Estrus Detection and Dairy Cow Identification with Cascade Deep Learning for Augmented Reality-Ready Livestock Farming

Accurate prediction of the estrus period is crucial for optimizing insemination efficiency and reducing costs in animal husbandry, a vital sector for global food production. Precise estrus period determination is essential to avoid economic losses, such as milk production reductions, delayed calf births, and disqualification from government support. The proposed method integrates estrus period detection with cow identification using augmented reality (AR). It initiates deep learning-based mounting detection, followed by identifying the mounting region of interest (ROI) using YOLOv5. The ROI is then cropped with padding, and cow ID detection is executed using YOLOv5 on the cropped ROI. The system subsequently records the identified cow IDs. The proposed system accurately detects mounting behavior with 99% accuracy, identifies the ROI where mounting occurs with 98% accuracy, and detects the mounting couple with 94% accuracy. The high success of all operations with the proposed system demonstrates its potential contribution to AR and artificial intelligence applications in livestock farming.

Human–Robot Interfaces of the NeuRoboScope: A Minimally Invasive Endoscopic Pituitary Tumor Surgery Robotic Assistance System

Endoscopic endonasal surgery is a commonly practiced minimally invasive neurosurgical operation for the treatment of a wide range of skull base pathologies including pituitary tumors. A common shortcoming of this surgery is the necessity of a third hand when the endoscope has to be handled to allow active use of both hands of the main surgeon. The robot surgery assistant NeuRoboScope system has been developed to take over the endoscope from the main surgeon's hand while providing the surgeon with the necessary means of controlling the location and direction of the endoscope. One of the main novelties of the NeuRoboScope system is its human–robot interface designs which regulate and facilitate the interaction between the surgeon and the robot assistant. The human–robot interaction design of the NeuRoboScope system is investigated in two domains: direct physical interaction (DPI) and master–slave teleoperation (MST). The user study indicating the learning curve and ease of use of the MST is given and this paper is concluded via providing the reader with an outlook of possible new human–robot interfaces for the robot assisted surgery systems.