Awarded work “Advanced deep learning for harvest robotics” presented at EMVA Business Conference in Seville. Next conference 2024 will take place in Gdansk.

Seville, Spain; May 8^th, 2023. The EMVA Young Professional Award 2023 goes to Dr. Pieter Blok for his work “Advanced deep learning for harvest robotics”. The awardee was announced on 05 May during the 21th EMVA Business Conference in Seville/Spain, where he also had the opportunity to present his work as part of the regular conference program. Pieter Blok is a researcher Deep Learning and Computer Vision at Wageningen University and Research in the Netherlands. Pieter holds a Bachelor and Master of Sciences in Agricultural Engineering from Wageningen University. In December 2022, he obtained his PhD degree at Wageningen University with the thesis entitled “Perception models for selective harvesting robots in fruit and vegetable production”. This PhD thesis was awarded the distinction cum laude. From July 1st, 2023, Pieter will continue his scientific career as an assistant professor at the Laboratory of Field Phenomics at the University of Tokyo in Japan. In Tokyo, Pieter will focus on machine learning and image processing technologies for plant phenotyping.

Awarded Work: Advanced deep learning for harvest robotics

Manual harvesting of fruits and vegetables is a labor-intensive task that suffers from the current shortage of labor in agriculture. To prevent this labor shortage from leading to a reduced supply of fruits and vegetables, robotic alternatives are currently being sought. For a robot to successfully harvest a crop, the fruits and vegetables must be detected using computer vision methods. Unfortunately, to date, most computer vision methods are unable to perform generically when deployed in different fields. This is unfavorable for the commercial success of these robots.

The goal of Pieter Blok’s PhD thesis was to research and develop new machine vision methods that can help a harvesting robot to deal with the mentioned variations and uncertainties. The focus of the PhD thesis was on three tasks that must be performed by every harvesting robot: crop detection, crop size estimation, and crop quality determination.

In the context of crop detection, Blok’s thesis focused on improving the generalization performance of convolutional neural networks (CNNs) to deal with variations within the same crop. Usually, there are many variations within a crop, which can cause the trained CNN to not be able to generalize sufficiently. Therefore, Blok’s research focused on applying different types of data augmentation to optimize the training of a CNN. With geometric data augmentation (rotation, cropping, and scaling of the image), it was demonstrated that the CNN could better generalize to multiple crop varieties.

Another research topic in Blok’s thesis focused on improving the size estimation of crops. Size estimation is important for a harvesting robot, as it determines whether a crop should be harvested or left in the field to grow further. A challenge, however, when estimating the size of a crop is that crops can be occluded by leaves, which reduces the visibility of the crop. Blok introduced a new perception method to alleviate this problem. His novel method used amodal perception, which is the ability to predict both the visible and occluded parts of objects in an image. By integrating this into a CNN, the larger amodal shape of occluded crops could be accurately estimated for three-dimensional crop size estimation and robot positioning.

The third research topic in Blok’s PhD thesis focused on crop quality determination. Specifically, it focused on using active learning to automatically select and annotate sporadically occurring plant diseases. The newly developed active learning method used the output of the CNN to select unlabeled images about which the network was most uncertain. These selected images were then interactively labelled in a semi-supervised way and used to retrain the network. This active learning method significantly reduced the annotation effort by 1400 image annotations, respectively 120 annotation hours.

The application of Blok’s deep learning technologies to five harvesting robots has enabled the successful commercialization of these robots, thus achieving a unique technology transfer from science to industry.

About the EMVA Young Professional Award 

The EMVA Young Professional Award is an annual award to honor the outstanding and innovative work of a student or a young professional in the field of machine vision or image processing. It is the goal of the European Machine Vision Association EMVA to further support innovation in the machine vision industry, to contribute to the important aspect of dedicated machine vision education and to provide a bridge between research and industry. With the annual Young Professional Award the EMVA intends to specifically encourage students to focus on challenges in the field of machine vision and to apply latest research results and findings in computer vision to the practical needs of the industry. The Award winner is presented during the EMVA Business Conference.

