Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “unreliable”

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.

At least 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
NASA NTRS2005

Apparatus for Precise Indium-Bump Bonding of Microchips

An improved apparatus has been designed and built for use in precise positioning and pressing of a microchip onto a substrate (which could, optionally, be another microchip) for the purpose of indium-bump bonding. The apparatus (see figure) includes the following: A stereomicroscope, A stage for precise positioning of the microchip in rotation angle (theta) about the nominally vertical pressing axis and in translation along two nominally horizontal coordinate axes (x and y), and An actuator system that causes a bonding tip to press the microchip against the substrate with a precisely controlled force. In operation, the microscope and the stage are used to position the microchip under the bonding tip and to align the indium bumps on the chip and the substrate, then the actuator system is used to apply a prescribed bonding force for a prescribed time. The improved apparatus supplants a partly similar prior apparatus that operated with less precision and repeatability, producing inconsistent and unreliable bonds. Results of the use of the prior apparatus included broken microchips, uneven bonds, and bonds characterized, variously, by overcompression or undercompression. In that apparatus, the bonding force was generated and controlled by use of a micrometer head positioned over the center of a spring-loaded scale, and the force was applied to the microchip via the scale, which was equipped for digital readout of the force. The inconsistency of results was attributed to the following causes: It was not possible to control the bonding force with sufficient precision or repeatability. Particularly troublesome was the inability to control the force at levels less than the weight of 150 g. Excessive compliance in the spring-loaded scale, combined with deviations from parallelarity of the substrate and bonding-tip surfaces, gave rise to nonuniformity in the pressure applied to the microchip, thereby generating excessive stresses and deformations in the microchip. In the improved apparatus, the bonding tip and the components that hold the substrate and the microchip are more rigid and precise than in the prior apparatus, so as to ensure less deviation from parallelarity of the bonding-tip and substrate surfaces, thereby ensuring more nearly uniform distribution of bonding force over the area of the microchip. The bonding force is now applied through, and measured by, a load cell that makes it possible to exert finer control over the force. The force can be set at any value between 0 and the weight of 800 g in increments of 0.2 g.

Wild, Larry↗
NASA NTRS2004

Software Implements a Space-Mission File-Transfer Protocol

CFDP is a computer program that implements the CCSDS (Consultative Committee for Space Data Systems) File Delivery Protocol, which is an international standard for automatic, reliable transfers of files of data between locations on Earth and in outer space. CFDP administers concurrent file transfers in both directions, delivery of data out of transmission order, reliable and unreliable transmission modes, and automatic retransmission of lost or corrupted data by use of one or more of several lost-segment-detection modes. The program also implements several data-integrity measures, including file checksums and optional cyclic redundancy checks for each protocol data unit. The metadata accompanying each file can include messages to users application programs and commands for operating on remote file systems.

Rundstrom, Kathleen↗
NASA NTRS2004

Lightweight, Self-Deploying Foam Antenna Structures

Lightweight, deployable antennas for a variety of outer-space and terrestrial applications would be designed and fabricated according to the concept of cold hibernated elastic memory (CHEM) structures, according to a proposal. Mechanically deployable antennas now in use are heavy, complex, and unreliable, and they utilize packaging volume inefficiently. The proposed CHEM antenna structures would be simple and would deploy themselves without need for any mechanisms and, therefore, would be more reliable. The proposed CHEM antenna structures would also weigh less, could be packaged in smaller volumes, and would cost less, relative to mechanically deployable antennas. The CHEM concept was described in two prior NASA Tech Briefs articles: "Cold Hibernated Elastic Memory (CHEM) Expandable Structures" (NPO-20394), Vol. 23, No. 2 (February 1999), page 56; and "Solar Heating for Deployment of Foam Structures" (NPO-20961), Vol. 25, No. 10 (October 2001), page 36. To recapitulate from the cited prior articles: The CHEM concept is one of utilizing opencell foams of shape-memory polymers (SMPs) to make lightweight, reliable, simple, and inexpensive structures that can be alternately (1) compressed and stowed compactly or (2) expanded, then rigidified for use. A CHEM structure is fabricated at full size from a block of SMP foam in its glassy state [at a temperature below the glass-transition temperature (Tg) of the SMP]. The structure is heated to the rubbery state of the SMP (that is, to a temperature above Tg) and compacted to a small volume. After compaction, the structure is cooled to the glassy state of the SMP. The compacting force can then be released and the structure remains compact as long as the temperature is kept below Tg. Upon subsequent heating of the structure above Tg, the simultaneous elastic recovery of the foam and its shape-memory effect cause the structure to expand to its original size and shape. Once thus deployed, the structure can be rigidified by cooling below Tg. Once deployed and rigidified, the structure could be heated and recompacted. In principle, there should be no limit on the achievable number of compaction/deployment/ rigidification cycles. Thus far, several different designs of a 3.5-m-long CHEM conical corrugated horn antenna have been analyzed (see figure). A small CHEM structural antenna model was fabricated and a thin, electrically conductive layer of aluminum was deposited on the inner surface of the model. This structural model was then subjected to the compaction and deployment treatments described above to demonstrate the feasibility of a CHEM corrugated horn antenna.

