This paper presents a comprehensive evaluation of YOLO architectures for smoke and wildfire detection, including YOLOv5, YOLOv6, YOLOv7, YOLOv8, and YOLO-NAS. We aim to assess their effectiveness in ...early detection of wildfires. The Foggia dataset is used for this, and performance metrics such as Recall, Precision, F1-score, and mean Average Precision are employed. Our methodology trains each architecture for 300 epochs, focusing on recall for its relevance in this area. The 'best models' are evaluated on the Foggia test set and further tested with a challenging, custom-assembled dataset from independent online sources to assess real-world performance. Results show that YOLOv5, YOLOv7, and YOLOv8 exhibit a balanced performance across all metrics in both validation and testing. YOLOv6 performs slightly lower in recall during validation but achieves a good balance on testing. YOLO-NAS variants excel in recall, making them suitable for minimizing missed detections. However, precision performance is lower for YOLO-NAS models. Visual results demonstrate that top-performing models accurately identify most instances in the test set. However, they struggle with distant scenes and poor lighting conditions, occasionally detecting false positives. In favorable conditions, the models perform well in identifying relevant instances. We conclude that no single model excels in all aspects of smoke and wildfire detection. The choice of model depends on specific application requirements, considering accuracy, recall, and inference time. This research enriches the field of computer vision for smoke and wildfire detection, laying a foundation for system enhancements and serving as a basis for future research to optimize detection effectiveness.
Significance: To expand our understanding of the roles of astrocytes in neural circuits, there is a need to develop optical tools tailored specifically to capture their complex spatiotemporal Ca2 + ... dynamics. This interest is not limited to 2D, but to multiple depths.
Aim: The focus of our work was to design and evaluate the optical performance of an enhanced version of a two-photon (2P) microscope with the addition of a deformable mirror (DM)-based axial scanning system for live mammalian brain imaging.
Approach: We used a DM to manipulate the beam wavefront by applying different defocus terms to cause a controlled axial shift of the image plane. The optical design and performance were evaluated by an analysis of the optical model, followed by an experimental characterization of the implemented instrument.
Results: Key questions related to this instrument were addressed, including impact of the DM curvature change on vignetting, field of view size, image plane flatness, wavefront error, and point spread function. The instrument was used for imaging several neurobiological samples at different depths, including fixed brain slices and in vivo mouse cerebral cortex.
Conclusions: Our implemented instrument was capable of recording z-stacks of 53 μm in depth with a fine step size, parameters that make it useful for astrocyte biology research. Future work includes adaptive optics and intensity normalization.
In this study, we extensively evaluated the viability of the state-of-the-art YOLOv8 architecture for object detection tasks, specifically tailored for smoke and wildfire identification with a focus ...on agricultural and environmental safety. All available versions of YOLOv8 were initially fine-tuned on a domain-specific dataset that included a variety of scenarios, crucial for comprehensive agricultural monitoring. The ‘large’ version (YOLOv8l) was selected for further hyperparameter tuning based on its performance metrics. This model underwent a detailed hyperparameter optimization using the One Factor At a Time (OFAT) methodology, concentrating on key parameters such as learning rate, batch size, weight decay, epochs, and optimizer. Insights from the OFAT study were used to define search spaces for a subsequent Random Search (RS). The final model derived from RS demonstrated significant improvements over the initial fine-tuned model, increasing overall precision by 1.39 %, recall by 1.48 %, F1-score by 1.44 %, mAP@0.50 by 0.70 %, and mAP@0.50:0.95 by 5.09 %. We validated the enhanced model's efficacy on a diverse set of real-world images, reflecting various agricultural settings, to confirm its robustness in detecting smoke and fire. These results underscore the model's reliability and effectiveness in scenarios critical to agricultural safety and environmental monitoring. This work, representing a significant advancement in the field of fire and smoke detection through machine learning, lays a strong foundation for future research and solutions aimed at safeguarding agricultural areas and natural environments.
ABSTRACT Detection and characterization of exo-Earths require direct imaging techniques that can deliver contrast ratios of 1010 at 100 mas or smaller angular separation. At the same time, ...astrometric data is required to measure planet masses and to help detect planets and constrain their orbital parameters. To minimize costs, a single space mission can be designed using a high-efficiency coronagraph to perform direct imaging and a diffractive pupil to calibrate wide field distortions to enable high-precision astrometric measurements. This article reports the testing of a diffractive pupil on the high-contrast test bed at the NASA Ames Research Center to assess the compatibility of using a diffractive pupil with coronagraphic imaging systems. No diffractive contamination was found within our detectability limit of 2 × 10-7 contrast outside a region of 12 λ/D and 2.5 × 10-6 within a region spanning from 2 to 12 λ/D. Morphology of the image features suggests that no contamination exists even beyond the detectability limit specified or at smaller working angles. In the case that diffractive contamination is found beyond these stated levels, active wavefront control would be able to mitigate its intensity to 10-7 or better contrast.