The next EMVA Business Conference will take place in Gdansk

Traditionally, at the end of the conference it was announced in which city the next, then 22nd EMVA Business Conference will take place. The machine vision industry will meet June 13 – 15, 2024 in Gdansk/Poland.

Photo: EMVA Young Professional Award Winner Dr. Pieter Blok (left), EMVA President Dr. Chris Yates; Picture source: EMVA

Focal topic
Real-world Machine Vision Challenges –
Coping with Variability and Uncontrolled Environments

Barcelona, March 1^st, 2023. The EMVA invites interested persons to submit their extended abstract via this Application Form for a contributed talk or poster during the 6th European Machine Vision Forum taking place October 12-13, 2023, in Wageningen, The Netherlands. Under the slogan “Research Meets Industry”, researchers and developers from machine vision, computer vision, machine learning, applied optics and photonics meet at the forum to exchange their newest ideas. Submission of extended abstracts for a contributed talk or poster shall be sent no later than May 2nd, 2023. All submissions are openly reviewed by the joint Scientific and Industrial Advisory Board of the forum.

Following some background on the forum’s focal topic in 2023 Real-world Machine Vision Challenges – Coping with Variability and Uncontrolled Environments:

Machine vision solutions provide great value to end-users, but also must function well in real-world environments like agriculture, environmental monitoring, industrial and medical applications. Depending on the application at hand, specific challenges arise which concern the variability of the vision task as well as possible disturbances or operational conditions, for example:

• Large varieties of disturbances (e.g., vibrations, motion in the scene, variable illumination, ambient light variations of the background)
• Variations of the objects to be inspected (high inter-class variability, e.g. for fruits), which may lead to insufficient training data for machine learning
• Unknown camera poses (e.g., for moving imaging platforms)

In consequence, real-world machine vision systems must be able to deal with such undesired variability. Approaches which are conceivable to address the issues include questions regarding the hardware and software design of machine vision systems; what hardware combinations are robust to a large variety of disturbances or interference; suitable preprocessing and evaluation methods; but also how machine learning can be used and adapted in such cases. Furthermore, aspects such as whether simulations can be used to model the physics of real-world scenarios; the trade-off between robustness and accuracy; and how the reliability of machine vision systems can be assessed and specified when variabilities and disturbances are present could be taken into account as well.

The Call for Contributions and further details on the 2023 forum may be found at www.emva.org as well as at www.european-forum-emva.org.

Topic: Machine Vision Enabling Logistics 4.0

Barcelona, February 23rd, 2023. The EMVA is proud to announce a series of vision-tech presentations during LogiMAT – International Trade Fair for Intralogistics Solutions and Process Management at Stuttgart Trade Fair Center. Under the title ‘Machine Vision Enabling Logistics 4.0’ four machine vision enterprises will present solutions specifically shaped to the requirements in logistics. The forum session takes place on Tuesday, 25 April 2023 from 3:00 – 3:50 p.m. and covers the following speeches:

• Schneider-Kreuznach Group => ‘Imaging Lenses in Logistics in focus‘
  This presentation discusses current technologies and highlights of imaging lenses for Logistics 4.0
• Allied Vision Technologies GmbH => ‘Vision solutions for Logistic vehicles and warehouse automation‘
  Person and pothole detection for safety for “Driver Assistant Systems and Functions” on Forklifts; object/ sign/ shelf sensing or load observation on AGVs and AMRs; pick and place applications on Robots.
• LUCID Vision Labs, Inc. => ‘Increase efficiency in logistics automation with the latest 3D Time-of-Flight cameras‘
  The presentation addresses how Time-of-Flight (ToF) can bring benefits to a vision system by reducing 3D application costs, increasing productivity, and making applications more efficient in the facility.
• LMI Technologies GmbH => ‘3D Smart Sensors for Packaging and Logistics Applications‘
  The presentation showcases how LMI’s Gocator 2490 laser profiler provides a fast and accurate method for 3D measurement of parcel dimensions.

