A Fuzzy Post-project Evaluation Approach for Security Video Surveillance System

Ming Liu, Zhi XuearXiv 2021 · OpenReview

Abstract

Video surveillance is an essential component of the public security system. The security video surveillance system is a powerful means to prevent violence and crimes, and it is closely coupled with the construction of smart cities. A post-project evaluation is an evaluation of a project's actions and outcomes after its completion. Post-project evaluation can scientifically and objectively evaluate the construction effectiveness of video surveillance system at a certain stage. Utilizing post-project evaluation can find out the causes of success or failure to make recommendations for the construction of a security video surveillance system in the next stage. Therefore, we propose a fuzzy post-project evaluation approach for the security video surveillance system in a real-world community. The fuzzy theory and fuzzy multi-level evaluation method are applied. The evaluation result demonstrates that the proposed approach is practically applicable to real-world security video surveillance systems.

Introduction

Building large-scale video surveillance systems is a complex undertaking involving hardware, networking, and software platforms. However, once these projects are finished, there is often no standardized way to measure if they actually met their goals or how they could be improved. Traditional evaluations can be overly subjective or fail to account for the "fuzziness" of human judgment—for example, the nuanced difference between "good" network security and "excellent" performance.

This paper addresses this gap by introducing a structured, multi-level Post-Project Evaluation (PPE) approach specifically tailored for surveillance systems in real-world communities. By combining a comprehensive index system with fuzzy set theory, the researchers provide a mathematical way to transform subjective expert opinions into a concrete performance rating, helping city planners and engineers improve future smart city infrastructure.

Methodology: The Fuzzy Multi-level Evaluation Framework

The core of the research is a Fuzzy Multi-level Evaluation Method. The process follows a rigorous hierarchical structure to ensure all aspects of the surveillance system are accounted for.

1. Index System Establishment

The authors define a two-tier hierarchy based on five principles: Integrity, Operability, Systematicness, Cost-effectiveness, and Guidance.

  • Primary Indexes: 9 broad categories such as Information Security, Infrastructure, and Public Experience.
  • Secondary Indexes: 31 specific metrics including Data Security, HD Video Construction Rate, and User Experience Surveys.
The hierarchical index system used for post-project evaluation, categorizing primary and secondary metrics.

2. Weight Determination and Expert Consultation

To quantify the importance of each metric, the team consulted 15 professional experts. These consultants assigned relative weights to each index. For instance, primary indexes like "Information Security" ($u_2$) and "Infrastructure" ($u_5$) were assigned normalized weights of 0.12, while "Information Resources" ($u_1$) was weighted at 0.1. This ensures that the final score reflects the priorities of industry professionals.

Consultant weights and normalized values for primary and secondary evaluation indexes.

3. Fuzzy Logic Processing

Because human labels are imprecise, the authors used fuzzy membership functions. Consultants evaluated the system against the 31 secondary indexes using a five-level scale: Excellent, Good, Average, Fair, and Poor. These qualitative labels were converted into evaluation matrices. Through matrix multiplication, these scores were propagated from the secondary level up to the primary level, resulting in a single final evaluation vector.

Case Study and Key Results

The approach was validated through a case study of a security video surveillance system in a real-world community. The input data consisted of feedback from 15 professional consultants and survey results from system users and the general public.

The final evaluation vector $B$ was calculated as $(0.79024, 0.15528, 0.05448, 0, 0)$. According to the principle of maximum membership, the highest value (0.79024) corresponds to the "Excellent" level. This high value provides a clear, mathematically backed "stamp of approval" for the project's implementation, demonstrating that the fuzzy approach can successfully yield a definitive qualitative conclusion from complex inputs.

Conclusion and Future Work

The study successfully demonstrates that quantifying qualitative expert opinions through fuzzy theory provides a robust framework for post-project evaluation. However, the authors acknowledge that the current reliance on manual consultant feedback can be slow.

Future research aims to incorporate Artificial Intelligence, knowledge engineering, and expert systems to automate the weighting process. This evolution would make the evaluation framework more scalable and universal, allowing for real-time performance monitoring and more efficient smart city planning.

Summary updated

Abstract

Video surveillance is an essential component of the public security system. The security video surveillance system is a powerful means to prevent violence and crimes, and it is closely coupled with the construction of smart cities. A post-project evaluation is an evaluation of a project's actions and outcomes after its completion. Post-project evaluation can scientifically and objectively evaluate the construction effectiveness of video surveillance system at a certain stage. Utilizing post-project evaluation can find out the causes of success or failure to make recommendations for the construction of a security video surveillance system in the next stage. Therefore, we propose a fuzzy post-project evaluation approach for the security video surveillance system in a real-world community. The fuzzy theory and fuzzy multi-level evaluation method are applied. The evaluation result demonstrates that the proposed approach is practically applicable to real-world security video surveillance systems.
BibTeX
@misc{liu2021fuzzy,
  author = {Ming Liu and Zhi Xue},
  title = {{A Fuzzy Post-project Evaluation Approach for Security Video Surveillance System}},
  year = {2021},
  eprint = {2106.15316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.15316},
}
Figure