NCC Montenegro

10.03.2023.10.03.2023.

Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC

Researchers from the AIMHiGH team published a scientific paper in MDPI journal Sensors, This article belongs to the “Special Issue Novel Architectures and Applications for Artificial Intelligent and Internet of Things Ecosystems” (link). The paper “Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC” by S. Cakic, T. Popovic, S. Krco, D. Nedic, D. Babic, and I. Jovovic reports on the approach, experiences, and results of using HPC and AI to develop advanced Edge AI computer vision solutions for smart agriculture systems. AIMHiGH project is implemented as an experiment done in the context of FF4EuroHPC project. FF4EuroHPC is a European initiative that helps facilitate access to all high-performance computing-related technologies for SMEs and thus increases the innovation potential of European industry. Whether it is running high-resolution simulations, doing large-scale data analyses, or incorporating AI applications into SMEs’ workflows, FF4EuroHPC connects business with cutting-edge technologies. Learn more at: link.

ABSTRACT – This research describes the use of high-performance computing (HPC) and deep learning to create prediction models that could be deployed on edge AI devices equipped with camera and installed in poultry farms. The main idea is to leverage an existing IoT farming platform and use HPC offline to run deep learning to train the models for object detection and object segmentation, where the objects are chickens in images taken on farm. The models can be ported from HPC to edge AI devices to create a new type of computer vision kit to enhance the existing digital poultry farm platform. Such new sensors enable implementing functions such as counting chickens, detection of dead chickens, and even assessing their weight or detecting uneven growth. These functions combined with the monitoring of environmental parameters, could enable early disease detection and improve the decision-making process. The experiment focused on Faster R-CNN architectures and AutoML was used to identify the most suitable architecture for chicken detection and segmentation for the given dataset. For the selected architectures, further hyperparameter optimization was carried out and we achieved the accuracy of AP = 85%, AP50 = 98%, and AP75 = 96% for object detection and AP = 90%, AP50 = 98%, and AP75 = 96% for instance segmentation. These models were installed on edge AI devices and evaluated in the online mode on actual poultry farms. Initial results are promising, but further development of the dataset and improvements in prediction models is needed.

02.03.2023.03.03.2023.

EuroCC at SmAgTech EXPO VIRAL!

Within the two-day SmAgTech EXPO VIRAL event held at the University of Donja Gorica in the period from February 23 to 24, 2023 the results of the EuroCC project were presented with a special focus on the application of HPC and Ai/ML for computer vision in smart chicken farms.

Ms. Bojana Malisic presented the project to the visitors

The event gathered over 300 visitors from Montenegro, Bosnia and Herzegovina, Serbia, Slovenia, the Netherlands, including agricultural small and medium-sized enterprises, representatives of the IT sector, and academy. In addition to the aforementioned, the event was attended by students and high school pupils attending educational programs complementary to agriculture, information technology and food technology.

Mr Stevan Cakic presenting a HPC/AI use case in agriculture

Numerous companies in the field of agriculture, food industry, as well as information technologies and systems that presented their products and services at the fair, had the opportunity to learn about the EuroCC project and the advantages offered by advanced computing in the form of HPC technology.As part of the EXPO, the representatives of NCC Montenegro presented a pilot project-experiment within Horizon 2020 for innovative small and medium-sized enterprises, which is related to the application of HPC technologies in agriculture, specifically in poultry farming, where with the help of HPC technology, diseases among poultry are monitored and predicted by applying machine learning.

NCC Montenegro team at VIRAL EXPO 2023

VIRAL EXPO 2023 video (longer version)

01.03.2023.02.03.2023.

FF4EuroHPC releases success story video on AIMHiGH

Within the FF4EuroHPC experiment, DigitalSmart Montenegro, together with DunavNET, University of Donja Gorica, Radinovic Company, and Meso-promet Franca, used HPC and AI to develop ML prediction models for computer vision that can be ported on Edge AI and integrated into Smart agriculture systems for poultry farms.

The smart agriculture solution developed within this experiment could boost the productivity of poultry farms by potentially reducing both manual labor costs and chicken mortality rates by about 10% each. This is accomplished because assessing the weight of chickens in real-time increases the uniformity of the finished product and reduces the impact of stress on both the chickens and manual labor. Furthermore, real-time insight into poultry barns allows for improving disease management due to early detection.

HPC provided the technology organisations DigitalSmart Montenegro and DunavNET needed to develop smart agriculture solutions quickly and efficiently using machine learning and computer vision, in this case for the needs of the poultry industry. The computer kit has become a part of the PoultryNET platform offering, and there is an opportunity to sell such components to third-party vendors active in the market of smart agriculture solutions.

Click to watch

20.02.2023.20.02.2023.

