MANTIS Vision

iMAgiNg Technologies of Industry and Security vision

About Mantis

Image capture and video-based applications have come a long way in the past decade. Image quality has made major leaps with the transition from HDTV to 4k ultra HD (and beyond), the introduction of high dynamic range, and the broadening of the spectral range. The purpose of this project is to further improve image capture systems for high-end security and broadcast, while lowering cost and opening the path for new functionality and ease of use. The core of MANTIS vision is the development of a multi-modal, multi µ-camera system connected to an artificial intelligence (AI) capable edge processing box.

Combining information from multiple wavelength spectrum leads to better contrast and detectability as shown in figure

In terms of utilization:

  • For high-end security systems, the project will deliver new solutions that allow users to see more, farther and longer at the same size, weight, power, and cost, without increasing the complexity for the end user.
  • For broadcast, project results will help content creators for live television productions support the evolution of mobile technology to transform the way people around the world consume media content.

Object detection and tracking: The pipeline developed by TNO processes a video real-time with a deep learning detector designed to detect and track small objects. The field of view is split into tiles which are processed in batches by the deep learning network running on the GPU.

The partners will cooperate both in the development of Systems and Components. In Systems, partners (Adimec, TNO and Grass Valley) will work together to develop the new multi µ-camera architecture connected to the edge processing box running image processing. Camera system design will be supported using image-based simulation. Further, all partners will collaborate on multi sensor information processing. Some partners (Adimec, IDEAS, AMS, TNO and Grass Valley) will collaborate to evaluate multi-camera solutions in the LWIR, NIR and visible range for surveillance applications. Image Sensor Components will be developed and improved by AMS, Grass Valley, Delft Technical University and IDEAS. Developments will cover new image sensors for visual, NIR and LWIR.


OUR CONSORTIUM





Supported by:

Publications

Internal link for consortium members to register publications.

News & Events


11th PCM

11th PCM, March 8, 2024

11th PCM, March 8th, 2024

11th PCM

11th PCM, March 8, 2024

All partners assembled at TU Delft to discuss progress and plan future activities for 11th PCM on March 8th, 2024

ePicture This

9th PCM, September 6th & 7th, 2023

Kick-off dinner at Oslo before the 9th Project Consortium Meeting (PCM) at IDEAS, Oslo

ePicture This

9th PCM, September 6th & 7th, 2023

All partners assembled at IDEAS, Oslo to discuss progress and plan future activities

Visit of Grass Valley to Adimec on July 11th, 2023 to discuss de-mosaicking

July 11th, 2023

Visit of Grass Valley to Adimec on July 11th, 2023 to discuss de-mosaicking

Visit of Grass Valley to Adimec on July 11th, 2023 to discuss de-mosaicking

July 11th, 2023

Visit of Grass Valley to Adimec on July 11th, 2023 to discuss de-mosaicking

Visit of Adimec to Grass Valley on July 5th, 2023 to discuss experience sharing

July 5th, 2023

Visit of Adimec to Grass Valley on July 5th, 2023 to discuss experience sharing

Visit of Adimec to Grass Valley on July 5th, 2023 to discuss experience sharing

July 5th, 2023

Visit of Adimec to Grass Valley on July 5th, 2023 to discuss experience sharing

ePicture This

June 21th, 2023

ePicture This event organised at the Delft University of Technology on 21st June 2023 and the best presentation award was received by Dirk Meier from IDEAS

Year 2

May 11th, 2023

2023- Progress presentations during Year 2 review at TNO

Year 2

May 11th, 2023

2023- Partners presenting demonstrators to reviewers during the Year 2 review at TNO

Year 2

May 11th, 2023

2023- Partners presenting demonstrators to reviewers during the Year 2 review at TNO

Grass Valey and TNO

May 11th, 2023

Our Mantis 2nd year review team. We used a 360 camera setup to capture everyone standing in a circle. This demo setup will be used in the year 3 demonstrations (click on image for larger version).

Grass Valey and TNO

April 13th, 2023

Grass Valley and TNO met on April 13th in The Hague to discuss and align the work frame-based depth map generation with Deep Learning algorithms. Intention is to link the work in the Penta projects Mantis Vision and Imagination

Grass Valey and TNO

April 13th, 2023

Grass Valley and TNO met on April 13th in The Hague to discuss and align the work frame-based depth map generation with Deep Learning algorithms. Intention is to link the work in the Penta projects Mantis Vision and Imagination

Y1-EYR

7th PCM, March 8th & 9th, 2023

All partners assembled to discuss progress and prepare for the year end review and future activities at AMS, Antwerp


Y1-EYR

7th PCM, March 8th & 9th, 2023

All partners assembled to discuss progress and prepare for the year end review and future activities at AMS, Antwerp


Y1-EYR

7th PCM, March 8th & 9th, 2023

All partners assembled to discuss progress and prepare for the year end review and future activities at AMS, Antwerp


Y1-EYR

7th PCM, March 8th & 9th, 2023

Kick-off dinner at Antwerp before the 7th Project Consortium Meeting (PCM) at AMS, Antwerp



Y1-EYR

Progress Meeting - January 23, 2023

On 23rd January 2023, TNO and Grass Valley met in Breda to discuss the progress on deep learning depth map generation and align future activities in both the Mantis Vision and Imagination project

Y1-EYR

EFECS 2022, November 24 & 25

We are glad that MANTIS VISION gained attention exhibiting demonstrators at EFECS 2022!



Y1-EYR

EFECS 2022, November 24 & 25

We are glad that MANTIS VISION gained attention exhibiting demonstrators at EFECS 2022!



Y1-EYR

year-1 EYR, May 19, 2022

Year 1, End Year Review of the Mantis Vision project. All partners assembled and ended the day with a determination to carry on the activities for year 2 with increased vigour and mutual co-operation!


Present & Past Vacancies

ePicture This (workshop 2024)

After the great success of ePicture This 2023, we are pleased to inform you that the Penta projects: Mantis Vision and Imagination and the Xecs project Elevation will jointly organize a one-day workshop ePicture This ’24. This workshop will take place on Thursday 26 September 2024 from 09:30 – 18:00 hours at Eindhoven University of Technology (TU/e), in the Netherlands. This inspiring workshop will provide a unique opportunity to interact with experts in imaging technologies. We intend to bring together experts in image sensor design, image processing in the widest sense, and image capture design.

Agenda

Find below the agenda for the workshop
If you are involved in the electronics, components and systems industry specifically on the topic of digital imaging, we invite you to participate in the workshop by registering below. The deadline for registration is September 17th 2024.

Attendance Registration

Please type in this code


We look forward to meeting you in Eindhoven!

Participants who have been selected for presentation, please upload their full presentations below no later than 30 August 2024.
Click here to download the template & upload the full presentation.



Venue: Senaatzaal (1st Floor, Auditorium building), Eindhoven University of Technology (TU/e), The Netherlands

Keynotes

Guy Meynants (Professor, KU Leuven, Belgium)
Title: CMOS Image sensors for machine vision in the era of artificial intelligence
.

Peter H.N. de With (Professor, TU Eindhoven, The Netherlands)
Title: Towards real-time analysis systems for automated phenotyping of livestock
.

Gordon Hamilton (Chief Executive Officer, Co-Founder of Depixus, France)
Title: Illuminating the invisible: visualizing biomolecular interactions with magnetic force spectroscopy
.

CONTACT us

Do you have a question related to the MANTIS project/ePICTURE THIS?
Contact us and we'll get back to you!


Please type in this code