USF Researcher Advances Computational Imaging Technology

In a groundbreaking development in the field of computational imaging, Assistant Professor John Murray-Bruce at the University of South Florida (USF) has made significant strides in expanding the capabilities of imaging technology. His research, which is being conducted at the USF Bellini College of Artificial Intelligence, Cybersecurity and Computing, aims to enhance the ability of machines to interpret complex visual data, potentially transforming various applications ranging from national security to medical imaging.

Murray-Bruce's work leverages techniques that utilize shadows and information not discernible to the human eye, thus pushing the boundaries of what imaging systems can achieve. This innovative approach is particularly relevant in scenarios where visibility is compromised, such as mapping terrain obscured by dense foliage or detecting hidden threats around corners. In an interview, Murray-Bruce reflected on the personal motivation behind his research, stating, "My interest in pursuing this idea of seeing around corners grew after my family was t-boned in an intersection even though we had the right of way. If we had that superhuman vision of being able to peer into the intersection, perhaps we would have been able to react accordingly to avoid that crash."

Murray-Bruce is currently engaged in two major research projects, one of which is funded by the Defense Advanced Research Projects Agency (DARPA), an agency renowned for its role in pioneering technologies, including the internet. The other project is supported by a prestigious CAREER award from the National Science Foundation (NSF). The NSF initiative, which commenced on July 1, 2025, emphasizes the development of a rigorous mathematical framework aimed at enhancing computational systems' ability to interpret incomplete or difficult-to-read data.

According to the NSF project overview, "this research has created a foundation that could support a wide range of applications we hadn't even anticipated, including long-range X-ray imaging and national security." Murray-Bruce characterized the research as akin to science fiction, highlighting the potential for extreme imaging capabilities such as deep tissue imaging and advanced surveillance methods. "Think of it as a million times finer than a human hair," he elaborated.

The genesis of this research traces back to earlier investigations by Murray-Bruce and his students, which focused on reconstructing three-dimensional images from indirect light reflections. This foundational work has evolved into a sophisticated modeling approach that enhances imaging systems' interpretive power.

The DARPA project is particularly ambitious, setting the challenge of developing a system capable of producing usable images from X-rays over several miles, in contrast to traditional systems that require proximity to the object being scanned. As Murray-Bruce noted, "We're competing with some of the biggest names in defense technology on this project - teams from major government contractors. And yet we're standing firm. It's a testament to the strength of our approach and the relentlessness of my talented students."

Murray-Bruce's students play an integral role in the research process. Chibuike Ezeokoli, a doctoral senior in computer science and engineering, expressed his enthusiasm for the collaborative environment fostered in Murray-Bruce's lab. "I've had the opportunity to collaborate with and learn from other students. It is the ideal environment to nurture the skills required for a future career trying to solve crucial real-world problems through research," Ezeokoli stated.

The innovative algorithms and modeling techniques developed by Murray-Bruce and his team have achieved promising results, with their system demonstrating 97% accuracy at distances just under one mile and 75% accuracy at nearly three miles. "These results are promising, though we are not yet at the limit of what is theoretically possible. It's an extreme version of shadow-based imaging," he explained. The methodology involves sending X-rays through an object to capture the shadows at the detector, though challenges remain as distances increase, causing shadows to become weaker and noisier.

If selected by DARPA to move forward to Phase 2 of the program, Murray-Bruce and his team plan to further explore imaging scenarios that involve greater distances and significant motion blur. This research not only highlights the potential advancements in imaging technology but also underscores the importance of academic-industry collaboration in addressing complex challenges in defense and public safety.

In summary, the work of John Murray-Bruce and his team at the University of South Florida represents a significant leap forward in computational imaging technology. With potential applications spanning from national security to healthcare, the implications of their research could redefine how we interact with and perceive the world around us.