MUMBAI: Stype Cajic, the founder of Stype, is a 40-year-old trailblazer who has built a global media tech empire from the ground up. His journey began with a simple idea while still a student—developing autofocus technology for camera cranes. What started as a project in his parent’s house bedroom has now evolved into Stype, a company with a team of over 200 people.

Since its inception in 2011, Stype has made a name for itself by providing state-of-the-art tracking solutions for VR, AR and MR (mixed reality) productions, as well as movie previsualisations. From the optical camera tracking system RedSpy 2.0 Fiber, used by the world’s biggest broadcasters like BBC, Fox, and MTV, to the innovative StypeKit mechanical tracking solution for cranes and jibs, Stype’s products are now a staple in the industry. The company’s latest breakthrough, Follower, takes talent and object tracking to new heights, enabling real people to seamlessly interact with virtual elements in AR.

In this interview, Cajic shares his insights into the evolution of his company, the technological innovations that have shaped the company’s success, and his vision for the future of media tech. Excerpts:  

What inspired you to develop Automatic aiming for camera cranes?

The idea came when a friend was building camera cranes and struggled with controlling the camera using a joystick. I thought, why not automate the process so the camera could track objects on its own? This led to the development of the first prototype, which proved the concept could work.

My background in shooting music videos against green screens also played a key role, as creating dynamic, realistic backgrounds was challenging with static shots. This led me to realise that the encoders used for automatic aiming could also track the camera’s position in 3D space, improving virtual backgrounds. Initially, we developed the system for my friend’s crane, naming it “Aim Crane,” but it took off when we adapted it into a universal kit that worked with popular cranes like the Stanton Jimmy Jib and Cammate.

How did you land your first major client?

Our big break came when we tested the system successfully in Lebanon – an AR project for a Ramadan TV show. This project helped me make necessary innovations in the software side of the workflow, particularly data conversion and lens calibration. The success of this project gave us a foothold in the industry.

Though we shared our work online, it didn’t initially lead to business until we received an unexpected email from Fox Sports Australia. They had ordered a Japanese tracking system for their AR-enhanced broadcast, but it wouldn’t arrive in time. After finding our online posts, they decided to try our system, even though it was much cheaper. We agreed to a trial, and I flew out to their studio. Despite some initial technical issues, I used a data logic analyser to tweak our system to work with theirs, and after a few adjustments, it worked perfectly. Fox Sports was impressed, especially with the auto-aiming feature, which solved problems they had with camera operators. The system not only improved their AR broadcasts but also enhanced the quality of their camera shots. The first unit we sold to them is still operational 13 years later.

                                                                     Stype’s RedSpy

What options were available on the market when you began developing an automatic aiming system for cranes?

When I started, I was studying electrical engineering and computing while also working as a video editor, mainly on music videos. It was a fun way to learn during my college days. A friend of mine, who ran a video company, began building camera cranes, but he and his team struggled to control the camera using a joystick—especially with a crane arm stretching five to six metres. It takes years of experience to master that kind of precision.

Drawing on my background in programming, I decided to create a device to automate the process, making crane operation easier, even for less experienced users. After some research, I realised there were no existing products like this on the market. Encouraged by my friend’s enthusiasm, I ordered components, incorporated the project into my college coursework, and eventually developed a prototype by the time I was around 22.

The first prototype worked brilliantly. For example, you could programme the crane to keep a flower perfectly centred in the frame while swinging the arm—producing smooth, professional shots that amazed everyone who saw them.

Interestingly, another benefit emerged from my experience shooting music videos against green screens. Back then—over 20 years ago—we’d rent films from video stores, find suitable backgrounds as inspirations, and painstakingly modify them in Photoshop to repurpose the scenes. However, these backgrounds were static, lacking the depth and dynamic feel of 3D environments. I wanted to move the camera and have the background shift perspective accordingly.

While developing the automated aiming system, I realised the same encoders used to track crane movements could output the camera’s 3D position. This “side feature” turned out to be transformative, opening up new creative possibilities—not just for us but potentially for others in video production. Eventually, this functionality became the core strength of the product, enhancing both camera control and visual effects.

                                            StypeKit and Human Crane setup

How do your camera tracking solutions differ for sports studios, music video production, and esports?

Our hardware solutions have been utilised across various production sectors, including sports, music video production, and esports. Initially, we started with mechanical tracking systems for cranes, such as the StypeKit, which provides auto-aiming and AR data output. Over time, we expanded into optical tracking products like RedSpy and Follower.

For OBs, concerts, arenas and sports, mechanical tracking systems are often preferred because they are reliable, self-sufficient, and don’t depend on external markers, making them ideal for large, dynamic environments like stadiums. In controlled studio spaces, RedSpy is the go-to solution, offering the most precise camera tracking available. Its infrared camera system uses retroreflective markers to ensure flawless tracking, with no drift or wobble, which is essential for high-quality virtual graphics. One key feature was its unobtrusiveness: the infrared LEDs blinked so briefly they were practically invisible, yet the tracking remained flawless. RedSpy’s reliability allows production teams to focus on the creative aspects of their shows instead of worrying about camera tracking performance. This is what has made it the world’s most popular camera tracking system.

StypeKit and RedSpy both have been honoured with an Emmy Award.

