An Improved Spectral Residual Algorithm for Sparrow Pest Detection in Rice Field CCTV Video

Raja Ayu Mahessya; Yuhandri Yuhandri; Rini Sovia

doi:10.29207/resti.v10i4.7775

Authors

Raja Ayu Mahessya Universitas Putra Indonesia YPTK Padang
Yuhandri Universitas Putra Indonesia YPTK Padang
Rini Sovia Universitas Putra Indonesia YPTK Padang

DOI:

https://doi.org/10.29207/resti.v10i4.7775

Keywords:

accuracy, CCTV Video, digital image processing, pest detection, spectral residual algorithm

Abstract

Agricultural pest surveillance in open field environments presents a persistent challenge for food security, particularly when early detection is limited by the inadequacy of traditional monitoring methods. Existing Spectral Residual (SR) algorithms, while capable of saliency-based object detection, exhibit notable limitations in adapting to dynamic agricultural conditions resulting in degraded segmentation quality and elevated false-positive rates. This study proposes an improved Spectral Residual algorithm that independently processes Red, Green, and Blue (RGB) channels via Fast Fourier Transform (FFT), preserving richer spectral information that is otherwise lost in conventional grayscale-based approaches. The proposed pipeline integrates spatial saliency maps with temporal motion cues extracted through frame-difference analysis, suppressing static background noise while reinforcing responses in regions exhibiting genuine movement. Adaptive binarization and Support Vector Machine (SVM) classification are further incorporated to strengthen object segmentation robustness across diverse lighting and background conditions. The model was evaluated on 136 frames extracted from 2MP Hikvision CCTV footage installed at rice field sites, benchmarked against the classical Spectral Residual baseline using accuracy, precision, recall, and F1-score. The proposed method achieved an accuracy of 98.15%, precision of 91.67%, recall of 98.98%, and F1-score of 95.18% — representing substantial improvements over the baseline (74.00%, 70.00%, 65.00%, and 69.00%, respectively). These results demonstrate that multi-channel spectral processing combined with motion-aware saliency yields a robust and computationally efficient saliency framework whose low algorithmic complexity makes it a strong candidate for real-time sparrow pest detection in CCTV-based agricultural monitoring systems.

Downloads

Download data is not yet available.

References

[1] E. F. Duque-Vazquez, R. E. Sanchez-Yanez, N. Saldaña-Robles, M. F. León-Galván, and J. Cepeda-Negrete, “HeLa cell segmentation using digital image processing.,” Heliyon, vol. 10, no. 5, p. e26520, Mar. 2024, doi: 10.1016/j.heliyon.2024.e26520.

[2] Y. Wang et al., “WBNet: Weakly-supervised salient object detection via scribble and pseudo-background priors,” Pattern Recogn., vol. 154, no. C, 2024, doi: 10.1016/j.patcog.2024.110579.

[3] J. Yu, S. Chen, N. Liu, F. Zhai, and Q. Pan, “Cascaded Aggregation Convolution Network for Salient Grain Pests Detection,” Insects, vol. 15, no. 7, 2024, doi: 10.3390/insects15070557.

[4] I. Ullah et al., “CMGNet: Context-aware middle-layer guidance network for salient object detection,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 1, p. 101838, 2024, doi: 10.1016/j.jksuci.2023.101838.

[5] C. Zhang, K. Dong, K. Aihara, L. Chen, and S. Zhang, “STAMarker: determining spatial domain-specific variable genes with saliency maps in deep learning,” Nucleic Acids Res., vol. 51, no. 20, pp. e103–e103, Nov. 2023, doi: 10.1093/nar/gkad801.

[6] Y. Zhang, Z. Zhang, P. Zhang, and M. Xu, “Salient object detection for RGBD video via spatial interaction and depth-based boundary refinement,” Complex & Intelligent Systems, vol. 9, no. 6, pp. 6343–6358, 2023, doi: 10.1007/s40747-023-01072-w.

[7] E. C. Tetila et al., “YOLO performance analysis for real-time detection of soybean pests,” Smart Agricultural Technology, vol. 7, p. 100405, 2024, doi: 10.1016/j.atech.2024.100405.