Sokolowski, Witold↗
NASA NTRS2011

Design of Spacecraft Missions to Test Kinetic Impact for Asteroid Deflection

There are currently over 8,000 known near-Earth asteroids (NEAs), and more are being discovered on a continual basis. More than 1,200 of these are classified as Potentially Hazardous Asteroids (PHAs) because their Minimum Orbit Intersection Distance (MOID) with Earth's orbit is <= 0.05 AU and their estimated diameters are >= 150 m. To date, 178 Earth impact structures have been discovered, indicating that our planet has previously been struck with devastating force by NEAs and will be struck again. Such collisions are aperiodic events and can occur at any time. A variety of techniques have been proposed to defend our planet from NEA impacts by deflecting the incoming asteroid. However, none of these techniques have been tested. Unless rigorous testing is conducted to produce reliable asteroid deflection systems, we will be forced to deploy completely untested -- and therefore unreliable -- deflection missions when a sizable asteroid on a collision course with Earth is discovered. Such missions will have a high probability of failure. We propose to address this problem with a campaign of deflection technology test missions deployed to harmless NEAs. The objective of these missions is to safely evaluate and refine the mission concepts and asteroid deflection system designs. Our current research focuses on the kinetic impactor, one of the simplest proposed asteroid deflection techniques in which a spacecraft is sent to collide with an asteroid at high relative velocity. By deploying test missions in the near future, we can characterize the performance of this deflection technique and resolve any problems inherent to its execution before needing to rely upon it during a true emergency. In this paper we present the methodology and results of our survey, including lists of NEAs for which safe and effective kinetic impactor test missions may be conducted within the next decade. Full mission designs are also presented for the NEAs which offer the best mission opportunities.

Hernandez, Sonia↗
NASA NTRS2003

Aerostructures Test Wing

The Aerostructures Test Wing (ATW) was an apparatus used in a flight experiment during a program of research on aeroelastic instabilities. The ATW experiment was performed to study a specific instability known as flutter. Flutter is a destructive phenomenon caused by adverse coupling of structural dynamics and aerodynamics. The process of determining a flight envelope within which an aircraft will not experience flutter, known as flight flutter testing, is very dangerous and expensive because predictions of the instability are often unreliable. The ATW was a small-scale airplane wing that comprised an airfoil and boom (see upper part of Figure 1). For flight tests, the ATW was mounted on the F-15B/FTF-II testbed, which is a second-generation flight-test fixture described in Flight-Test Fixture for Aerodynamic Research (DRC- 95-27), NASA Tech Briefs, Vol. 19, No. 9, September 1995, page 84. The ATW was mounted horizontally on this fixture, and the entire assembly was attached to the undercarriage of the F-15B airplane (see lower part of Figure 1). The primary objective of the ATW project was to investigate traditional and advanced methodologies for predicting the onset of flutter. In particular, the ATW generated data that were used to evaluate a flutterometer. This particular flutterometer is an on-line computer program that uses method analysis to estimate worst-case flight conditions associated with flutter. This software was described in A Flutterometer Flight Test Tool NASA Tech Briefs, Vol. 23, No. 1, January 1999, page 52.

