Jul 2026· European Conference on Artificial Intelligence· pp. 1-10· 0 citations· 18 references
Abstract
Modern warehouse environments demand intelligent monitoring systems that ensure both operational safety and security. However, existing surveillance solutions remain largely reactive, relying on manual observation or isolated detection mechanisms that fail to address complex real-world challenges such as occluding theft behaviors, unsafe item placement, and varying lighting conditions. This research proposes an integrated vision-based framework that unifies warehouse safety monitoring and theft detection using advanced computer vision and deep learning techniques. The system combines object detection, human pose identification, human activity recognition (HAR), and multi-camera dynamic person re-identification in occlusion scenarios for theft detection and geometry-aware risk analysis and automated shelf edge detection to detect hazardous shelf conditions in real-time. Theft-related activities such as loitering and abnormal human– item interactions are identified using activity sequences, while safety risks such as overhanging or fallen items are detected through segmentation-based object recognition and spatial boundary analysis. To enhance robustness, the framework incorporates multiple cameras for handling occluded situations and temporal stabilization techniques to reduce detection instability and false alerts. By integrating behavioral analysis with environmental risk assessment, the proposed system transforms traditional passive surveillance into a proactive monitoring solution. The framework aims to improve warehouse safety, reduce product damage, and enable early detection of theft through accurate, real-time alerts. This research contributes a scalable, multi-modal approach that addresses key limitations in existing systems, including lack of context awareness, poor occlusion handling, and absence of unified safety-security monitoring.
Vehicle theft and vandalism remain significant urban security challenges commonly addressed through reactive, post-incident forensic measures. This paper proposes a proactive, real-time computer vision system designed to detect potentially suspicious behavior around parked vehicles, with a specific focus on unauthorized proximity and loitering. The proposed architecture integrates state-of-the-art object detection using YOLOv11 (You Only Look Once version 11), multi-object tracking via a lightweight custom association tracker inspired by the ByteTrack/StrongSORT/OC-SORT paradigm, and monocular depth estimation based on the Intel DPT-Large framework.A key contribution is the identification and mitigation of the Perspective Challenge: the two-dimensional (2D) scale ambiguity that causes distant background pedestrians to appear falsely proximate to foreground vehicles in monocular camera feeds. To address this, three spatial analysis strategies are implemented and evaluated: (A) fixed Euclidean thresholding, (B) adaptive perspective thresholding, and (C) three-dimensional (3D) depth injection. Experimental results on real-world urban surveillance footage (27,000 annotated frames across two datasets) demonstrate that Strategy C achieves the highest precision (0.95) with an F1-score of 0.92, while Strategy B provides the best balance between accuracy (precision 0.88, recall 0.91, F1 0.89) and computational efficiency (32.7 frames per second, FPS). Compared to naive 2D thresholding (Strategy A), Strategy B reduces false alarms by approximately 80%, while Strategy C further improves precision to 0.95 through depth-plane verification. The system maintains real-time performance exceeding 30 FPS under Strategy B, making it a strong candidate for practical urban vehicle monitoring, subject to further large-scale validation across diverse environments.
Umar Adeel, Ammar Rashid, S. Yusof et al.· Information· 0 citations
Modern security systems have raised a new system of a need to integrate automated surveillance systems as part of their security infrastructure because of the sudden increase in urbanization, civil safety issues and the necessity to have a smart monitoring system. The conventional surveillance systems are very dependent on human operator hence constraints include fatigue, delay in response and subjectivity. Computer vision as a branch of artificial intelligence will allow machines to read and understand visual information automatically, and thus change the traditional surveillance into its intelligent and active form. This paper gives an extensive research of the computer vision approaches in automated surveillance systems. It also explores how the classical approaches to image processing have been transformed to deep learning based methods such as their application in object detection and tracking, activity recognition, anomaly detection and facial recognition. System architectures, data acquisition pipelines, feature extraction methods, model training strategies and performance evaluation metrics are also discussed in the paper. Moreover, the issues like occlusion, change of illumination, scalability, privacy, real-time processing are examined. The effectiveness of the modern computer vision methods is discussed with references to the experimental results of the representative surveillance scenarios. Lastly, the paper provides the future research direction, such as edge-AI surveillance, multimodal fusion, and explainable computer vision, which is important to the next-generation intelligent surveillance systems.