Short course and student workshop on IoT and AI

A short course and student workshop on AI and IoT took place on 16 February, 2023 within a dedicated session at the IEEE IT2023 conference. This training event is organized by UDG and NCC Montenegro as a part of implementation of the project called “Competency Training for IoT and AI – InnovateYourFuture” supported by ANSO – Alliance of International Science Organizations, China. The edge AI devices were provided through NVIDIA Academic grant. The workshop is includes introduction to AI and IoT (AIoT), software tools for AI/ML, edge AI, and IoT, and presentation and practical demonstrations. The target audience is MSc, BSc, and high-school students, but others are welcome, too. The conference program is available at the following link. The presenters at the workshop were Tomo Popovic, Stevan Cakic, Ivan Jovovic, Zoja Scekic, Dejan Babic and Igor Culafic. The event involved around 60 attendees, 30 on-site and 30 online.

Live demo for the audience (Edge AI with NVIDIA Jetson Nano)

Around 30 students in-person and 30 online attended the event

More information about the conference is available at the IT2023 conference website (link). The workshop will include introduction to AI and IoT (AIoT), software tools for AI/ML, edge AI, and IoT, and presentation and practical demonstrations. The target audience is MSc, BSc, and high-school students, but others are welcome, too. The conference program is available at the following link.

17.02.2023.19.02.2023.

IEEE IT2023: Disease Prediction Using ML Algorithms

Researchers from NCC Montenegro presented a paper at the 27th IEEE Conference on Information Technology IT2023 on 17th February 2023. The paper is titled “Disease Prediction Using Machine Learning Algorithms” and authored by I. Jovovic, D. Babic, T. Popovic, S. Cakic and I. Katnic.

ABSTRACT – This study aimed to investigate the application of machine learning techniques for disease prediction. Three popular machine learning algorithms, Random Forest, Support Vector Machines and Naive Bayes, were employed and their performance was evaluated. Results showed that the best performing model was based on Random Forest algorithm with the average accuracy of 87%. This model has been additionally tuned in order to achieve even better performance, which resulted with 90% accuracy. This study highlights the potential of AI in disease prediction and provides insights into the importance of algorithm selection and tuning for optimal performance.

Mr. Ivan Jovovic presenting at IEEE 2023 conference

The paper will soon be available through IEEE Xplore

17.02.2023.28.04.2023.

IEEE IT2023: Vision-based Vehicle Speed Estimation Using the YOLO Detector and RNN

Researchers from NCC Montenegro presented a paper at the 27th IEEE Conference on Information Technology IT2023. The paper is titled “Vision-based Vehicle Speed Estimation Using the YOLO Detector and RNN” and authored by Andrija Peruničić, Slobodan Djukanović and Andrej Cvijetić

ABSTRACT : The paper deals with vehicle speed estimation using video data obtained from a single camera. We propose a speed estimation method which uses the YOLO algorithm for vehicle detection and tracking, and a recurrent neural network (RNN) for speed estimation. As input features for speed estimation, we use the position and size of bounding boxes around the vehicles, extracted by the YOLO detector. The proposed method is trained and tested on the recently proposed VS13 dataset. The experimental results show that the box position does not bring any improvement in the speed estimation performance. The proposed RNN-based estimator gives an average error of 4.08 km/h using only the area of bounding box as input feature, which significantly outperforms audio-based approaches on the same dataset.

Link : https://ieeexplore.ieee.org/document/10078639

17.02.2023.28.04.2023.

IEEE IT2023: Deep learning-based vehicle speed estimation using the YOLO detector and 1D-CNN

Researchers from NCC Montenegro presented a paper at the 27th IEEE Conference on Information Technology IT2023. The paper is titled “Deep learning-based vehicle speed estimation using the YOLO detector and 1D-CNN” and authored by Andrej Cvijetić, Slobodan Djukanović and Andrija Peruničić

ABSTRACT : This paper addresses vehicle speed estimation using visual data obtained from a single video camera. The proposed method accurately predicts the speed of a vehicle, using the YOLO algorithm for vehicle detection and tracking, and a one-dimensional convolutional neural network (1D-CNN) for speed estimation. The YOLO algorithm outputs bounding boxes around detected objects in an image, which is, in our case, the vehicle whose speed is to be predicted. As input to our 1D-CNN speed estimation model, we introduce a novel feature based on the change of area of the bounding box around the vehicle. The feature, referred to as the changing bounding box area (CBBA), is obtained by calculating the area of the bounding box, frame-to-frame, as the vehicle approaches the camera. The shape of the CBBA curve remains closely the same for all vehicles, with differences conditioned by the value of the observed vehicle’s speed. The proposed method is trained and tested on the VS13 dataset. Experiments show that it is able to accurately predict the vehicle’s speed with an average error of 2.76 km/h, with the best performing vehicle having the average error of just 1.31 km/h. The proposed method exhibits the robustness as a key advantage, eliminating the need for prior knowledge of real-world dimensions such as the vehicle size, road width, camera distance and angle in relation to the road etc.

Link : https://ieeexplore.ieee.org/document/10078518