Punch-Seeded Face Enrollment and Multi-Camera Re-Identification in Legacy Indian CCTV Deployments: A Dual-Site Pilot Study
Fuente:
Zenodo
Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901147038515200 |
|---|---|
| author | Aggarwal, Vibhav |
| author_facet | Aggarwal, Vibhav |
| contents | <p>Indian small and medium manufacturers operate a vast installed base of legacy CCTV infrastructure — Hikvision IP cameras, analog DVRs, and consumer-grade NVRs — that is typically used only for passive recording. The gap between “cameras that exist” and “cameras that contribute to operational intelligence” is substantial and rarely addressed in the face-recognition literature, which assumes greenfield IP deployments and large-scale labeled datasets.</p><p>We describe a two-site pilot that retrofits face recognition and multi-camera worker re-identification onto unmodified legacy infrastructure at two distinct sites in Haryana, India: (i) a 22-camera Hikvision IP deployment at a gasket manufacturing facility (Phase 2, 3 cameras online, 3 workers enrolled), and (ii) a 16-channel analog DVR deployment at an Ayurvedic-pharmaceutical company office (12 cameras live, production face-recognition operational via CompreFace + Double Take + Frigate).</p><p>The technical contribution is <strong>punch-seeded enrollment</strong>: a single timestamped biometric-attendance snapshot, already captured by the plant's turnstile, is used as the sole enrollment seed from which the system propagates worker identity labels across downstream camera footage via density-based clustering (DBSCAN) with a temporal window. This reduces annotation effort from “tens of labeled frames per worker” to “one automatically-captured punch snapshot per worker”.</p><p>The paper reports only aggregate deployment metrics — no face images, no embeddings, no worker identifiers — consistent with India's Digital Personal Data Protection Act 2023 requirements for biometric data. We also document legacy-integration engineering gotchas that consumed a meaningful fraction of deployment effort: H.265 hardware decode failures on GTX 970M (compute capability 5.2), OpenVINO failing silently and reverting to CPU TFLite, digest-authenticated ISAPI calls on Hikvision cameras, and DVR SSH access that resets at every reboot.</p><p>A companion Python script (<code>compute_aggregate_metrics.py</code>) that produced the published numbers is released alongside this paper. The underlying pilot dataset (83 files, 787 MB comprising face images and multi-camera video from three workers) is <strong>not released</strong> in accordance with DPDP Act 2023 obligations.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19659518 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Punch-Seeded Face Enrollment and Multi-Camera Re-Identification in Legacy Indian CCTV Deployments: A Dual-Site Pilot Study Aggarwal, Vibhav face recognition DBSCAN clustering multi-camera re-identification CompreFace Frigate NVR Double Take legacy CCTV punch-fusion biometric attendance integration Hikvision small-organization deployment DPDP Act 2023 India manufacturing applied computer vision <p>Indian small and medium manufacturers operate a vast installed base of legacy CCTV infrastructure — Hikvision IP cameras, analog DVRs, and consumer-grade NVRs — that is typically used only for passive recording. The gap between “cameras that exist” and “cameras that contribute to operational intelligence” is substantial and rarely addressed in the face-recognition literature, which assumes greenfield IP deployments and large-scale labeled datasets.</p><p>We describe a two-site pilot that retrofits face recognition and multi-camera worker re-identification onto unmodified legacy infrastructure at two distinct sites in Haryana, India: (i) a 22-camera Hikvision IP deployment at a gasket manufacturing facility (Phase 2, 3 cameras online, 3 workers enrolled), and (ii) a 16-channel analog DVR deployment at an Ayurvedic-pharmaceutical company office (12 cameras live, production face-recognition operational via CompreFace + Double Take + Frigate).</p><p>The technical contribution is <strong>punch-seeded enrollment</strong>: a single timestamped biometric-attendance snapshot, already captured by the plant's turnstile, is used as the sole enrollment seed from which the system propagates worker identity labels across downstream camera footage via density-based clustering (DBSCAN) with a temporal window. This reduces annotation effort from “tens of labeled frames per worker” to “one automatically-captured punch snapshot per worker”.</p><p>The paper reports only aggregate deployment metrics — no face images, no embeddings, no worker identifiers — consistent with India's Digital Personal Data Protection Act 2023 requirements for biometric data. We also document legacy-integration engineering gotchas that consumed a meaningful fraction of deployment effort: H.265 hardware decode failures on GTX 970M (compute capability 5.2), OpenVINO failing silently and reverting to CPU TFLite, digest-authenticated ISAPI calls on Hikvision cameras, and DVR SSH access that resets at every reboot.</p><p>A companion Python script (<code>compute_aggregate_metrics.py</code>) that produced the published numbers is released alongside this paper. The underlying pilot dataset (83 files, 787 MB comprising face images and multi-camera video from three workers) is <strong>not released</strong> in accordance with DPDP Act 2023 obligations.</p> |
| title | Punch-Seeded Face Enrollment and Multi-Camera Re-Identification in Legacy Indian CCTV Deployments: A Dual-Site Pilot Study |
| topic | face recognition DBSCAN clustering multi-camera re-identification CompreFace Frigate NVR Double Take legacy CCTV punch-fusion biometric attendance integration Hikvision small-organization deployment DPDP Act 2023 India manufacturing applied computer vision |
| url | https://doi.org/10.5281/zenodo.19659518 |