SEARCH · Search NASA

Results for “object detection”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Glass Refraction Distortion Object Detection via Abstract Features

Glass reflection and refraction lead to missing and distorted object feature data, affecting the accuracy of object detection. In order to solve the above problems, this paper proposed a glass refraction distortion object detection via abstract features. The number of parameters of the algorithm is reduced by introducing skip connections and expansion modules with different expansion rates. The abstract feature information of the object is extracted by binary cross-entropy loss. Meanwhile, the abstract feature distance between the object domain and source domain is reduced by a loss function, which improves the accuracy of object detection under glass interference. To verify the effectiveness of the algorithm in this paper, the GRI dataset is produced and made public on GitHub. The algorithm of this paper is compared with the current state-of-the-art Deep Face, VGG Face, TBE-CNN, DA-GAN, PEN-3D, LMZMPM, and the average detection accuracy of our algorithm is 92.57% at the highest, and the number of parameters is only 5.13 M.

Cai, Lei↗

DOE OSTI2022

An Application of Faster R-CNNs in Object Detection Efforts Applied to the Critical Infrastructure Domain

Object detection and segmentation approaches have been successfully applied to multiple interdisciplinary domains ranging from medical imaging to autonomous vehicles. The following study details efforts to apply segmentation methods to the critical infrastructure domain. Specifically, the identification of critical sub-components of four facilities: airports, hospitals, hydroelectric dams, and water treatment plants. Data for this study was extracted from the U.S. Department of Agriculture’s National Agriculture Imagery Program data set. Each facility class was considered independently of the other facilities, producing four different segmentation models during the testing and training process. Ultimately, the study team concluded there are significant challenges associated with object detection modeling when applied to facility analysis within the critical infrastructure domain. The study team was able to identify possible sources of these challenges that could be potentially addressed in future work.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Concept Study of Robotic Camera-Based Foreign Object Detection for EV Wireless Charging

Wireless charging of an electric vehicle (EV) is an emerging charging technology promising convenient, autonomous, and highly efficient EV charging without requiring heavy gauge cables. However, due to the strong electromagnetic field created by this process that surrounds the wireless charger, the presence of foreign objects can detrimentally interact with it, thus affecting wireless power transfer (WPT) performance or leading to harmful and unwanted safety risks. This paper presents the results for a concept study on a robotic camera-based foreign object detection (FOD) system, as a supplement to the industry-existing overlapped FOD coil array method, for EV wireless charging. A Raspberry PI 4 control board and compatible Raspberry PI Camera Module 2 are used to implement camera-based object detection. The FOD program was developed using a state-of-the-art deep learning object detection model with the OpenCV and Pytorch library and is compatible with camera module hardware. A dry-run test with Raspberry PI and a camera module was conducted and the preliminary FOD function was verified. The feasibility assessment is also validated by comparing the performance of five existing state-of-the-art deep learning object detection models for vehicles, animals, persons, and metals subsets, respectively. Satisfactory performance on the benchmark datasets is observed by the tests, but further improvements are needed in future work when detecting small-sized metallic objects. A programable robotic car is also under development as ongoing work for carrying the Raspberry PI and camera module while moving for the maintenance process.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Event-to-Video Conversion for Overhead Object Detection

Collecting overhead imagery using an event camera is desirable due to the energy efficiency of the image sensor compared to standard cameras. However, event cameras complicate downstream image processing, especially for complex tasks such as object detection. In this paper, we investigate the viability of event streams for overhead object detection. We demonstrate that across a number of standard modeling approaches, there is a significant gap in performance between dense event representations and corresponding RGB frames. We establish that this gap is, in part, due to a lack of overlap between the event representations and the pre-training data that the object detectors were initially trained on through a number of experiments. Then, apply an off-the-shelf event-to-video conversion tool that converts event streams into gray-scale video to close this gap. We demonstrate that this approach results in a large performance increase, outperforming even event-specific object detection techniques on our overhead target task. These results suggest that better aligning event representations with existing large pre-trained models may result in greater short-term performance gains compared to end-to-end event-specific architectural improvements.

machine learning (ML), computer vision, Neuromorph↗

DOE OSTI2018

Real-time object detection, tracking and occlusion reasoning

A system for object detection and tracking includes technologies to, among other things, detect and track moving objects, such as pedestrians and/or vehicles, in a real-world environment, handle static and dynamic occlusions, and continue tracking moving objects across the fields of view of multiple different cameras.

