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.
Feature Extraction and Selection Strategies for Automated Target Recognition
Several feature extraction and selection methods for an existing automatic target recognition (ATR) system using JPLs Grayscale Optical Correlator (GOC) and Optimal Trade-Off Maximum Average Correlation Height (OT-MACH) filter were tested using MATLAB. The ATR system is composed of three stages: a cursory region of-interest (ROI) search using the GOC and OT-MACH filter, a feature extraction and selection stage, and a final classification stage. Feature extraction and selection concerns transforming potential target data into more useful forms as well as selecting important subsets of that data which may aide in detection and classification. The strategies tested were built around two popular extraction methods: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Performance was measured based on the classification accuracy and free-response receiver operating characteristic (FROC) output of a support vector machine(SVM) and a neural net (NN) classifier.
Developing a Natural User Interface and Facial Recognition System With OpenCV and the Microsoft Kinect
The task for this project was to design, develop, test, and deploy a facial recognition system for the Kennedy Space Center Augmented/Virtual Reality Lab. This system will serve as a means of user authentication as part of the NUI of the lab. The overarching goal is to create a seamless user interface that will allow the user to initiate and interact with AR and VR experiences without ever needing to use a mouse or keyboard at any step in the process.
Autonomous Spacecraft Inspection with Free-Flying Drones
This paper describes a proof-of-concept mission demonstrating a multi-agent system performing visual inspection of damage sustained by a spacecraft. Free-flying satellites, simulated by unmanned aerial vehicles (UAVs), autonomously fly around a mock space module maximizing the search space for damage detection. The free-flyers are responsible for independently coordinating their flights to avoid collision with the space module and each other, while executing mission tasks. Damage analysis on the surface of the mock space module is performed in real-time using video from each free-flyer. Three-dimensional modeling is deployed offline to supplement and improve damage detection. This approach demonstrates the feasibility of deploying real space systems for damage detection, where 2D analysis can quickly determine region of interest and 3D visualization can produce a human-navigable virtual environment with depth perspective for further investigation.
Autonomous Freeflying Drones for Spacecraft Inspection
Explore the source record for details and available documents.
Measurement of Material Recession and Shock Standoff in Plasma Windtunnel using Neural Nets
Arcjets are plasma wind tunnels used to test the performance of heatshield materials for spacecraft atmospheric entry. These facilities present an extremely harsh flow environment with heat fluxes up to 109 W/m2 for up to 30 minutes. The plasma is low-temperature (∼1 eV) but high pressure (> 10 kPa) creating high-enthalpy supersonic flows similar to atmospheric entry conditions. Typically, material samples are measured before and after a test to characterize the total recession. However, this does not capture time-dependent effects such as material expansion and non-linear recession. This work will present new analysis of arcjet test videos which measure both the time-dependent 2D recession of the material samples and the shock standoff distance. The results show non-linear time-dependent effects are present for some conditions. The material and shock edges are extracted from the videos by training and applying a convolutional neural network. Due to the consistent camera settings, the machine learning model achieves high accuracy (± 2 px) relative to manually segmented images with only a small number of training frames (80).
Precise Image-Based Motion Estimation for Autonomous Small Body Exploration
Because they hold answers to questions about the origin of our solar system, comets and asteroids play a prominent role in NASA's roadmap for solar system exploration. This paper presents an algorithm for autonomous onboard motion estimation that will enable the precision guidance and landing necessary for small body sample return.
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.