‘Digitization of the logistics market is a macro trend with profound implications for supply chain management, material handling and warehouse operations. Machine vision is making an important contribution to the implementation of this transformation by supporting solutions for identification, tracking, measurement, robot guidance and many other important tasks. In this forum, EMVA will present the most exciting vision tech applications for logistics,‘ confirms EMVA Business Development Manager Oliver Scheel, who will moderate the forum.

The event is free of charge for LogiMAT trade fair visitors. A registration is not required.

Michael Schmidt takes over from long-term serving Dr. Fritz Dierks    

Barcelona,​ December 19^th, 2022. During the last International Vision Standards Meeting (IVSM) in Tokyo/Japan the GenICam Working Group has elected Michael Schmidt as new Chair of the Standard Working Group. Michael Schmidt leads a camera development team at Basler AG. He takes over the position from Dr. Fritz Dierks who has been leading the GenICam working group for almost 18 years and chose not to stand for another reelection to initiate the process of rejuvenating the board of the GenICam standard working group. The GenICam standard is hosted by the European Machine Vision Association (EMVA).

“I would like to thank Fritz for his relentless work driving standardization in the machine vision industry throughout all these years. The impact of his strategic vision on the industry is a lasting contribution to standardization as one of the core pillars for the success of machine vision technology,” says Michael Schmidt.

Also, the EMVA Board of Directors thanks Dr. Dierks for his extraordinary and long-term engagement to serve the machine vision industry.

Unique interchange between research and industry continues 2023 in the Netherlands.

Barcelona,​ November 11^th, 2022. Organized by the European Machine Vision Association, the fifth European Machine Vision Forum end of October in Cork/Ireland once again brought together industry and academic machine vision experts in a unique setting.

Through the hosting Tyndall Institute, the European Machine Vision Forum became a door opener of its own kind for all attendees for a deep dive into the vivid Irish Vision Tech Ecosystem covering both academic and industrial activities. This included a broad spectrum of vision-tech activities ranging from driver assistance and autonomous driving to manufacturing and quality assurance of microelectronics; all in top-notch equipped research and production facilities.

One highlight of the conference agenda was the Keynote on Terahertz Light-Field Imaging given by Professor Ullrich Pfeiffer from the University of Wuppertal who discussed challenges in beam generation and sensing as well as evaluation and introduced new approaches to solve these encounters which could also give new impulse in the visible light spectrum. The broad spectrum of machine vision technology was further covered by presentations dealing with multi-/hyperspectral image acquisition as well as real-time 3D data acquisition; high quality components for image acquisition; but also energy efficiency as a growing requirement as well as hardware support for machine vision algorithms which was highlighted in the second Keynote presenting emerging photonic platforms for developing optical non-von Neumann computing devices. Furthermore, the list of topics also included the currently very heavily researched topic of machine learning with neuronal networks. Here it was shown how this promising approach can be brought together with proven concepts, e.g. from measurement technology and computer science.

The 6^th European Machine Vision Forum is already scheduled to take place 2023 in Wageningen/The Netherlands in cooperation with Wageningen University and Research. More details will be announced soon.

Social Media feedback post of a 2022 participant in Cork/Ireland:

“Enriching presentations on current vision topics coupled with insights into local Irish research, industry and (pub) culture – the 5th European Machine Vision Forum in Cork was definitely worth the trip! I am already looking forward to the next forum at Wageningen University.”

About the European Machine Vision Forum

The European Machine Vision Forum is an annual event of the European Machine Vision Association – EMVA. The aim is to foster interaction between the machine vision industry and academic research to learn from each other, discuss the newest research results as well as challenges from applications, learn about emerging application fields, and to discuss research cooperation between industry and academic institutes. The overall aim is to accelerate innovation by translating new re­search results faster into practice. The forum is directed to scientists, development engineers, software and hardware engineers, and programmers both from research and industry.