At a distance of ∼2 pc, our nearest brown dwarf neighbor, Luhman 16 AB, has been extensively studied since its discovery 3 years ago, yet its most fundamental parameter-the masses of the individual ...dwarfs-has not been constrained with precision. In this work, we present the full astrometric orbit and barycentric motion of Luhman 16 AB and the first precision measurements of the individual component masses. We draw upon archival observations spanning 31 years from the European Southern Observatory (ESO) Schmidt Telescope, the Deep Near-Infrared Survey of the Southern Sky (DENIS), public FORS2 data on the Very Large Telescope (VLT), and new astrometry from the Gemini South Multiconjugate Adaptive Optics System (GeMS). Finally, we include three radial velocity measurements of the two components from VLT/CRIRES, spanning one year. With this new data sampling a full period of the orbit, we use a Markov chain Monte Carlo algorithm to fit a 16-parameter model incorporating mutual orbit and barycentric motion parameters and constrain the individual masses to be for the T dwarf and for the L dwarf. Our measurements of Luhman 16 AB's mass ratio and barycentric motion parameters are consistent with previous estimates in the literature utilizing recent astrometry only. The GeMS-derived measurements of the Luhman 16 AB separation in 2014-2015 agree closely with Hubble Space Telescope (HST) measurements made during the same epoch, and the derived mutual orbit agrees with those measurements to within the HST uncertainties of 0.3-0.4 mas.
High-precision astrometry can identify exoplanets and measure their orbits and masses while coronagraphic imaging enables detailed characterization of their physical properties and atmospheric ...compositions through spectroscopy. In a previous paper, we showed that a diffractive pupil telescope (DPT) in space can enable sub-muas accuracy astrometric measurements from wide-field images by creating faint but sharp diffraction spikes around the bright target star. The DPT allows simultaneous astrometric measurement and coronagraphic imaging, and we discuss and quantify in this paper the scientific benefits of this combination for exoplanet science investigations: identification of exoplanets with increased sensitivity and robustness, and ability to measure planetary masses to high accuracy. We show how using both measurements to identify planets and measure their masses offers greater sensitivity and provides more reliable measurements than possible with separate missions, and therefore results in a large gain in mission efficiency. The combined measurements reliably identify potentially habitable planets in multiple systems with a few observations, while astrometry or imaging alone would require many measurements over a long time baseline. In addition, the combined measurement allows direct determination of stellar masses to percent-level accuracy, using planets as test particles. We also show that the DPT maintains the full sensitivity of the telescope for deep wide-field imaging, and is therefore compatible with simultaneous scientific observations unrelated to exoplanets. We conclude that astrometry, coronagraphy, and deep wide-field imaging can be performed simultaneously on a single telescope without significant negative impact on the performance of any of the three techniques.
Astrometry is a promising exoplanet detection and characterization technique that can detect earth-size exoplanets if submicroarcsecond precision is achieved. However, instrumentation available today ...can only reach in the order of 102 microarcseconds, mainly limited by long-term dynamic distortions on wide-field observations. To overcome this problem, we propose the implementation of a diffractive pupil, which has an array of microscopic dots imprinted on the primary mirror coating. The dots create diffractive spikes on the focal plane that are used to calibrate image plane distortions that degrade the astrometric measurement precision. This astrometry technique can be utilized simultaneously with coronagraphy for exhaustive characterization of exoplanets (mass, spectra, orbit). We designed and built an astrometry laboratory to validate the diffractive pupil ability to calibrate distortions and stabilize wide-field astrometric measurements over time. We achieved a precision of 0.0123 px, which represents 42% of the 0.0288 px stability measured for this setup before the calibration. On sky units, this result is equivalent to 3.42 × 10-3λ/D that corresponds to 150 μas for a 2.4 m telescope at 500 nm wavelength. Also, at large field angles the distortion error was reduced by a factor of 5 when the calibration was used, proving its effectiveness for large field of view. We present an astrometry error budget here to explain the source of the residual error observed when the diffractive pupil calibration is used.