Surya Prakash Guna Sekhar, Karthik Sai Pothireddy

DOI: https://doi.org/10.5281/zenodo.22144615

The growth of Body-Worn Cameras (BWCs) and CCTV systems in law enforcement has generated unprecedented volumes of surveillance data, presenting new opportunities for enhancing transparency, accountability, and public trust. However, manual review of this footage remains slow, inconsistent, and often significantly delayed, creating substantial barriers to timely oversight. This study addresses this gap by designing an AI-driven surveillance auditing system capable of detecting unethical practices in policing — including acts of aggression, racial profiling, and procedural violations — to strengthen transparency, accountability, and public trust. Multimodal AI techniques are employed, integrating computer vision and Natural Language Processing (NLP). Computer vision detects aggression, facial expressions, and nonconforming gestures from video feeds, while NLP models analyse spoken language for hostile, biased, or inappropriate tones. These modalities are fused in a scoring engine to flag questionable behaviour and generate structured compliance reports, while a secure dashboard allows supervisors and external oversight bodies to visualise audit results in real-time or batch mode. The research targets a scalable, precise, and ethically aligned AI system for real-world policing. All datasets will be anonymised, and the system will be audited for fairness across race, gender, and contextual variables. Expected outcomes include a working prototype, peer-reviewed contributions to AI ethics in law enforcement, and a deployment-ready implementation framework. By automating surveillance audits, this research aims to accelerate accountability processes, standardise behavioural assessments, and strengthen public trust in policing practices.

Body-Worn Cameras (BWC), Artificial Intelligence (AI), Surveillance Auditing, Computer Vision, Natural Language Processing (NLP), Police Accountability, Ethical AI, Multimodal Analysis.

This work addresses a critical and timely challenge: the need for accountable, transparent, and fair application of AI in law enforcement surveillance. A novel system has been proposed that audits bodycam and CCTV footage using multimodal AI to identify suspicious encounters and gauge compliance with ethical policing standards. The innovation spans both the technical implementation — computer vision, natural language processing, and audio analytics — and the commitment to bias mitigation, interpretability, and usability. The system has the potential to contribute toward greater transparency in policing, reduce the harms of unreviewed surveillance, and provide oversight bodies with more consistent, objective methods of accountability. The project advances responsible AI governance by providing an operational framework for ethical implementation in high-stakes situations.

