Researchers at Purdue University’s College of Engineering have created two imaging technologies that could be developed and commercialized for applications such as medical imaging, autonomous navigation, surveillance, microscopy, and advanced manufacturing. The patent-pending technologies, the CT-Bound and MetaHDR, were created by separate research teams led by Qi Guo, assistant professor in the Elmore Family School of Electrical and Computer Engineering. In computer vision, boundary detection is necessary in applications like autonomous navigation, manufacturing, and medical imaging. While boundary detection has been studied since the early days of computer vision, accuracy of even the current best algorithms remains unsatisfactory for noisy and low light images, Guo said. CT-Bound approaches the issue by decomposing boundary estimation into two tasks: local detection and global regularization. “During the local detection, the model uses a convolutional architecture to predict the boundary structure of each image patch in the form of a predefined local boundary representation, the field of junctions,” said Guo. “Then it uses a feed-forward transformer architecture to globally refine the boundary structures of each patch to generate an edge map and a smoothed color map simultaneously.” A thorough experimental study found that CT-Bound achieved the highest or among the highest accuracy in detecting image boundaries from very noisy images compared to the previous best algorithms. “We also demonstrated that CT-Bound produces boundary and color maps on real captured images without extra fine-tuning and real-time boundary map and color map videos at 10 frames per second,” Guo said. Purdue University graduate student Yuxuan Liu (left) and assistant professor in the Elmore Family School of Electrical and Computer Engineering, Qi Guo, analyze results captured during the testing of their MetaHDR technology. Courtesy of Purdue University/Wei Xu. In contrast, MetaHDR is a single-shot high-dynamic range (HDR) imaging and sensing system that uses a multifunctional metasurface. The system captures HDR images with a single exposure or few exposures while creating multiple low-dynamic range (LDR) images simultaneously. The system is designed to help avoid ghosting artifacts when measuring objects in motion, without the need for sophisticated post-processing algorithms. Single-shot HDR imaging and sensing is applied where the full brightness profile of a moving environment needs to be measured, including in advanced manufacturing, autonomous vehicles, microscopic imaging, and videography. “The metasurface can split an incident beam into multiple focusing beams with different amounts of power, simultaneously forming multiple LDR images with distinct irradiance on a photosensor,” said Guo. “Then the LDR images are jointly processed using a gradient-based HDR fusion algorithm, which is shown to be effective in attenuating the residual light artifacts incurred by the metasurface and the lens flare.” The validation results showed a >50 dB increase in dynamic range compared to hardware driven solutions, he continued. For the CT-Bound, the team has expanded on the technology into a broader algorithm called Blurry-Edges, which simultaneously performs boundary detection and depth estimation from noisy images. “For this, we built a hardware prototype using a deformable lens to capture low-light image pairs with varying optical powers,” said Purdue electrical and computer engineering doctoral student Wei Xu. “These advances set the stage for the next steps to be transitioning from research prototypes to deployable tools that can be integrated into industry imaging products.” Yuxuan Liu, a Purdue electrical and computer engineering graduate student, said the next step to commercializing MetaHDR is to enable full-color imaging with an enlarged field of view. “Building on recent advances in computational imaging and optical metasurfaces, we are exploring the integration of artificial intelligence, meta-optics, and refractive lenses to achieve this goal,” Liu said. “This holds significant potential for reconstructing higher-dimensional information, such as spectrum, depth, and polarization in a snapshot.” Guo’s team is currently collaborating with Jian Jin, associate professor in Purdue’s department of agricultural and biological engineering, to explore MetaHDR’s potential use in agricultural phenotyping. The research was published in IEEE Xplore (www.doi.org/10.1109/MMSP61759.2024.10743517) and Optics Express (www. doi.org/10.1364/OE.528270).