本論文的主要目標是開發一個適用於工廠場景的異常事件之檢測系統，並在偵測到異常事件時向監控端發送警報。首先，本系統使用Lightweight Openpose演算法捕獲人體骨架關鍵點，然後利用提出的多層感知器神經網絡來識別各種人體姿勢，包括跌倒、蹲、跪、站和坐。透過該系統，本文提出的輕量級架構獲得了與常見的卷積神經網絡相當的識別準確率和較低的計算需求，並進行了不同標準的評估測試。隨後，提出的系統還整合了人臉識別功能，使系統不僅能夠檢測異常的人體姿勢，還能夠檢測非法人員進入工廠場地。檢測到異常事件時，即時向監控室發送警報。實驗結果證實了提出的系統在姿勢識別方面能夠取得良好的準確率，証完其輕量級架構在即時影像辨識中的可行性，以達到進行遠端的異常事件檢測。

The primary objective of this study is to develop an abnormal event detection system suitable for factory scenarios, capable of sending alerts to the monitoring end upon detecting abnormal events. First, the Lightweight OpenPose algorithm is employed to capture human skeletal key points, followed by the use of a proposed multilayer perceptron (MLP) neural network to recognize various human postures, including falling, squatting, kneeling, standing, and sitting. Through this system, the proposed lightweight architecture achieves recognition accuracy comparable to common convolutional neural networks (CNNs) with lower computational requirements. Various evaluation tests were conducted under different criteria. Furthermore, the proposed system integrates facial recognition functionality, enabling it not only detect abnormal human postures but also monitor the unauthorized person in the factory. When an abnormal event is detected, an alert is promptly sent to the backend. Experimental results confirm that the proposed system achieves satisfactory accuracy in posture recognition. Its lightweight architecture proves feasible for real-time image recognition and remote abnormal event detection.

“中華民國111年勞動檢查統計年報,” 111. [線上]. Available: https://www.osha.gov.tw/48110/48331/48333/48339/150732/post.
WEI, Shih-En, et al. Convolutional pose machines. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2016. p. 4724-4732.
J. Wang et al., "Deep High-Resolution Representation Learning for Visual Recognition," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3349-3364, 1 Oct. 2021,
Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
Papandreou, George, et al. "Personlab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model." Proceedings of the European conference on computer vision (ECCV). 2018.
Osokin, Daniil. "Real-time 2d multi-person pose estimation on cpu: Lightweight openpose." arXiv preprint arXiv:1811.12004 (2018).
A. S. Dileep, N. S. S., S. S., F. K. and S. S., "Suspicious Human Activity Recognition using 2D Pose Estimation and Convolutional Neural Network," 2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), Chennai, India, 2022, pp. 19-23
X. Li, H. Du and X. Wu, "Algorithm of Pedestrian Pose Recognition Based on Keypoint Detection," 2023 8th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC), Beijing, China, 2023, pp. 122-126
S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," in Neural Computation, vol. 9, no. 8, pp. 1735-1780, 15 Nov. 1997
Viola, Paul, and Michael Jones. "Rapid object detection using a boosted cascade of simple features." Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001. Vol. 1. Ieee, 2001.
“Opencv Cascade Object Detection”, CH.Tseng,2018. Available: https://chtseng.wordpress.com/2018/06/15/opencv-cascade-object-detection/
Kingma, Diederik P., and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014).
Zhang, Kaipeng, et al. "Joint face detection and alignment using multitask cascaded convolutional networks." IEEE signal processing letters 23.10 (2016): 1499-1503.
Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
Pashine, Samay, et al. "Deep fake detection: survey of facial manipulation detection solutions." arXiv preprint arXiv:2106.12605 (2021).
Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
Schroff, Florian, Dmitry Kalenichenko, and James Philbin. "Facenet: A unified embedding for face recognition and clustering." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
Dense Spatial-Temporal Graph Convolutional Network Based on Lightweight OpenPose for Detecting Falls - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/Lightweight-OpenPose-structure_fig2_375219566 [accessed 21 Apr, 2024]
Meilinaeka, “Definition, Function, Advantages, and Disadvantages UDP Protocol,” Direktorat Pusat Teknologi Informasi, 2024. Available:
https://it.telkomuniversity.ac.id/en/udp-is/
K. Team, “Keras documentation: KerasTuner,” keras.io. Available:
https://keras.io/keras_tuner/
"Kinect for Windows SDK 2.0," Microsoft, 2014. Available: https://www.microsoft.com/en-us/download/details.aspx?id=44561.
“混淆矩陣 (confusion matrix) -模型評估指標”,Tako Analytics,2024. Available: https://tako-analytics.com/2024-03-21-data-science-what-is-confusion-matrix-model-evaluation-metric/
“D-Link | Welcome,” Dlinktw.com.tw, 2014.Available:https://www.dlinktw.com.tw/home/product?id=9092 (accessed Dec. 09, 2024).
“C922 PRO HD STREAM WEBCAM,” Logitech.com, 2024.Available:https://www.logitech.com/zh-tw/products/webcams/c922-pro-stream-webcam.960-001091.html
"Doog Robotic Cart," Doog,2020. Available:https://doog-inc.com/en/type-transport/
Song, Yujie, and Fei Pei. "An Improved Local Mean-Based Distance Weighted K-Nearest Neighbor with Distance Metrics." 2023 IEEE 6th International Conference on Information Systems and Computer Aided Education (ICISCAE). IEEE, 2023.
Li, Lisha, et al. "Hyperband: A novel bandit-based approach to hyperparameter optimization." Journal of Machine Learning Research 18.185 (2018): 1-52.