experiments conducted across diverse datasets and benchmark methods demonstrate significantly improved accuracy and expanded capabilities in detection and classification.
References
Ahmed, I., Din, S., Jeon, G., Piccialli, F., & Fortino, G. (2021). Towards collaborative robotics in top view surveillance: A framework for multiple object tracking by detection using deep learning. IEEE Chinese Association of Automation Journal of Automatica Sinica, 8(7), 1253-1270. doi: 10.1109/JAS.2020.1003 453.
Attamimi, M., Nagai, T., & Purwanto, D. (2018). Object detection based on particle filter and integration of multiple features. Procedia Computer Science, 144, 214-218. doi:10.1016/j.procs.2018.10.521.
Bhuvaneswari, R., & Subban, R. (2018). Novel object detection and recognition system based on points of interest selection and SVM classification. Cognitive Systems Research, 58(1), 1-18. doi: 10.1016/j.cogsys.2018.09.022.
Hou, B., Li, J., Zhang, X., Wang, S., & Jiao, L. (2019). Object detection and tracking based on convolutional neural networks for high-resolution optical remote sensing video. In IEEE Int. Geoscience and Remote Sensing Sym., Yokohama, Japan, 5433-5436. doi: 10.1109/IGARSS.2019.8898173.
Kanimozhi, S., Gayathri, G., & Mala, T. (2019). Multiple real-time object identification using single-shot multi-box detection. In Second Int. Conf. on Computational Intelligence in Data Science, Chennai, India, 1-5. doi: 10.1109/ICCIDS.2019.8862041.
Kim, J. U., & Ro, Y. M. (2019). Attentive layer separation for object classification and object localization in object detection. In IEEE Int. Conf. on Image Processing (ICIP), Taipei, Taiwan, 3995-3999. doi: 10.1109/ICIP.2019.8803439.
Kim, J., Koh, J., & Choi, J. W. (2020). Video object detection using motion context and feature aggregation. In Int. Conf. on Information and Communication Technology Convergence (ICTC), Jeju, Korea (South), 269-272. doi: 10.1109/ICTC49870.2020.9289386.
Kousik, N. V., Natarajan, Y., Raja, A. R., Kallam, S., Patan, R., et al. (2020). Improved salient object detection using hybrid convolution recurrent neural network. Expert Systems with Applications, 166(3), 114064. doi: 10.1016/j.eswa.2020.114064.
Kumar, A., & Srivastava, S. (2020). Object detection system based on convolution neural networks using single-shot multi-box detector. Procedia Computer Science, 171(1), 2610-2617. doi: 10.1016/j.procs. 2020.04.283.
Lee, H., Eum, S., & Kwon, H. (2019). ME R-CNN multi-expert R-CNN for object detection. IEEE Transactions on Image Processing, 29, 1030-1044. doi: 10.1109/TIP.2019.2938879.
Lu, Z., Lu, J., Ge, Q., & Zhan, T. (2019). Multi-object detection method based on YOLO and resnet hybrid networks. In 4th Int. Conf. on Advanced Robotics and Mechatronics (ICARM), Toyonaka, Japan, 827-832. doi: 10.1109/ICARM.2019.8833671.
Pang, Y., & Cao, J. (2019). Deep learning in object detection. In Deep Learning in Object Detection and Recognition, 1st ed. Singapore: Springer, 19-57 [Online]. doi: 10.1007/978-981-10-5152-4_2.
Rani, R., Singh, A. P., & Kumar, R. (2019). Impact of reduction in descriptor size on object detection and classification. Multimedia Tools and Applications, 78(7), 8965-8979. doi: 10.1007/s11042-018-6911-7.
Rao, N. V., Prasad, D. V., & Sugumaran, M. (2021). Real-time video object detection and classification using hybrid texture feature extraction. International Journal of Computers and Applications, 43(2), 119-126. doi: 10.1080/1206212X.2018.1525929
Ray, K. S., & Chakraborty, S. (2019). Object detection by spatio-temporal analysis and tracking of the detected objects in a video with variable background. Journal of Visual Communication and Image Representation, 58, 662-674. doi: 10.1016/j.jvcir.2018.
Yi, S., Ma, H., Li, X., & Wang, Y. (2020). WSODPB weakly supervised object detection with PCS net and box regression module. Neurocomputing, 418(12), 232-240. doi: 10.1016/j.neucom.2020. 08.028.
Yin, Y., Li, H., & Fu, W. (2020). Faster-YOLO an accurate and faster object detection method. Digital Signal Processing, 102(6), 1-11. doi:10.1016/j.dsp.2020.102756.
Yu, Q., Wang, B., & Su, Y. (2021). Object detection-tracking algorithm for unmanned surface vehicles based on a radar-photoelectric system. IEEE Access, 9, 57529-57541. doi: 10.1109/ACCESS.2021.3072897.
Yuan, J., Xiong, H. C., Xiao, Y., Guan, W., Wang, M., et al., (2019). Gated CNN integrating multi-scale feature layers for object detection. Pattern Recognition, 105(6), 1-33. doi: 10.1016/j.patcog.2019. 107131.
Zhu, Y., Wu, J. S., Liu, X., Zeng, G., Sun, J., et al., (2020). Photon-limited non-imaging object detection and classification based on single-pixel imaging system. Applied Physics B, 126(1), 1-8. doi: 10.1007/s00340-019-7373-y.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 The Research Publication
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