Lind, RIck↗
NASA NTRS2005

Performance Assessment of Refractory Concrete Used on the Space Shuttle's Launch Pad

The John F. Kennedy Space Center (KSC) maintains several facilities for launching space vehicles. During recent launches it has been observed that the refractory concrete materials that protect the steel-framed flame duct are breaking away from this base structure and are being projected at high velocities. There is significant concern that these projected pieces can strike the launch complex or space vehicle during the launch, jeopardizing the safety of the mission. A qualification program is in place to evaluate the performance of different refractory concretes and data from these tests have been used to assess the performance of the refractory concretes. However, there is significant variation in the test results, possibly making the existing qualification test program unreliable. This paper will evaluate data from past qualification tests, identify potential key performance indicators for the launch complex, and will recommend a new qualification test program that can be used to better qualify refractory concrete.

Trejo, David↗
NASA NTRS2011

Reliability and Maintainability Engineering - A Major Driver for Safety and Affordability

The United States National Aeronautics and Space Administration (NASA) is in the midst of an effort to design and build a safe and affordable heavy lift vehicle to go to the moon and beyond. To achieve that, NASA is seeking more innovative and efficient approaches to reduce cost while maintaining an acceptable level of safety and mission success. One area that has the potential to contribute significantly to achieving NASA safety and affordability goals is Reliability and Maintainability (R&M) engineering. Inadequate reliability or failure of critical safety items may directly jeopardize the safety of the user(s) and result in a loss of life. Inadequate reliability of equipment may directly jeopardize mission success. Systems designed to be more reliable (fewer failures) and maintainable (fewer resources needed) can lower the total life cycle cost. The Department of Defense (DOD) and industry experience has shown that optimized and adequate levels of R&M are critical for achieving a high level of safety and mission success, and low sustainment cost. Also, lessons learned from the Space Shuttle program clearly demonstrated the importance of R&M engineering in designing and operating safe and affordable launch systems. The Challenger and Columbia accidents are examples of the severe impact of design unreliability and process induced failures on system safety and mission success. These accidents demonstrated the criticality of reliability engineering in understanding component failure mechanisms and integrated system failures across the system elements interfaces. Experience from the shuttle program also shows that insufficient Reliability, Maintainability, and Supportability (RMS) engineering analyses upfront in the design phase can significantly increase the sustainment cost and, thereby, the total life cycle cost. Emphasis on RMS during the design phase is critical for identifying the design features and characteristics needed for time efficient processing, improved operational availability, and optimized maintenance and logistic support infrastructure. This paper discusses the role of R&M in a program acquisition phase and the potential impact of R&M on safety, mission success, operational availability, and affordability. This includes discussion of the R&M elements that need to be addressed and the R&M analyses that need to be performed in order to support a safe and affordable system design. The paper also provides some lessons learned from the Space Shuttle program on the impact of R&M on safety and affordability.

Safie, Fayssal M.↗
NASA NTRS2012

Copilot: Monitoring Embedded Systems

Runtime verification (RV) is a natural fit for ultra-critical systems, where correctness is imperative. In ultra-critical systems, even if the software is fault-free, because of the inherent unreliability of commodity hardware and the adversity of operational environments, processing units (and their hosted software) are replicated, and fault-tolerant algorithms are used to compare the outputs. We investigate both software monitoring in distributed fault-tolerant systems, as well as implementing fault-tolerance mechanisms using RV techniques. We describe the Copilot language and compiler, specifically designed for generating monitors for distributed, hard real-time systems. We also describe two case-studies in which we generated Copilot monitors in avionics systems.

Pike, Lee↗
NASA NTRS2012

A Study of Global Cirrus Cloud Morphology with AIRS Cloud-clear Radiances (CCRs)

Version 6 (V6) AIRS cloud-clear radiances (CCR) are used to derive cloud-induced radiance (Tcir=Tb-CCR) at the infrared frequencies of weighting functions peaked in the middle troposphere. The significantly improved V 6 CCR product allows a more accurate estimation of the expected clear-sky radiance as if clouds are absent. In the case where strong cloud scattering is present, the CCR becomes unreliable, which is reflected by its estimated uncertainty, and interpolation is employed to replace this CCR value. We find that Tcir derived from this CCR method are much better than other methods and detect more clouds in the upper and lower troposphere as well as in the polar regions where cloud detection is particularly challenging. The cloud morphology derived from the V6 test month, as well as some artifacts, will be shown.

