Sign In

Otto Debals

CEO at Segments.ai (YC W21) | Multi-sensor labeling for self-driving vehicles/robots | PhD | *Hiring!*

Professional Background

Otto Debals is a distinguished professional with a strong background in electrical engineering and technology leadership. He is widely recognized for his innovative contributions to the fields of robotics and automotive technology, notably as the founder and former CEO of Segments.ai. This advanced company specializes in the rapid creation of 2D and 3D multi-sensor datasets, empowering robotics and automotive industries to drive incredible advancements and improve operational efficiencies. The passion Otto exhibits for building solutions and fostering connections aligns perfectly with Segments.ai's mission, and his leadership has been instrumental in shaping its growth and impact on the market.

Before embarking on his entrepreneurial journey, Otto amassed notable experience at McKinsey & Company. His time there, spanning several roles from Junior Associate to Associate and ultimately to Summer Business Analyst, provided him with a wealth of knowledge in strategic problem-solving and analytical frameworks. His tenure at such a prestigious firm polished his ability to navigate complex business challenges with both creativity and strategic insight. Furthermore, his role as Founder and Coordinator at TechStart showcased his commitment to nurturing the tech ecosystem, emphasizing his drive to collaborate and innovate in tech-centric environments.

Education and Achievements

Otto’s academic foundation is equally impressive. He earned his Doctor of Philosophy (Ph.D.) in Electrical Engineering from KU Leuven, one of Europe’s top universities, deepening his expertise in this crucial technology field. His scholarly accomplishments include a Master’s Degree in Mathematical Engineering and a Bachelor’s Degree in Electrical Engineering and Computer Science from the same prestigious institution. This rigorous educational background, complemented by studies at the renowned CFA Institute, has provided him with a strong analytical framework, which is crucial for his work in technology innovation and business strategy.

An early educational chapter in his journey took place at Sint-Amandscollege Kortrijk, where Otto focused on Latin, Mathematics, and Science—subjects that fostered his analytical mindset and problem-solving abilities that would serve him well throughout his career.

Achievements

Otto is not just a passive participant in his professional landscape; he actively seeks impact through his engagements. His leadership roles, highlighted by serving as President and a member of the Board of Directors at Sagio.be, reflect a strong commitment to the advancement of technology in business. His involvement as a Ph.D. Researcher at KU Leuven solidifies his standing as a thought leader in the field fostering academic inquiry and practical application of technology in various sectors.

Through each of his roles, from his foundational studies to his cutting-edge work at Segments.ai and influential positions at McKinsey, Otto Debals has made an indelible mark in the technology space. Otto continues to be enthusiastic about building solutions that create meaningful impacts and looks forward to connecting with other professionals who share a similar passion for technology and innovation.

Highlights

Aug 9 · linkedin

When I receive labeling guideline documents from prospects and customers, they typically include the what, but not the how. Nevertheless, clear rules ensure consistency and accuracy across the dataset. 👇

Especially for more advanced labeling projects, the number of rules grows exponentially. Three ways to uncover the missing parts in the guidelines are:

  • Process the guidelines of similar public datasets and extract the choices made
  • Task the engineering team to label some samples and to raise questions whenever there's doubt
  • Start from existing templates, such as our free templates (https://lnkd.in/enezjdDv)

Questions to get you started (You can find more here: https://lnkd.in/ekc6aK9B) You can structure the type of rules in different topics, ranging from more general rules to sensor-specific, annotation-specific, and data-specific rules. Some platforms such as the Segments.ai (YC W21) allow you to enforce rules while labeling.

General rules, e.g.

  • How precise/tight should annotations be?
  • What should be done with unclear objects/areas?
  • Which parts/areas do not require labeling?
  • Can labels overlap?
  • How do you annotate groups of individual instances that are difficult to distinguish from each other?

Sensor-specific rules, e.g.

  • What is the labeling horizon?
  • What should be done with 3D occlusions?
  • How should be dealt with sensor artifacts?

Annotation-specific rules, e.g.

  • Can there be some overlap between cuboids and the ground plane?
  • Can cuboids overlap?
  • Should all three rotational degrees of freedom be labeled?
  • Is there a minimum size of a cuboid?
  • Should an object be labeled if it is only visible on 3D sensors and not on 2D sensors?
  • Vice versa, how should an object be labeled if it is not visible on 3D sensors and only on 2D sensors?

Data-specific rules, e.g.

  • How should be dealt with dust & reflections?
  • How should be dealt with ego pose-related data drift?
  • How should be dealt with weather conditions?

Reach out for help with your labeling guidelines, or check out more questions to guide writing it yourself here: https://lnkd.in/ekc6aK9B

Jun 17 · linkedin

Looking forward to #CVPR this week in Seattle - and while flying, of course cheering for the Belgian Red Devils at Euro 2024 today 😃🇧🇪

With Bert De Brabandere & Segments.ai (YC W21)

Related Questions

How did Otto Debals leverage his expertise in electrical engineering to found Segments.ai?
What inspired Otto Debals to transition from a career at McKinsey & Company to entrepreneurship?
In what ways has Otto Debals's education at KU Leuven influenced his career in technology and engineering?
How does Otto Debals envision the future of robotics and automotive technology evolving with multi-sensor data solutions?
What key challenges did Otto Debals face when building Segments.ai and how did he overcome them?
How has Otto's role at Sagio.be contributed to his professional development in the tech industry?
Can Otto Debals share insights on effective leadership in tech startups?
Otto Debals
Add to my network

Location

Brussels Region, Belgium