[8] J. A. Figueroa-Alvarez et al., “Insectivorous birds and potential pest control services: An occupancy study of functional groups in a coffee landscape in Oaxaca, Mexico,” Perspect. Ecol. Conserv., vol. 22, no. 4, pp. 331–341, 2024, doi: 10.1016/j.pecon.2024.09.002.

[9] A. Raza, M. R. Al Nasar, E. S. Hanandeh, R. A. Zitar, A. Y. Nasereddin, and L. Abualigah, “A Novel Methodology for Human Kinematics Motion Detection Based on Smartphones Sensor Data Using Artificial Intelligence,” 2023. doi: 10.3390/technologies11020055.

[10] V. C. Warad and R. Fatima, “Video saliency-recognition by applying custom spatio temporal fusion technique,” IAES International Journal of Artificial Intelligence, vol. 13, no. 1, pp. 82–91, 2024, doi: 10.11591/ijai.v13.i1.pp82-91.

[11] J. Hentati-Sundberg et al., “Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research,” Remote Sens. Ecol. Conserv., vol. 9, no. 4, pp. 568–581, Aug. 2023, doi: 10.1002/rse2.329.

[12] A. A. Gharahbagh, V. Hajihashemi, M. C. Ferreira, J. J. M. Machado, and J. M. R. S. Tavares, “Hybrid time-spatial video saliency detection method to enhance human action recognition systems,” Multimed. Tools Appl., vol. 83, no. 30, pp. 74053–74073, 2024, doi: 10.1007/s11042-024-18126-x.

[13] Y. Wen, Y. Wang, H. Wang, W. Shi, and W. Cao, “Co-salient object detection with iterative purification and predictive optimization,” Virtual Reality & Intelligent Hardware, vol. 6, no. 5, pp. 396–407, 2024, doi: 10.1016/j.vrih.2024.06.002.

[14] Z. Berger Haladova, M. Zrubec, and Z. Cernekova, “A method for estimating roadway billboard salience,” in ACM Symposium on Applied Perception 2024, in SAP ’24. New York, NY, USA: Association for Computing Machinery, 2024. doi: 10.1145/3675231.3675238.

[15] F. Zhao, R. Wei, Y. Chao, S. Shao, and C. Jing, “Infrared Bird Target Detection Based on Temporal Variation Filtering and a Gaussian Heat-Map Perception Network,” 2022. doi: 10.3390/app12115679.

[16] C. Gwon and S. C. Howell, “ODSmoothGrad: Generating Saliency Maps for Object Detectors,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, pp. 3686–3690. doi: 10.1109/CVPRW59228.2023.00376.

[17] S. Andika Maulana, S. Husna Batubara, Y. Permata Putri Pasaribu, H. Syahputra, and F. Ramadhani, “Deteksi Burung Menggunakan Convolutional Neural Network (Cnn) Dengan Model Arsitektur Mobilenetv2,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 8, no. 4, pp. 6108–6114, 2024, doi: 10.36040/jati.v8i4.10126.

[18] M. Olague, G. Olague, R. Pineda, and G. Ibarra-Vazquez, “Salient object detection dataset with adversarial attacks for genetic programming and neural networks,” Data Brief, vol. 57, p. 111043, 2024, doi: 10.1016/j.dib.2024.111043.

[19] Y. Zhu and T. H. Falk, “Spectral–temporal saliency masks and modulation tensorgrams for generalizable COVID-19 detection,” Comput. Speech Lang., vol. 86, p. 101620, 2024, doi: 10.1016/j.csl.2024.101620.

[20] A.-C. Woerl, J. Disselhoff, and M. Wand, “Initialization Noise in Image Gradients and Saliency Maps,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 1766–1775. doi: 10.1109/CVPR52729.2023.00176.

[21] D. A. Septian and A. Suhendar, “Klasifikasi Penyakit pada Daun Kentang Menggunakan Pengolahan Citra dengan Metode Convolutional Neural Network (CNN).,” Jurnal teknologi dan sains, pp. 1017–1025, 2024. doi: 10.51401/jinteks.v6i4.4880

[22] Z.-W. Sun et al., “FBD-SV-2024: Flying Bird Object Detection Dataset in Surveillance Video,” Sci. Data, vol. 12, no. 1, p. 530, 2025, doi: 10.1038/s41597-025-04872-6.

