Animal Detection and Monitoring System Using IoT

The Animal Detection and Monitoring System Using IoT is a budget-friendly project that aims at minimizing the loss of assets from the intrusion of animals. The ESP32-CAM is used in capturing the images of the surroundings and identifying animals and sending out an alert through the buzzer, LED and OLED screen with data being transferred via Wi-Fi for remote monitoring. Unlike manual surveillance, the project is automated and eliminates the requirement of continuous human intervention. The project is constructed using easily obtainable materials that can be used around farms, gardens, villages borders and forests. The project is also a good educational project on embedded systems, interfacing cameras, IoT connectivity and automatic alert systems. Further improvement can help in improving the performance of the project. In the future, storing images in cloud, notification through mobile application, utilizing solar power with battery back up, PIR motion sensor for saving energy, infrared camera for night vision and machine learning algorithms for identification of species of the animal can be introduced. Tests have to be conducted in various environmental conditions including lighting and distance to find the performance of the project in terms of accuracy and energy consumption. Since no results have been obtained  

[1] Arduino, Arduino IDE Documentation. Arduino Documentation. [2] Espressif Systems, ESP32 Series Datasheet. Espressif Systems. [3] Espressif Systems, ESP-WHO: Face Detection and Recognition Framework. Espressif Systems. [4] Howard, A. G., et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv:1704.04861, 2017. [5] Lin, T.-Y., et al., “Microsoft COCO: Common Objects in Context,” in European Conference on Computer Vision (ECCV), pp. 740–755, 2014. [6] Liu, W., et al., “SSD: Single Shot MultiBox Detector,” in European Conference on Computer Vision (ECCV), pp. 21–37, 2016. [7] NXP Semiconductors, I²C-Bus Specification and User Manual, UM10204, Rev. 7.0, 2021. [8] Redmon, J., Divvala, S., Girshick, R., and Farhadi, A., “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016. [9] Solomon Systech Limited, SSD1306: 128 × 64 Dot Matrix OLED/PLED Segment/Common Driver with Controller, Technical Datasheet. [10] Wang, J., et al., “Deep High-Resolution Representation Learning for Visual Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3349–3364, 2021.