“Deep learning–based automated measurements of the scrotal circumference of Norwegian Red bulls from 3D images” seminarium QFRG i DSLab [27.02.2023]
Serdecznie zapraszamy do wzięcia udziału w 31. seminarium organizowanym przez Quantitative Finance Research Group i Data Science Lab.
Podczas spotkania swoje badanie zaprezentują Joanna Bremer (Inland Norway University of Applied Sciences) i Michał Maj (Climatica).
Spotkanie odbędzie się 27 lutego 2023 r. o godz. 17:00 w formule hybrydowej: w Sali B002 na Wydziale Nauk Ekonomicznych (ul. Długa 44/50) oraz za pośrednictwem platformy Zoom.
Link do spotkania:
https://uw-edu-pl.zoom.us/j/92325152517?pwd=bGx5R0RVRXRtTk95YUZKNzNMa0o4dz09
Meeting ID: 923 2515 2517 Passcode: 844384
Spotkanie będzie prowadzone w języku angielskim.
Prosimy o zalogowanie najpóźniej o godz. 16:50.
Dołączenie do spotkania oznacza zgodę na nagrywanie. Prosimy o wyłączenie kamer i mikrofonów w trakcie prezentacji i wysyłanie pytań do prelegenta na czacie.
Streszczenie wystąpienia:
Our study aimed to create an automated method for the measurement of the scrotal circumference (SC) of Norwegian Red bulls using 3D images of the scrotum based on convolutional neural networks. It is a major agricultural trend to automate measurements of different physiological and behavioural traits. Scrotal circumference is an essential part of the selection criteria for bulls in breeding programs. Traditionally circumference is measured manually with the use of scrotal tape. The study population was bull calves recruited for performance testing before the selection of bulls for semen production in the breeding program. Bulls were measured at four different time points: upon arrival in quarantine (Q) and thereafter at approximately 6, 9 and 12 months of age. Both 3D images and manual SC measurements were performed at all time points. In our approach, SC could be calculated without direct contact with the bull, using only 3D images and a simple, user–friendly application into which mentioned images are uploaded. The results show that SC measurements obtained using semantic segmentation are comparable with manual measurements. The mean prediction error was significantly different between age groups Q, 6, 9 and 12, and it was -3.07 cm, -3.02 cm, -1.79 cm and -1.11 cm, respectively. The results show a significant difference in the SC measurement error based on the image quality. For good prediction accuracy, we recommend capturing 3D images of the best quality defined in the paper for bulls older than 6 months, considering the light conditions.