Intelligent Video Recording Optimization using Activity Detection for Surveillance Systems

TL;DR

This paper proposes an optimized video recording solution focused on activity detection that combines motion detection via frame subtraction with object detection using YOLOv9 using a hybrid method that combines motion detection via frame subtraction with object detection using YOLOv9.

Abstract

Surveillance systems often struggle with managing vast amounts of footage, much of which is irrelevant, leading to inefficient storage and challenges in event retrieval. This paper addresses these issues by proposing an optimized video recording solution focused on activity detection. The proposed approach utilizes a hybrid method that combines motion detection via frame subtraction with object detection using YOLOv9. This strategy specifically targets the recording of scenes involving human or car activity, thereby reducing unnecessary footage and optimizing storage usage. The developed model demonstrates superior performance, achieving precision metrics of 0.855 for car detection and 0.884 for person detection, and reducing the storage requirements by two-thirds compared to traditional surveillance systems that rely solely on motion detection. This significant reduction in storage highlights the effectiveness of the proposed approach in enhancing surveillance system efficiency. Nonetheless, some limitations persist, particularly the occurrence of false positives and false negatives in adverse weather conditions, such as strong winds.

Figures (6)

• Figure 1: flowchart explaining the global architecture of the proposed system
• Figure 2: Samples from the dataset used to train YOLO model
• Figure 3: Confusion matrix for the proposed video recording optimization method applied to surveillance footage
• Figure 4: Training and Validation Performance Metrics of the 7th YOLOv9 based Model.
• Figure 5: Screenshot of the Hikvision System with Motion Detection Enabled