Ajay Krishnan· International Journal of Mod...· 0 citations
Commercial kitchen surveillance provides important visual evidence for food-safety supervision, but automatic anomaly detection in such scenes is still challenging. Abnormal events are usually sparse and are embedded in cluttered operating environments with occlusion, low illumination, and large appearance variation. This study focuses on three representative anomalies: rat intrusion, staff smoking, and staff upper-body clothing violation. These categories cover two different recognition difficulties. Rat intrusion requires reliable tiny-object detection, whereas the two staff-related categories require the model to capture subtle local cues while also using human posture and surrounding scene context. To address these issues, this paper develops a complete framework that combines data construction and detection model enhancement. For data construction, a semi-automatic annotation-assistance workflow is built using SAM3 and Qwen3-VL-32B. SAM3 recalls candidate regions. Qwen3-VL-32B verifies candidate categories using local patches, global context, and task-specific prompts. Before manual verification, the SAM3–Qwen3-VL workflow achieves 0.928 candidate recall and 0.903 label precision. Human verification further improves the final candidate recall and label precision to 0.971 and 0.976, respectively. The complete annotation workflow requires only 38.2% of the time used by fully manual annotation. For detection, a task-oriented YOLOv11 adaptation is developed by integrating three complementary modules from prior studies. FeaturePyramidSharedConv is used to enhance high-level multi-scale context, MultiScaleGatedAttn is used to strengthen adaptive cross-layer feature selection, and DynamicScalSeq is used to reinforce the $P_{3}$ small-object branch through stacking along the scale dimension and max-response selection. Experiments on a custom kitchen anomaly dataset show that, under the default YOLOv11n setting with an input size of $640\times 640$ , the improved model achieves 0.862 mAP@0.5, which is 3.3 percentage points higher than the YOLOv11n baseline. Additional experiments further show that each adapted component contributes to the final performance, and that the framework remains effective under different MSGA placements, DynamicScalSeq variants, input resolutions, and model scales. These results indicate that the proposed method provides a practical solution for complex kitchen anomaly detection and intelligent food-safety monitoring.
Deep learning-based object identification models have been incorporated for improved situational awareness and security monitoring as a result of the quick development of intelligent surveillance systems. In order to detect dangerous objects including guns, explosives, and suspicious goods in complicated situations, this study proposes an Advanced Surveillance Framework that makes use of YOLOv10, a next-generation real-time object detection algorithm. In order to increase detection accuracy in a variety of illumination and occlusion scenarios, the suggested system integrates visual and infrared modalities through multi-sensor data fusion. Through enhanced feature aggregation, adaptive anchor mechanisms, and transformer-based attention modules, YOLOv10's optimised architecture provides greater speed–accuracy trade-offs. The fusion-based YOLOv10 model is a potent solution for contemporary surveillance applications in public safety, border control, and smart city security networks because experimental results show that it greatly outperforms conventional single-sensor approaches in precision, recall, and real-time responsiveness.
Sadiya Begum, Lubna Nausheen, Ruqiya Fatima· International Journal of Eng...· 0 citations
This study presents an intelligent framework for identifying security intrusions around wind farms by integrating advanced video surveillance and target tracking technologies. To address the challenges posed by dynamic outdoor environments — such as occlusions, illumination changes, and large scale spatial layouts — the framework introduces two core components: The Dynamic Surveillance Intrusion Detection Model (DSIDM) and the Dynamic Intrusion Detection Framework (DIDF). The DSIDM leverages a hierarchical design combining convolutional neural networks for spatial feature extraction and recurrent structures for modeling temporal dependencies. It incorporates feature encoding, object localization, motion pattern understanding, and multiobject tracking to accurately recognize diverse categories, including authorized personnel, wildlife, and potential intruders. A decision mechanism further integrates spatial temporal cues to evaluate intrusion likelihood with high robustness. Complementing this, the DIDF employs adaptive surveillance principles to refine detection under real-world operational variability. It integrates spatial–temporal prediction, probabilistic modeling, reinforcement learning-based decision optimization, and noise reduction mechanisms to ensure reliable performance under fluctuating weather, camera noise, and complex motion behaviors. By dynamically adjusting thresholds and surveillance actions, the DIDF enhances responsiveness and reduces false alarms. Extensive experiments conducted on multiple wind farm-related surveillance datasets demonstrate the effectiveness of the proposed framework, showing improvements in accuracy, robustness, and computational efficiency compared with state of the art methods. Together, the DSIDM and DIDF provide a scalable and adaptive solution for real time protection of wind farm infrastructure.
Huatao Si, Jiakun Wang, Bei Wang· International Journal of Ima...· 0 citations
Suggestions for ensuring safe person detection using AI in industrial environments are offered, including suggestions for ensuring safe person detection using AI in industrial environments.
Iwo Kurzidem, Andrea Matic-Flierl, Poulami Sinhamahapatra et al.· 0 citations