Livestock farming is assisted more and more by technological solutions, such as robots. One of the main problems for shepherds is the control and care of livestock in areas difficult to access where grazing animals are attacked by predators such as the Iberian wolf in the northwest of the Iberian Peninsula. In this paper, we propose a system to automatically generate benchmarks of animal images of different species from iNaturalist API, which is coupled with a vision-based module that allows us to automatically detect predators and distinguish them from other animals. We tested multiple existing object detection models to determine the best one in terms of efficiency and speed, as it is conceived for real-time environments. YOLOv5m achieves the best performance as it can process 64 FPS, achieving an mAP (with IoU of 50%) of 99.49% for a dataset where wolves (predator) or dogs (prey) have to be detected and distinguished. This result meets the requirements of pasture-based livestock farms.

No abstract

Manufacturing processes require to satisfy quality standards in the produced parts. In particular, the edge finishing must be burr-free, avoiding that it yields different problems such as wasting time removing them what increases the production cost and time. A burr can be noticed microscopically, but it can contain imperfections or evidence of poor piece design. In order to detect automatically this imperfections and to evaluate the quality of the edge finishing, this paper proposes a complete vision based method using image processing and linear regression. With the calculated function, the slope is isolated and compared to obtain quality assessment thresholds. Results validate the good performance of the proposed method to differenciate three types of burrs.

No abstract

No abstract