[23] N.-T. Thu, H. N. Tran, Md. D. Hossain, and E.-N. Huh, “LightSOD: Towards lightweight and efficient network for salient object detection,” Computer Vision and Image Understanding, vol. 249, p. 104148, 2024, doi: 10.1016/j.cviu.2024.104148.

[24] Y. A. D. Djilali, K. McGuinness, and N. O’Connor, “Learning Saliency From Fixations,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 382–392. doi: 10.1109/WACV57701.2024.00045.

[25] Z. Li, X. Pang, Y. Jiang, and Y. Wang, “RealFuVSR: Feature Enhanced Real-World Video Super-Resolution,” Virtual Reality & Intelligent Hardware, vol. 5, no. 6, pp. 523–537, 2023, doi: 10.1016/j.vrih.2023.06.006.

[26] P. Liu, T. Xu, G. Shi, J. Xu, H. Chen, and J. Li, “Spectrum-Oriented Point-Supervised Saliency Detector for Hyperspectral Images,” IEEE Trans. Instrum. Meas., vol. 74, no. 8, pp. 1–15, 2025, doi: 10.1109/TIM.2025.3527488.

[27] L. Li et al., “An Effective Infrared and Visible Image Fusion Approach via Rolling Guidance Filtering and Gradient Saliency Map,” 2023. doi: 10.3390/rs15102486.

[28] K. Szczepankiewicz et al., “Ground truth based comparison of saliency maps algorithms,” Sci. Rep., vol. 13, no. 1, p. 16887, 2023, doi: 10.1038/s41598-023-42946-w.

[29] G. Cartella, V. Cuculo, M. Cornia, M. Papasidero, F. Ruozzi, and R. Cucchiara, “Pixels of Faith: Exploiting Visual Saliency to Detect Religious Image Manipulation,” in Computer Vision – ECCV 2024 Workshops: Milan, Italy, September 29–October 4, 2024, Proceedings, Part VI, Berlin, Heidelberg: Springer-Verlag, 2024, pp. 229–245. doi: 10.1007/978-3-031-91572-7_14.

[30] N. Tomar, S. Chandel, and G. Bhatnagar, “A visual attention-based algorithm for brain tumor detection using an on-center saliency map and a superpixel-based framework,” Healthcare Analytics, vol. 5, p. 100323, 2024, doi: 10.1016/j.health.2024.100323.

[31] A. Moskalenko et al., “AIM 2024 Challenge on Video Saliency Prediction: Methods and Results,” Lecture Notes in Computer Science, vol. 15632 LNCS, pp. 178–194, 2025, doi: 10.1007/978-3-031-91856-8_11.

[32] H. Lee, J. Kim, and J. H. Park, “Power System Transient Stability Prediction Using Convolution Neural Network and Saliency map,” in 2023 IEEE PES Innovative Smart Grid Technologies - Asia (ISGT Asia), 2023, pp. 1–5. doi: 10.1109/ISGTAsia54891.2023.10372670.

[33] M. N. Darpito, K. Firdausy, and A. Fadlil, “Comparative Evaluation of Thresholding Methods for Optimized Digital Document Parsing Accuracy,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 10, no. 2 SE-Computer Vision and Pattern Recognition, Apr. 2026, doi: 10.29207/resti.v10i2.6982.

[34] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Trans. Syst. Man Cybern., vol. 9, no. 1, pp. 62–66, 1979, doi: 10.1109/TSMC.1979.4310076.

[35] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/BF00994018.

[36] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, 2017, doi: 10.1145/3065386.

[37] J. Snoek, H. Larochelle, and R. P. Adams, “Practical Bayesian optimization of machine learning algorithms,” Adv. Neural Inf. Process. Syst., vol. 4, pp. 2951–2959, 2012. doi: 10.48550/arXiv.1206.2944.

.