Follower, our newest addition, is another optical solution, goes beyond just tracking cameras. It’s similar to a motion capture system and can track people and objects in real-time. Follower is designed for interactive 3D elements, allowing real-time tracking of objects, people, or even props, making it ideal for interactive broadcasts or performances. Unlike other motion capture systems, Follower can handle the complex demands of high-quality AR and virtual content in live environments. It’s also used in LED volume environments, where traditional tracking systems might struggle with precise tracking when complex foreground graphics are involved.

                                                                  Follower Spyder

What innovations have you introduced in your software solutions?

On the software side, we have consistently pushed the envelope. After recognising the need for advanced chroma keying, we developed StypeLand, a software tool for Unreal Engine that includes a 3D difference-based chroma keyer called GreenKiller. This keyer surpasses others on the market by refining edges, enhancing shadows, and even keying through transparent objects—features that earned us an Emmy Award.

We also lead in XR solutions, offering photorealistic XR sets with LED volumes and set extensions. Our system ensures seamless transitions between virtual and real environments by automatically adjusting colour shifts across LED panels. This innovation, which is the only one of its kind on the market, earned us another Emmy, recognising our work in XR technology for Fox Sports in Los Angeles.

In total, we’ve won multiple Emmys, both for our technical contributions and for our cutting-edge software solutions. These accolades reinforce our commitment to delivering the most precise and the most reliable technology to the media production industry.

Are your solutions compatible with other suppliers, or do clients need to use your complete end-to-end system?

Our solutions are designed to integrate with other systems. Our hardware camera tracking portfolio is fully compatible with any software manufacturer that requires high-quality camera tracking. We’ve ensured that integration is straightforward, making it easy for clients to incorporate our technology into their existing workflows.

On the software side, we operate almost like a standalone company, which means our virtual graphics and XR solutions can support any other camera tracking system on the market. Compatibility has always been a focus for us, ensuring flexibility for broadcasters and studios with diverse setups.

While some clients prefer the simplicity of having a single point of contact for their entire studio solution, we also work with those who already have existing camera tracking or software in place. They don’t need to replace their current systems—whether they require just camera tracking or software integration, our solutions are fully compatible with others.

                                                 StypeKit main console

How does your technology compare to Zero Density’s solutions?

Our hardware product line is fully compatible with Zero Density, ensuring seamless integration for users. However, when it comes to software, we believe our solutions not only meet but exceed the performance of Zero Density’s offerings.

While Zero Density initially gained more installations by being the first to introduce an Unreal-based workflow, the landscape is shifting. During the period they advanced their software, we concentrated on perfecting our RedSpy camera tracking technology. Now, with both hardware and software offerings, we’re setting new industry standards.

Although software wasn’t our original focus, once we entered the market, we were determined to deliver the best possible solutions. A prime example is our chroma keyer, GreenKiller. When compared to Zero Density’s keyer, GreenKiller consistently delivers superior results—a fact many of our clients have attested to.

How is the Indian market responding to your products? Have you done many installations, and do you see India evolving into a global virtual production hub like Korea or the US?

The Indian market is one of our largest, with over 40 installations across the country. Our biggest client in India is Network18, but we’ve also worked with major broadcasters like Star Sports, Sony, Times Now, India News, and many others. In addition to broadcast and news networks, we’ve collaborated with several film studios and cinema production houses across the country.

While India’s market is vibrant and full of creative potential, it comes with unique challenges, particularly around budget constraints. Unlike regions like the US or Korea, where large-scale LED volume installations are more common, India leans heavily towards AR and green screen setups, which are more cost-effective. However, this hasn’t limited the ambition or creativity we see from Indian clients—they are eager to explore new technologies and make the most of what’s available.

Interest in our products grew significantly after our success with projects in Australia, and it has continued to expand ever since. Even for products like StypeLand, there’s considerable demand in India. Despite budget limitations, the market remains dynamic, with broadcasters and studios pushing the boundaries of virtual production in innovative ways.

With generative AI products like Sora becoming increasingly lifelike, how do you see AI impacting the AR products you deliver? Are you also using AI and machine learning within your company to improve your products?

Generative AI, like Sora from OpenAI, opens up tremendous possibilities for the AR space. When creating virtual shows, hardware and software are just part of the equation. One of the biggest investments often lies in designing virtual environments, which requires extensive work from virtual architects and designers. AI can significantly reduce these costs by automating the creation of intricate details within virtual environments—something that would typically take an enormous amount of time. This will accelerate the adoption of virtual production by making content creation more efficient and accessible.

Within our company, we’re actively exploring AI and machine learning to enhance our products. For example, in our StypeLand product, we’re experimenting with AI to optimise certain features. Looking ahead, AI will play an even more prominent role in the next generation of our products, as we continue to explore how it can enhance both performance and efficiency.

Where do you see Stype going from here?

Looking ahead, Stype is focused on expanding its portfolio with several new camera tracking products. As you’ve likely noticed, we’re continually enhancing our camera tracking solutions. We’re also diving deeper into the robotics space, similar to how we developed the StypeKit.

StypeLand has become a major growth driver for us, and its improvements are ongoing. We’re constantly refining it, adding new features that help us stay ahead of the competition. One of the latest advancements we introduced is a playlist-based system for StypeLand, which integrates with newsroom control systems using multiple protocols. This update fills in some of the gaps that were missing before.

What’s especially exciting is how StypeLand has evolved from being a tool for AR and green screens to a full-fledged solution that TV stations are now using as a central part of their workflow. It’s become more than just a piece of software—it’s now an essential tool for broadcasters.

Our aim is to continue offering a comprehensive suite of solutions that meet the needs of modern TV stations, and that’s the direction we’re taking Stype in.