Wu, Dong L.↗
NASA NTRS2012

The Magnetic Origins of Solar Activity

The defining physical property of the Sun's corona is that the magnetic field dominates the plasma. This property is the genesis for all solar activity ranging from quasi-steady coronal loops to the giant magnetic explosions observed as coronal mass ejections/eruptive flares. The coronal magnetic field is also the fundamental driver of all space weather; consequently, understanding the structure and dynamics of the field, especially its free energy, has long been a central objective in Heliophysics. The main obstacle to achieving this understanding has been the lack of accurate direct measurements of the coronal field. Most attempts to determine the magnetic free energy have relied on extrapolation of photospheric measurements, a notoriously unreliable procedure. In this presentation I will discuss what measurements of the coronal field would be most effective for understanding solar activity. Not surprisingly, the key process for driving solar activity is magnetic reconnection. I will discuss, therefore, how next-generation measurements of the coronal field will allow us to understand not only the origins of space weather, but also one of the most important fundamental processes in cosmic and laboratory plasmas.

Antiochos, S. K.↗
NASA NTRS2012

Composite Wavelet Filters for Enhanced Automated Target Recognition

Automated Target Recognition (ATR) systems aim to automate target detection, recognition, and tracking. The current project applies a JPL ATR system to low-resolution sonar and camera videos taken from unmanned vehicles. These sonar images are inherently noisy and difficult to interpret, and pictures taken underwater are unreliable due to murkiness and inconsistent lighting. The ATR system breaks target recognition into three stages: 1) Videos of both sonar and camera footage are broken into frames and preprocessed to enhance images and detect Regions of Interest (ROIs). 2) Features are extracted from these ROIs in preparation for classification. 3) ROIs are classified as true or false positives using a standard Neural Network based on the extracted features. Several preprocessing, feature extraction, and training methods are tested and discussed in this paper.

automated target recognition↗
NASA NTRS2012

On Applications of Disruption Tolerant Networking to Optical Networking in Space

The integration of optical communication links into space networks via Disruption Tolerant Networking (DTN) is a largely unexplored area of research. Building on successful foundational work accomplished at JPL, we discuss a multi-hop multi-path network featuring optical links. The experimental test bed is constructed at the NASA Glenn Research Center featuring multiple Ethernet-to-fiber converters coupled with free space optical (FSO) communication channels. The test bed architecture models communication paths from deployed Mars assets to the deep space network (DSN) and finally to the mission operations center (MOC). Reliable versus unreliable communication methods are investigated and discussed; including reliable transport protocols, custody transfer, and fragmentation. Potential commercial applications may include an optical communications infrastructure deployment to support developing nations and remote areas, which are unburdened with supporting an existing heritage means of telecommunications. Narrow laser beam widths and control of polarization states offer inherent physical layer security benefits with optical communications over RF solutions. This paper explores whether or not DTN is appropriate for space-based optical networks, optimal payload sizes, reliability, and a discussion on security.

Hylton, Alan Guy↗
NASA NTRS2013

Work Practice Simulation of Complex Human-Automation Systems in Safety Critical Situations: The Brahms Generalized berlingen Model

The transition from the current air traffic system to the next generation air traffic system will require the introduction of new automated systems, including transferring some functions from air traffic controllers to on­-board automation. This report describes a new design verification and validation (V&V) methodology for assessing aviation safety. The approach involves a detailed computer simulation of work practices that includes people interacting with flight-critical systems. The research is part of an effort to develop new modeling and verification methodologies that can assess the safety of flight-critical systems, system configurations, and operational concepts. The 2002 Ueberlingen mid-air collision was chosen for analysis and modeling because one of the main causes of the accident was one crew's response to a conflict between the instructions of the air traffic controller and the instructions of TCAS, an automated Traffic Alert and Collision Avoidance System on-board warning system. It thus furnishes an example of the problem of authority versus autonomy. It provides a starting point for exploring authority/autonomy conflict in the larger system of organization, tools, and practices in which the participants' moment-by-moment actions take place. We have developed a general air traffic system model (not a specific simulation of Überlingen events), called the Brahms Generalized Ueberlingen Model (Brahms-GUeM). Brahms is a multi-agent simulation system that models people, tools, facilities/vehicles, and geography to simulate the current air transportation system as a collection of distributed, interactive subsystems (e.g., airports, air-traffic control towers and personnel, aircraft, automated flight systems and air-traffic tools, instruments, crew). Brahms-GUeM can be configured in different ways, called scenarios, such that anomalous events that contributed to the Überlingen accident can be modeled as functioning according to requirements or in an anomalous condition, as occurred during the accident. Brahms-GUeM thus implicitly defines a class of scenarios, which include as an instance what occurred at Überlingen. Brahms-GUeM is a modeling framework enabling "what if" analysis of alternative work system configurations and thus facilitating design of alternative operations concepts. It enables subsequent adaption (reusing simulation components) for modeling and simulating NextGen scenarios. This project demonstrates that BRAHMS provides the capacity to model the complexity of air transportation systems, going beyond idealized and simple flights to include for example the interaction of pilots and ATCOs. The research shows clearly that verification and validation must include the entire work system, on the one hand to check that mechanisms exist to handle failures of communication and alerting subsystems and/or failures of people to notice, comprehend, or communicate problematic (unsafe) situations; but also to understand how people must use their own judgment in relating fallible systems like TCAS to other sources of information and thus to evaluate how the unreliability of automation affects system safety. The simulation shows in particular that distributed agents (people and automated systems) acting without knowledge of each others' actions can create a complex, dynamic system whose interactive behavior is unexpected and is changing too quickly to comprehend and control.

