SEARCH · Search NASA
Results for “Computer Vision”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Spatial Grid-Based Object Localization from A Single Passive Sensor: A Deep Learning-Integrated Approach
Ongoing efforts at NASA’s Langley Research Center have produced a single passive sensor system for detecting ground objects and pinpointing their real-world location to a desired level of precision. The Langley center serves as a test range for unmanned aerial systems (UAS) and real-time knowledge about the location of people on campus is needed to inform least-risk UAS flight operations. The proposed system provides this knowledge through a camera combined with a convolutional neural network and an algorithm that projects an imaginary grid of square cells from the ground plane onto the perspective view of the camera. The position of detected objects on the camera’s projected grid determines their location in the real-world. The imaginary grid is easily mapped to a universal coordinate system, such as longitude and latitude, to provide both relative and absolute positional information of the detected objects. This simple system is shown to be accurate and effective, with decisive advantages over alternative multi-sensor and active sensor approaches. Extensions to the system are described to allow adaptation to a variety of other use cases.
Concepts for Distributed Sensing and Collaborative Airspace Autonomy in Advanced Urban Air Mobility
Emerging concepts for advanced urban air mobility envision responsive air transportation capabilities that will safely move people and cargo in locations presently underserved by aviation. Expanding aviation services to these locales, particularly for high-density autonomous flight operations over urban centers, will require advances beyond the state-of-the-art techniques for airborne sensing. The emerging field of distributed sensing and ‘smart spaces’ – where sensing, processing, communication, and actuation are embedded in the environment in which agents are acting – may provide attractive alternatives over traditional aviation solutions. This paper outlines the challenges and opportunities for distributed sensing and smart space concepts to meet the emerging needs of advanced urban operations in the national airspace. We present an overview of distributed sensing concepts and research currently being investigated under this endeavor.
A Structurally-Adaptive Framework for Distributed Airborne Sensing over Real-time Collaborative Information Sharing Networks
The emergence and maturation of wireless communication technologies continue to transform the aviation industry and are enabling new solutions to challenges faced by NASA’s Advanced Air Mobility (AAM) initiative. AAM is leading towards high-density autonomous aircraft operations in areas underserved by traditional aviation, such as over densely populated urban centers. In this paper, we build on concepts from distributed sensing and smart spaces - where sensing, processing, and communication are embedded in an environment, and agents are operating within the space can exploit these capabilities in real-time through collaborative information sharing networks. Building from these concepts, we propose a framework to enable a dynamic, topologically-adaptive, and distributed estimation system for man-rated aviation to address challenges faced by autonomous AAM operations. This paper presents the initial concept of operations and system design for this framework, presents a mathematical formulation for abstraction of the problem, identifies requirements and constraints for operation, and presents algorithmic constructs to demonstrate operation. The initial framework design will focus on supporting precision navigation and independent surveillance supporting conformance monitoring of aircraft in airspace corridors and vertiport airspaces. Preliminary results from this framework shows promise in addressing gaps in current technologies needed to enable future AAM concepts, while promising greater capabilities, performance, robustness, and safety over current aviation systems and operations.
Impact Ice Microstructure Segmentation Using Transfer Learned Model
A process of using machine learning to segment impact ice microstructure is presented and analyzed. The segmentation was conducted with the goal of obtaining average grain size estimations. The model was trained on a set of micrographs of impact ice grown at NASA Glenn’s Icing Research Tunnel. The model leveraged a model pre-trained on a large set of micrographs of various materials as a starting point. Post-processing of the segmented images was done to connect broken boundaries. An automatic method of determining grain size following an ASTM standard was implemented. Segmentation results using different training sets as well as different encoder and decoder pairs are presented. Calculated sizes are compared to manual grain size measurement methods. Results show promise in accuracy as well as a possible improvement in repeatability and consistency. Next steps for improving the model are suggested.
Using Generative AI for Lunar Image Denoising: Instantaneous Clarity of Ambient eNvironment Capability (ICAN-C)
Using Generative AI for Lunar Image Denoising
Using Generative AI for Lunar Image Denoising: Instantaneous Clarity of Ambient eNvironment Capability (ICAN-C)
Using Generative AI for Lunar Image Denoising
Astrobee: The International Space Station Robotic Freeflyer
The Astrobees are free-flying robots that operate inside the International Space Station (ISS) and were launched to the ISS in 2019. Designed as a mobile camera, an astronaut assistant, and a research platform, they have successfully performed hundreds of activities in space supporting dozens of research projects. The robots were designed to overcome multiple challenges unique to the ISS environment, including safety, upgradeability and maintainability, limited mass and computation, and unique localization challenges from lack of gravity and a constantly changing environment. Robots such as Astrobee, have the capacity to become caretakers for future spacecraft, working to monitor and keep systems operating smoothly while crew are away. This talk will give an overview of the Astrobee robots, with an emphasis on Astrobee’s development, robotic software, and its successful use on the ISS.
