No abstract

Automated weeding is an important research area in agrorobotics. Weeds can be removed mechanically or with the precise usage of herbicides. Deep Learning techniques achieved state of the art results in many computer vision tasks, however their deployment on low-cost mobile computers is still challenging. The described system contains several novelties, compared both with its previous version and related work. It is a part of a project of the automatic weeding machine, developed by the Warsaw University of Technology and MCMS Warka Ltd. Obtained models reach satisfying accuracy (detecting 47–67% of weed area, misclasifing as weed 0.1–0.9% of crop area) at over 10 FPS on the Raspberry Pi 3B+ computer. It was tested for four different plant species at different growth stadiums and lighting conditions. The system performing semantic segmentation is based on Convolutional Neural Networks. Its custom architecture combines U-Net, MobileNets, DenseNet and ResNet concepts. Amount of needed manual ground truth labels was significantly decreased by the usage of the knowledge distillation process, learning final model which mimics an ensemble of complex models on a large database of unlabeled data. Further decrease of the inference time was obtained by two custom modifications: in the usage of separable convolutions in DenseNet block and in the number of channels in each layer. In the authors’ opinion, the described novelties can be easily transferred to other agrorobotics tasks.

A global increase in the populations of drug resistant bacteria exerts negative effects on animal production and human health. Our study has been focused on the assessment of resistance determinants in relation to phenotypic resistance of the 74 commensal E. coli isolates present in different ecological environments. The samples were collected from poultry litter, feces, and neck skin. Among the microorganisms isolated from the poultry litter (group A), the highest resistance was noted against AMP and DOX (100%). In the E. coli extracts from the cloacal swabs (group B), the highest resistance was observed against AMP (100%) and CIP (92%). The meat samples (group C) were characterized by resistance to AMP (100%) and STX (94.7%). Genes encoding resistance to β-lactams (blaTEM, blaCTX-M), fluoroquinolones (qnrA, qnrB, qnrS), aminoglycosides (strA-strB, aphA1, aac(3)-II), sulfonamides (sul1, sul2, sul3), trimethoprim (dfr1, dfr5, dfr7/17) and tetracyclines (tetA, tetB) were detected in the studied bacterial isolates. The presence of class 1 and 2 integrons was confirmed in 75% of the MDR E. coli isolates (plasmid DNA), of which 60% contained class 1 integrons, 15% contained class 2 integrons, and 11.7% carried integrons of both classes. Thus, it may be concluded that integrons are the common mediators of antimicrobial resistance among commensal multidrug resistant Escherichia coli at important stages of poultry production.

No abstract

No abstract