Journal of Physics Conference Series · 2020 · 10 citations · 14 references
AgricultureAgricultural EngineeringCrop SciencesAgricultural AutomationCrop ProtectionYield MonitoringAgricultural ApplicationsAgricultural Internet Of ThingsAgricultural Machine VisionInsect MonitoringPest ControlPest DetectionAgricultural SensorsAvian Pest ControlCrop MonitoringCrop YieldsInsect Pest DetectionPest Monitoring AutomationRepellent EfficacySensor-based Pest Detection
Abstract Rice field environments and bird attacks are the main problems for coverage and automatic pest control. Birds are one of several pests or destructive animals that can be found in rice fields. In general, farmers use traditional equipment such as plastic ropes and scarecrow to ward off these bird attacks. This research compares several methods of bird detection through camera sensors and chooses the best method in terms of accuracy, then applies it to repel birds automatically by utilizing sound frequencies that are disliked by birds and can repel bird pests. The design of the Bird repellent device works by utilizing computer vision techniques through camera sensors to capture bird objects in each frame, then it is processed by a microcontroller. After the object is captured on the camera, the microcontroller will activate the actuator in the form of sound frequency. The research objective is to design prototypes for the process of monitoring and automatic control of bird attacks to optimize crop yields in agriculture, based on the Internet of Things.
14
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · 2017 · 28.8K citations
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick et al. · arXiv (Cornell University) · 2015 · 18.2K citations · Full text