Improving Satellite-Based Hotspot Detection Through Deep Learning-Enabled Smoke Recognition
While geostationary satellites, such as the GOES-R series, provide wildland fire hotspot readings at a high temporal resolution, they are prone to false negative readings and decreased confidence. One cause of decreased hotspot confidence is cloud contamination. Smoke produced from wildfire is often misinterpreted as cloud contamination, resulting in inaccurate and unsure sensor readings. To this end, we built a deep learning image segmentation model to identify smoke and cloud in true color satellite images. The model is pre-trained using self-supervised learning on over 10,000 GOES-R images to learn the underlying structure of satellite imagery. Then, the model is fine-tuned on a set of 130 labeled documents using supervised learning. The resulting model performs multi-class image segmentation with 85% accuracy and runs in under a minute on a standard personal computer. When paired alongside hotspot data, the model’s outputs can help increase confidence in wildfire location by identifying cases of cloud contamination that are due to smoke. The resulting model can be deployed in a stand-alone application or bundled in an Open Data Integration for wildland fire management (ODIN) application.
Machine Learning Based Crater Detection for Terrain Relative Navigation
As Lunar exploration continues to become more commonplace, reliable methods of precise Terrain Relative Navigation (TRN) are needed. While there are many TRN techniques available, one that has received increased interest in the past few years is that of crater based navigation. Crater based navigation has numerous benefits, including being a human recognizable feature (important for crewed missions), as well as the fact that craters are often possible hazards that need to be detected and avoided. The use of crater based navigation has been limited however. This has been due to the difficulty of running such algorithms on board a spacecraft, as well as the difficulty in procuring large amounts of the required training data. This paper presents a new rendering tool for generating large amounts of high quality training data. It then looks at two recently developed machine learning techniques for crater detection and crater identification in real-time on near-future space hardware.
Method and apparatus for predicting the direction of movement in machine vision
A computer-simulated cortical network is presented. The network is capable of computing the visibility of shifts in the direction of movement. Additionally, the network can compute the following: (1) the magnitude of the position difference between the test and background patterns; (2) localized contrast differences at different spatial scales analyzed by computing temporal gradients of the difference and sum of the outputs of paired even- and odd-symmetric bandpass filters convolved with the input pattern; and (3) the direction of a test pattern moved relative to a textured background. The direction of movement of an object in the field of view of a robotic vision system is detected in accordance with nonlinear Gabor function algorithms. The movement of objects relative to their background is used to infer the 3-dimensional structure and motion of object surfaces.
A Compact VLSI Neural Computer Integrated with Active Pixel Sensor for Real-time Machine Vision Applications
A compact VLSI neural computer integrated with an active pixel sensor has been under development to mimic what is inherent in biological visio systems.
Computation and parallel implementation for early vision
The problem of early vision is to transform one or more retinal illuminance images-pixel arrays-to image representations built out of such primitive visual features such as edges, regions, disparities, and clusters. These transformed representations form the input to later vision stages that perform higher level vision tasks including matching and recognition. Researchers developed algorithms for: (1) edge finding in the scale space formulation; (2) correlation methods for computing matches between pairs of images; and (3) clustering of data by neural networks. These algorithms are formulated for parallel implementation of SIMD machines, such as the Massively Parallel Processor, a 128 x 128 array processor with 1024 bits of local memory per processor. For some cases, researchers can show speedups of three orders of magnitude over serial implementations.
Stereo vision for planetary rovers - Stochastic modeling to near real-time implementation
JPL has achieved the first autonomous cross-country robotic traverses to use stereo vision, with all computing onboard the vehicle. This paper describes the stereo vision system, including the underlying statistical model and the details of the implementation. It is argued that the overall approach provides a unifying paradigm for practical domain-independent stereo ranging.
Vision 2030 Aircraft Propulsion Grand Challenge Problem: Full-engine CFD Simulations with High Geometric Fidelity and Physics Accuracy
2014 NASA published the outcome of the 2030 CFD (Computational Fluid Dynamics) Vision study: “CFD Vision 2030: A path to Revolutionary Computational Aerosciences” . The study provided a comprehensive review of the state of the art of CFD in 2014 for aerospace applications including, but not limited to, numerical algorithms, physics models, MDAO (Multidisciplinary Design Analysis and Optimization) and HPC (High Performance Computing) hardware. The study also proposed four conceptual ideas of Grand Challenge problems that would build on and benefit from advances outlined in the roadmap. The proposed challenges were meant to foster more detailed descriptions of grand challenge problems for specific disciplines. One of the proposed challenges was in the gas turbine propulsion area, focusing on transient full engine simulations. The current paper addresses detailed technical aspects of that challenge, and proposes a plan to approach it in a gradual manner, which includes high fidelity modeling of components, component coupling, and targeted experimental campaigns relying on common research models.
EVA/manned systems
Viewgraphs on extravehicular activity/manned systems are presented. Objectives of crewstation design include (1) development of human-computer interface technology and graphical presentations, including multi-dimensional visual and aural displays; (2) provide a technology base for autonomous vision and other perceptual systems, virtual workstation technology, and computational vision systems; and (3) develop databases and models of human strength, motion, and body positions in microgravity environments. Extravehicular technology is addressed.
Computer graphics testbed to simulate and test vision systems for space applications
Artificial intelligence concepts are applied to robotics. Artificial neural networks, expert systems and laser imaging techniques for autonomous space robots are being studied. A computer graphics laser range finder simulator developed by Wu has been used by Weiland and Norwood to study use of artificial neural networks for path planning and obstacle avoidance. Interest is expressed in applications of CLIPS, NETS, and Fuzzy Control. These applications are applied to robot navigation.