The continuous progress of society has put forward higher requirements for the performance of current video surveillance, and object detection is an essential research content in the video surveillance process. Traditional object detection methods have disadvantages such as poor generalization ability, large limitations, and weak adaptability, which cannot meet the current social demand for object detection in video surveillance. Therefore, to promote the effectiveness of urban video surveillance, an Improved Fast Regional Convolutional Neural Network (IFast R-CNN) model is constructed. This model has been introduced with optimization strategies such as the K-Means Clustering Algorithm (K-means), optimized Non-Maximum Suppression (NMS) algorithm, weighted penalty method, and Region of Interest Align (RoIAlign) layer to raise the accuracy of object detection in video surveillance. This study conducts relevant research to assess the effectiveness of the proposed model. This model has better convergence performance compared to the other two comparative models, and it tends to stabilize after 56 iterations. The Area Under the Curve (AUC) of the model can arrive at 0.989. After verifying the effectiveness of the optimization strategy, it is found that the mean accuracy of the optimized model can reach 96.13%. Therefore, the model constructed by this research institute has good object detection performance and great potential for application in video surveillance processes.

[1] Dhillon A. and Verma G., “Convolutional Neural Network: A Review of Models, Methodologies and Applications to Object Detection,” Progress in Artificial Intelligence, vol. 9, no. 2, pp. 85-112, 2020. https://doi.org/10.1007/s13748-019- 00203-0

[2] Elhoseny M., “Multi-Object Detection and Tracking (MODT) Machine Learning Model for Real-Time Video Surveillance Systems,” Circuits, Systems, and Signal Processing, vol. 39, pp. 611- 630, 2020. https://doi.org/10.1007/s00034-019- 01234-7

[3] Giveki D., “Robust Moving Object Detection Based on Fusing Atanassov’s Intuitionistic 3D Fuzzy Histon Roughness Index and Texture Features,” International Journal of Approximate Reasoning, vol. 135, pp. 1-20, 2021. https://doi.org/10.1016/j.ijar.2021.04.007

[4] Junos M., Mohd Khairuddin A., Thannirmalai S., and Dahari M., “An Optimized YOLO-Based Object Detection Model for Crop Harvesting System,” IET Image Processing, vol. 15, pp. 2112-2125, 2021. https://doi.org/10.1049/ipr2.12181

[5] Kim S., Park S., Na B., and Yoon S., “Spiking- Yolo: Spiking Neural Network for Energy- Efficient Object Detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, New York, vol. 34, no. 7, pp. 11270-11277, 2020. https://doi.org/10.1609/aaai.v34i07.6787

[6] Li X., Jiang Y., Liu C., Liu S., and et al., “Playing Against Deep-Neural-Network-Based Object Detectors: A Novel Bidirectional Adversarial Attack Approach,” IEEE Transactions on Artificial Intelligence, vol. 3, no. 1, pp. 20-28, 2022. https://doi.org/10.1109/TAI.2021.3107807

[7] Nasir V. and Sassani F., “A Review on Deep Learning in Machining and Tool Monitoring: Methods, Opportunities, and Challenges,” The International Journal of Advanced Manufacturing Technology, vol. 115, pp. 2683- 2709, 2021. https://doi.org/10.1007/s00170-021- 07325-7

[8] Natarajan S. and Periyasamy K., “A Silicosis- Focused Hybrid Architecture Leveraging Enhanced Segmentation and Feature Based Classification,” The International Arab Journal of Information Technology, vol. 23, no. 2, pp. 283-296, 2026. DOI: 10.34028/iajit/23/2/09

[9] Pareek P. and Thakkar A., “A Survey on Video- Based Human Action Recognition: Recent Updates, Datasets, Challenges, and Applications,” Artificial Intelligence Review, vol. 54, pp. 2259-2322, 2020. https://doi.org/10.1007/s10462-020- 09904-8

[10] Qin H., Wu Y., Dong F., and Sun S., “Dense Sampling and Detail Enhancement Network: Improved Small Object Detection Based on Dense Sampling and Detail Enhancement,” IET Computer Vision, vol. 16, no. 4, pp. 307-316, 2022. DOI: 10.1049/cvi2.12089

[11] Qin L., Shi Y., He Y., Zhang J., and et al., “ID- YOLO: Real-Time Salient Object Detection Based on the Driver’s Fixation Region,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 9, pp. 15898-15908, 2022. https://doi.org/10.1109/TITS.2022.3146271