complex systems↗
NASA NTRS2013

Service Oriented Robotic Architecture for Space Robotics: Design, Testing, and Lessons Learned

This paper presents the lessons learned from six years of experiments with planetary rover prototypes running the Service Oriented Robotic Architecture (SORA) developed by the Intelligent Robotics Group (IRG) at the NASA Ames Research Center. SORA relies on proven software engineering methods and technologies applied to space robotics. Based on a Service Oriented Architecture and robust middleware, SORA encompasses on-board robot control and a full suite of software tools necessary for remotely operated exploration missions. SORA has been eld tested in numerous scenarios of robotic lunar and planetary exploration. The experiments conducted by IRG with SORA exercise a large set of the constraints encountered in space applications: remote robotic assets, ight relevant science instruments, distributed operations, high network latencies and unreliable or intermittent communication links. In this paper, we present the results of these eld tests in regard to the developed architecture, and discuss its bene ts and limitations.

service oriented architecture↗
NASA NTRS2015

3D-Laser-Scanning Technique Applied to Bulk Density Measurements of Apollo Lunar Samples

In order to better interpret gravimetric data from orbiters such as GRAIL and LRO to understand the subsurface composition and structure of the lunar crust, it is import to have a reliable database of the density and porosity of lunar materials. To this end, we have been surveying these physical properties in both lunar meteorites and Apollo lunar samples. To measure porosity, both grain density and bulk density are required. For bulk density, our group has historically utilized sub-mm bead immersion techniques extensively, though several factors have made this technique problematic for our work with Apollo samples. Samples allocated for measurement are often smaller than optimal for the technique, leading to large error bars. Also, for some samples we were required to use pure alumina beads instead of our usual glass beads. The alumina beads were subject to undesirable static effects, producing unreliable results. Other investigators have tested the use of 3d laser scanners on meteorites for measuring bulk volumes. Early work, though promising, was plagued with difficulties including poor response on dark or reflective surfaces, difficulty reproducing sharp edges, and large processing time for producing shape models. Due to progress in technology, however, laser scanners have improved considerably in recent years. We tested this technique on 27 lunar samples in the Apollo collection using a scanner at NASA Johnson Space Center. We found it to be reliable and more precise than beads, with the added benefit that it involves no direct contact with the sample, enabling the study of particularly friable samples for which bead immersion is not possible

Macke, R. J.↗
NASA NTRS2015

Addressing Unison and Uniqueness of Reliability and Safety for Better Integration