[1]  C. Lum et al., “Body-worn cameras’ effects on police officers and citizen behavior: A systematic review,” Campbell Systematic Reviews, vol. 16, no. 3, Sep. 2020.
[2]  A. Taofeek, “Ethical Considerations in Using Artificial Intelligence for AML Surveillance,” ResearchGate, May 2025.
[3]  N. Guha et al., “AI Regulation Has Its Own Alignment Problem,” 2024. Available: https://dho.stanford.edu/wp-content/uploads/AI_Regulation.pdf
[4]  V. Shevchenko et al., “Using AI to Counter Criminal Offences Against the Will, Honour, and Dignity of a Person,” J. Theoretical and Applied Information Technology, vol. 103, no. 6, 2025.
[5]  A. Johnson, E. Egan, and J. Londono, “Police Tech: Exploring the Opportunities and Fact-Checking the Criticisms,” itif.org, Jan. 2023.
[6]  S. Hyland, “Body-Worn Cameras in Law Enforcement Agencies, 2016,” Bureau of Justice Statistics, 2022.
[7]  NIJ, “Research on Body-Worn Cameras and Law Enforcement,” National Institute of Justice, 2022.
[8]  P. P. Thulasiram, “Explainable Artificial Intelligence (XAI): Enhancing Transparency and Trust in ML Models,” Philpapers.org, 2025.
[9]  C. Rodriguez, “Improving Public Safety Through Better Accountability and Prevention,” Center for American Progress, May 2024.
[10] M. Allen, “Changing Policing: The Impact of Body-Worn Cameras on Law Enforcement Officers,” 2021.
[11] Deloitte, “Surveillance and Predictive Policing Through AI,” Deloitte, 2024.
[12] L. A. Saleem and G. Mamidisetti, “Violence Detection in Videos Using Low-Complex CNN for Surveillance,” J. Wireless Mobile Networks, 2024.
[13] P. Negre et al., “Literature Review of Deep-Learning-Based Detection of Violence in Video,” Sensors, vol. 24, no. 12, 2024.
[14] J. Joseph, “Predicting crime or perpetuating bias? The AI dilemma,” AI & Society, Aug. 2024.
[15] N.-J. Akpinar, M. De-Arteaga, and A. Chouldechova, “The effect of differential victim crime reporting on predictive policing systems,” Proc. ACM FAccT, 2021.
[16] G. B. Mensah, “Artificial intelligence and ethics: A comprehensive review of bias mitigation, transparency, and accountability,” ResearchGate, Nov. 2023.
[17] A. Chourasiya et al., “A Review of Sentiment Analysis and Emotion Detection from Text using Different Models,” IJEASM, vol. 6, no. 1, Jan. 2025.
[18] Z. Chen et al., “Evolution and Prospects of Foundation Models: From LLMs to Large Multimodal Models,” Computers, Materials & Continua, vol. 80, no. 2, 2024.
[19] M. Tran and M. Soleymani, “A Pre-trained Audio-Visual Transformer for Emotion Recognition,” arXiv:2201.09165, 2022.
[20] Y.-Y. Wang et al., “Multimodal transformer augmented fusion for speech emotion recognition,” Frontiers in Neurorobotics, vol. 17, May 2023.
[21] A. Srbinovska et al., “Towards AI-Driven Policing: Knowledge Discovery from Police Body-Worn Camera Footage,” arXiv, 2024.
[22] C. Archbold, “Police Accountability in the USA: Gaining Traction or Spinning Wheels?,” Policing: A J. Policy and Practice, vol. 15, no. 3, Sep. 2021.
[23] B. Raffish, “Civilian Oversight as a Police Accountability Mechanism,” Lawfare, 2021.
[24] A. Davies and G. Krame, “Integrating body-worn cameras, drones, and AI: A framework for enhancing police readiness and response,” Policing, vol. 17, 2023.
[25] P. Thakore and D. Johari, “An Interface for Communication for the Deaf Using Hand Gesture Recognition through CV and NLP,” J. Image Processing & Pattern Recognition Progress, vol. 9, no. 3, 2022.
[26] X. Chen, X. Wang, and Y. Qu, “Constructing Ethical AI Based on the ‘Human-in-the-Loop’ System,” Systems, vol. 11, no. 11, p. 548, Nov. 2023.
[27] M. Khan and Y. Hossni, “A comparative analysis of LSTM models aided with attention and squeeze and excitation blocks for activity recognition,” Scientific Reports, vol. 15, no. 1, Jan. 2025.
[28] S. Barde and V. Kaimal, “Speech recognition technique for identification of raga,” Elsevier eBooks, pp. 101–117, Jan. 2020.
[29] R. Raj and A. Kos, “An Extensive Study of Convolutional Neural Networks: Applications in Computer Vision,” Sensors, vol. 25, no. 4, pp. 1033–1033, Feb. 2025.
[30] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997.
[31] Y.-Y. Chen et al., “Distributed Real-Time Object Detection Based on Edge-Cloud Collaboration for Smart Video Surveillance,” IEEE Access, vol. 10, pp. 93745–93759, 2022.
[32] A. Pavlenko, “Flask vs React: Understanding the Differences,” Medium – Toward Dev, Mar. 2023.
[33] B. Memarian and T. Doleck, “Fairness, Accountability, Transparency, and Ethics (FATE) in AI and higher education: A systematic review,” Computers and Education: Artificial Intelligence, vol. 5, p. 100152, Jan. 2023.

Surya Prakash Guna Sekhar, Karthik Sai Pothireddy (2026). AI-Driven Surveillance Auditing to Police Ethically. International Journal of Computer Techniques, 13(4), 292–298. ISSN: 2394-2231. DOI: https://doi.org/10.5281/zenodo.22144615