Lightweight UAV-based object detection and tracking for intelligent oil and gas field safety monitoring
- 1Digital Intelligent Technology Subsidiary of Southwest Oil and Gas Field, Chengdu, China
Abstract
Continuous, reliable monitoring of geographically dispersed oil and gas production facilities is essential for accident prevention, asset integrity, and regulatory compliance, yet ground-based inspection is labour-intensive and temporally sparse. Unmanned aerial vehicles (UAVs) offer on-demand aerial coverage, but automated interpretation of production-site imagery is hindered by extreme target-scale variation, irregular equipment geometries, and the limited compute available on airborne platforms. This paper presents an integrated lightweight detection-and-tracking framework tailored to oil and gas field surveillance. The detector augments YOLOv8s with deformable C2f (DCNv2) modules for geometry-adaptive feature extraction, a progressive feature pyramid (AFPN) that suppresses cross-scale semantic conflict, a parameter-shared detail-enhanced head (LSDECD-Head), a Focaler-GIoU regression loss, and LAMP structured pruning for embedded deployment. For dynamic situational awareness, an improved ByteTrack introduces a spatial–appearance similarity matrix encoding operational-state cues and an acceleration-aware Kalman correction. On VisDrone2019, UAVDT, and a self-constructed oil-and-gas dataset (OGF-UAV), the method attains 44.1%, 57.6%, and 56.3% [email protected] with only 7.8 M parameters at 78 FPS, and reduces tracking identity switches by up to 43.2%. The pruned model runs at 18.3 FPS on an NVIDIA Jetson Orin NX 16 GB under TensorRT FP16, confirming practicality for real-time field deployment.
Related
- TCLNet: A Thermal Contrast-Aware Lightweight Network for infrared object detection
- A lightweight YOLO based framework for real-time seat belt detection in intelligent traffic surveillance
- A lightweight underwater biological object detector with enhanced cross-scale feature interaction
- Intelligent Hydrogel Sensors for Health Monitoring and Therapeutic Intervention: From Material Design to Integrated Diagnosis and Treatment.
- Objective sleep tracking for fatigue management in cargo pilots: six months of continuous smart-ring monitoring
BibTeX
@article{gong2026lightweight,
title = {{Lightweight UAV-based object detection and tracking for intelligent oil and gas field safety monitoring}},
author = {Jianhua Gong and Yifu Wang and Jun Zhang and Defei Du and Yang Huang},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0358757},
url = {https://doi.org/10.1371/journal.pone.0358757},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Lightweight UAV-based object detection and tracking for intelligent oil and gas field safety monitoring
AU - Jianhua Gong
AU - Yifu Wang
AU - Jun Zhang
AU - Defei Du
AU - Yang Huang
PY - 2026
DA - 2026/09/25
JO - PLOS One
DO - 10.1371/journal.pone.0358757
UR - https://doi.org/10.1371/journal.pone.0358757
AB - Continuous, reliable monitoring of geographically dispersed oil and gas production facilities is essential for accident prevention, asset integrity, and regulatory compliance, yet ground-based inspection is labour-intensive and temporally sparse. Unmanned aerial vehicles (UAVs) offer on-demand aerial coverage, but automated interpretation of production-site imagery is hindered by extreme target-scale variation, irregular equipment geometries, and the limited compute available on airborne platforms. This paper presents an integrated lightweight detection-and-tracking framework tailored to oil and gas field surveillance. The detector augments YOLOv8s with deformable C2f (DCNv2) modules for geometry-adaptive feature extraction, a progressive feature pyramid (AFPN) that suppresses cross-scale semantic conflict, a parameter-shared detail-enhanced head (LSDECD-Head), a Focaler-GIoU regression loss, and LAMP structured pruning for embedded deployment. For dynamic situational awareness, an improved ByteTrack introduces a spatial–appearance similarity matrix encoding operational-state cues and an acceleration-aware Kalman correction. On VisDrone2019, UAVDT, and a self-constructed oil-and-gas dataset (OGF-UAV), the method attains 44.1%, 57.6%, and 56.3% [email protected] with only 7.8 M parameters at 78 FPS, and reduces tracking identity switches by up to 43.2%. The pruned model runs at 18.3 FPS on an NVIDIA Jetson Orin NX 16 GB under TensorRT FP16, confirming practicality for real-time field deployment.
SN - 1932-6203
ER -