[12] Sharma R. and Sungheetha A., “An Efficient Dimension Reduction Based Fusion of CNN and SVM Model for Detection of Abnormal Incident in Video Surveillance,” Journal of Soft Computing Paradigm, vol. 3, no. 2, pp. 55-69, 2021. https://doi.org/10.36548/JSCP.2021.2.001

[13] Unver M., Olgun M., and Turkarslan E., “Cosine and Cotangent Similarity Measures Based on Choquet Integral for Spherical Fuzzy Sets and Applications to Pattern Recognition,” Journal of Computational and Cognitive Engineering, vol. 1, no. 1, pp. 21-31, 2022. https://doi.org/10.47852/bonviewJCCE2022010 105

[14] Wan S., Xu X., Wang T., and Gu Z., “An Intelligent Video Analysis Method for Abnormal Event Detection in Intelligent Transportation Systems,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 7, pp. 4487- 4495, 2021. https://doi.org/10.1109/TITS.2020.3017505

[15] Wang Z., Xu P., Liu B, Cao Y., and et al., “Hyperspectral Imaging for Underwater Object Detection,” Sensor Review, vol. 41, no. 2, pp. 176-191, 2021. DOI:10.1108/SR-07-2020-0165

[16] Wardana A., Hu S., Shimasaki K., and Ishii I., “Development of a Multi-User Remote Video Monitoring System Using a Single Mirror-Drive Pan-Tilt Mechanism,” Journal of Robotics and Mechatronics, vol. 34, no. 5, pp. 1122-1132, 2022. https://doi.org/10.20965/jrm.2022.p1122

[17] Wei J., Wang S., and Huang Q., “F³Net: Fusion, Feedback and Focus for Salient Object Detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, New York, pp. 12321- 12328, 2020. DOI:10.1609/aaai.v34i07.6916

[18] Wu X., Sahoo D., and Steven C., “Recent Advances in Deep Learning for Object Detection,” Neurocomputing, vol. 396, pp. 39-64, 2020. https://doi.org/10.1016/j.neucom.2020.01.085

[19] Yang M., “Research on Vehicle Automatic Driving Target Perception Technology Based on Improved MSRPN Algorithm,” Journal of Computational and Cognitive Engineering, vol. 1, no. 3, pp. 147-151, 2021. https://doi.org/10.47852/bonviewJCCE20514

[20] Yang Y. and Song X., “Research on Face Intelligent Perception Technology Integrating Deep Learning under Different Illumination Intensities,” Journal of Computational and Cognitive Engineering, vol. 1, no. 1, pp. 32-36, 2022. https://doi.org/10.47852/bonviewJCCE19919

[21] Yu L., Nazir B., and Wang Y., “Intelligent Power Monitoring of Building Equipment Based on Internet of Things Technology,” Computer Communications, vol. 157, pp. 76-84, 2020. https://doi.org/10.1016/j.comcom.2020.04.016

[22] Zhang J., Shi Y., Zhang Q., Liu C., and et al., “Attention Guided Contextual Feature Fusion Network for Salient Object Detection,” Image and Vision Computing, vol. 117, pp. 104337, 2022. https://doi.org/10.1016/j.imavis.2021.104337

[23] Zhang L., “Enterprise Employee Work Behavior Recognition Method Based on Faster Region- Convolutional Neural Network,” The International Arab Journal of Information Technology, vol. 22, no. 2, pp. 291-302, 2025. https://doi.org/10.34028/iajit/22/2/7

[24] Zhang X. and Zhi Y., “Design of Environment Monitoring System for Intelligent Breeding Base Based on Internet of Things,” Open Access Library Journal, vol. 8, no. 10, pp. 1-9, 2021. DOI:10.4236/oalib.1108044

[25] Zhang X., Liu Y., Huo C., Xu N., and et al., “PSNet: Perspective-Sensitive Convolutional Network for Object Detection,” Neurocomputing, vol. 468, pp. 384-395, 2022. https://doi.org/10.1016/j.neucom.2021.10.068

[26] Zhang Y., Song C., and Zhang D., “Deep Learning-Based Object Detection Improvement for Tomato Disease,” IEEE Access, vol. 8, pp. 56607-56614, 2020. https://doi.org/10.1109/ACCESS.2020.2982456