← Back to NASA Technology Projects
Completed TRL 3 (started at 2, targeting 3)
As NASA prepares to return humans to the moon the need for near-instant image and video denoising will become vitally important to decision making. One of the use cases for video denoising will be for landing leg attenuation on the Human Landing System during Lunar descent. Instantaneous Clarity of Ambient eNvironment Capability(ICAN-C) answers the need for visual aids in hash off-planet environments.
This software and hardware implementation aims to increase visibility in scenarios of obscured and hazy vision. ICAN-C builds off of Marshall Space Flight Center (MSFC) EV31's optical technology capabilities by adapting in-house software to identify and remove vision obscuring dust and lofted lunar regolith in real-time for reduction of visual noise in a visual display. We use Computer Vision and AI/ML techniques to segment and mask dusty regions of an image/video and use a custom 2 pronged neural network to replace the vision obscuring segments with a relevant background.
ICAN-C answers the need for onboard video denoising for use in Moon to Mars missions. The ability to use ICAN-C on any video means it is flexible enough to use on FLIR, SWIR/LWIR, high speed, or ordinary video in any environment. Near real-time capability allows the user to make instantaneous decisions by reducing the visual obstruction of nearby terrain. The current iteration of ICAN-C has been trained on Clementine Spacecraft and Lunar Reconnaissance Orbiter images to build a context-informed model. Preliminary performance and results have shown promise.
This technology directly ties to Marshall Space Flight Center's focus areas of surface systems, habitation systems, lander systems, and the directive to improve Artificial Intelligence/Machine Learning capabilities at MSFC. This technology is directly transferrable to external customers for non in-space use, such as military applications, underwater applications, and medical transport field. ICAN-C’s technology level has grown to a TRL 3 since its inception in 2022. This project has been awarded a Center Innovation Fund for FY2023, and Technical Investment Program for FY2024. We are pursuing another Center Innovation Fund for FY2025 and looking for external partnerships.
ICAN-C directly addresses STMD gaps COMMNAV-004, CN-05-001, Surface Navigation in Challenging Environments; COMNAV-005, CN-02-008, Metric Tracking Data From All Optical Surfaces. This project meets the definition of both push and pull, with the push coming from the optical enhancement capability of any low visibility scenario such as lunar dust obstructing vision during landing, lunar regolith operations, and video feeds of docking. The pull comes from the ability to transfer this technology to Earth industries such as improving brownout obscuring soldiers’ vision during helicopter landing, the turbidity of water obscuring a diver’s vision, or any operations where visual clarity is needed. ICAN-C has wide reaching applications and performs exceptionally well in simulated lunar environments (such as MSFC’s Lunar Regolith Terrain (LRT)). The current iteration of ICAN-C is best suited for lunar and Martian operations. However, ICAN-C’s architecture allows for alternative Earth-based terrain landscapes to be used as training data to customize the model based on different geographic deployment locations and weather conditions (i.e., blowing southeastern US clay vs Saharan dust vs snow). There is no other similar technology on the market today.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.
None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.