For a long time, both in theory and in practice, safety and reliability have not been clearly differentiated, which leads to confusion, inefficiency, and sometime counter-productive practices in executing each of these two disciplines. It is imperative to address the uniqueness and the unison of these two disciplines to help both disciplines become more effective and to promote a better integration of the two for enhancing safety and reliability in our products as an overall objective. There are two purposes of this paper. First, it will investigate the uniqueness and unison of each discipline and discuss the interrelationship between the two for awareness and clarification. Second, after clearly understanding the unique roles and interrelationship between the two in a product design and development life cycle, we offer suggestions to enhance the disciplines with distinguished and focused roles, to better integrate the two, and to improve unique sets of skills and tools of reliability and safety processes. From the uniqueness aspect, the paper identifies and discusses the respective uniqueness of reliability and safety from their roles, accountability, nature of requirements, technical scopes, detailed technical approaches, and analysis boundaries. It is misleading to equate unreliable to unsafe, since a safety hazard may or may not be related to the component, sub-system, or system functions, which are primarily what reliability addresses. Similarly, failing-to-function may or may not lead to hazard events. Examples will be given in the paper from aerospace, defense, and consumer products to illustrate the uniqueness and differences between reliability and safety. From the unison aspect, the paper discusses what the commonalities between reliability and safety are, and how these two disciplines are linked, integrated, and supplemented with each other to accomplish the customer requirements and product goals. In addition to understanding the uniqueness in reliability and safety, a better understanding of unison and commonalities will further help in understanding the interaction between reliability and safety. This paper discusses the unison and uniqueness of reliability and safety. It presents some suggestions for better integration of the two disciplines in terms of technical approaches, tools, techniques, and skills to enhance the role of reliability and safety in supporting a product design and development life cycle. The paper also discusses eliminating the redundant effort and minimizing the overlap of reliability and safety analyses for an efficient implementation of the two disciplines.

Huang, Zhaofeng↗
NASA NTRS2012

Towards Reliable Evaluation of Anomaly-Based Intrusion Detection Performance

This report describes the results of research into the effects of environment-induced noise on the evaluation process for anomaly detectors in the cyber security domain. This research was conducted during a 10-week summer internship program from the 19th of August, 2012 to the 23rd of August, 2012 at the Jet Propulsion Laboratory in Pasadena, California. The research performed lies within the larger context of the Los Angeles Department of Water and Power (LADWP) Smart Grid cyber security project, a Department of Energy (DoE) funded effort involving the Jet Propulsion Laboratory, California Institute of Technology and the University of Southern California/ Information Sciences Institute. The results of the present effort constitute an important contribution towards building more rigorous evaluation paradigms for anomaly-based intrusion detectors in complex cyber physical systems such as the Smart Grid. Anomaly detection is a key strategy for cyber intrusion detection and operates by identifying deviations from profiles of nominal behavior and are thus conceptually appealing for detecting "novel" attacks. Evaluating the performance of such a detector requires assessing: (a) how well it captures the model of nominal behavior, and (b) how well it detects attacks (deviations from normality). Current evaluation methods produce results that give insufficient insight into the operation of a detector, inevitably resulting in a significantly poor characterization of a detectors performance. In this work, we first describe a preliminary taxonomy of key evaluation constructs that are necessary for establishing rigor in the evaluation regime of an anomaly detector. We then focus on clarifying the impact of the operational environment on the manifestation of attacks in monitored data. We show how dynamic and evolving environments can introduce high variability into the data stream perturbing detector performance. Prior research has focused on understanding the impact of this variability in training data for anomaly detectors, but has ignored variability in the attack signal that will necessarily affect the evaluation results for such detectors. We posit that current evaluation strategies implicitly assume that attacks always manifest in a stable manner; we show that this assumption is wrong. We describe a simple experiment to demonstrate the effects of environmental noise on the manifestation of attacks in data and introduce the notion of attack manifestation stability. Finally, we argue that conclusions about detector performance will be unreliable and incomplete if the stability of attack manifestation is not accounted for in the evaluation strategy.

cyber defense↗
NASA NTRS2011

Testing of a Composite Wavelet Filter to Enhance Automated Target Recognition in SONAR

Automated Target Recognition (ATR) systems aim to automate target detection, recognition, and tracking. The current project applies a JPL ATR system to low resolution SONAR and camera videos taken from Unmanned Underwater Vehicles (UUVs). These SONAR images are inherently noisy and difficult to interpret, and pictures taken underwater are unreliable due to murkiness and inconsistent lighting. The ATR system breaks target recognition into three stages: 1) Videos of both SONAR and camera footage are broken into frames and preprocessed to enhance images and detect Regions of Interest (ROIs). 2) Features are extracted from these ROIs in preparation for classification. 3) ROIs are classified as true or false positives using a standard Neural Network based on the extracted features. Several preprocessing, feature extraction, and training methods are tested and discussed in this report.

image processing↗