47 OTHER INSTRUMENTATION↗

DOE OSTI2017

Statistical Hypothesis Testing using CNN Features for Synthesis of Adversarial Counterexamples to Human and Object Detection Vision Systems

Validating the correctness of human detection vision systems is crucial for safety applications such as pedestrian collision avoidance in autonomous vehicles. The enormous space of possible inputs to such an intelligent system makes it difficult to design test cases for such systems. In this report, we present our tool MAYA that uses an error model derived from a convolutional neural network (CNN) to explore the space of images similar to a given input image, and then tests the correctness of a given human or object detection system on such perturbed images. We demonstrate the capability of our tool on the pre-trained Histogram-of-Oriented-Gradients (HOG) human detection algorithm implemented in the popular OpenCV toolset and the Caffe object detection system pre-trained on the ImageNet benchmark. Our tool may serve as a testing resource for the designers of intelligent human and object detection systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

AEPF: Attention-Enabled Point Fusion for 3D Object Detection

Current state-of-the-art (SOTA) LiDAR-only detectors perform well for 3D object detection tasks, but point cloud data are typically sparse and lacks semantic information. Detailed semantic information obtained from camera images can be added with existing LiDAR-based detectors to create a robust 3D detection pipeline. With two different data types, a major challenge in developing multi-modal sensor fusion networks is to achieve effective data fusion while managing computational resources. With separate 2D and 3D feature extraction backbones, feature fusion can become more challenging as these modes generate different gradients, leading to gradient conflicts and suboptimal convergence during network optimization. To this end, we propose a 3D object detection method, Attention-Enabled Point Fusion (AEPF). AEPF uses images and voxelized point cloud data as inputs and estimates the 3D bounding boxes of object locations as outputs. An attention mechanism is introduced to an existing feature fusion strategy to improve 3D detection accuracy and two variants are proposed. These two variants, AEPF-Small and AEPF-Large, address different needs. AEPF-Small, with a lightweight attention module and fewer parameters, offers fast inference. AEPF-Large, with a more complex attention module and increased parameters, provides higher accuracy than baseline models. Experimental results on the KITTI validation set show that AEPF-Small maintains SOTA 3D detection accuracy while inferencing at higher speeds. AEPF-Large achieves mean average precision scores of 91.13, 79.06, and 76.15 for the car class’s easy, medium, and hard targets, respectively, in the KITTI validation set. Results from ablation experiments are also presented to support the choice of model architecture.

Chemistry↗

DOE OSTI2017

Faint Object Detection in Multi-Epoch Observations via Catalog Data Fusion

Astronomy in the time-domain era faces several new challenges. One of them is the efficient use of observations obtained at multiple epochs. The work presented here addresses faint object detection and describes an incremental strategy for separating real objects from artifacts in ongoing surveys. The idea is to produce low-threshold single-epoch catalogs and to accumulate information across epochs. This is in contrast to more conventional strategies based on co-added or stacked images. We adopt a Bayesian approach, addressing object detection by calculating the marginal likelihoods for hypotheses asserting that there is no object or one object in a small image patch containing at most one cataloged source at each epoch. The object-present hypothesis interprets the sources in a patch at different epochs as arising from a genuine object; the no-object hypothesis interprets candidate sources as spurious, arising from noise peaks. We study the detection probability for constant-flux objects in a Gaussian noise setting, comparing results based on single and stacked exposures to results based on a series of single-epoch catalog summaries. Our procedure amounts to generalized cross-matching: it is the product of a factor accounting for the matching of the estimated fluxes of the candidate sources and a factor accounting for the matching of their estimated directions. We find that probabilistic fusion of multi-epoch catalogs can detect sources with similar sensitivity and selectivity compared to stacking. The probabilistic cross-matching framework underlying our approach plays an important role in maintaining detection sensitivity and points toward generalizations that could accommodate variability and complex object structure.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2024

Exploring Object Detection and Image Classification Tasks for Niche Use Case in Naturalistic Driving Studies

Naturalistic driving studies consist of drivers using their personal vehicles and provide valuable real-world data, but privacy issues must be handled very carefully. Drivers sign a consent form when they elect to participate, but passengers do not for a variety of practical reasons. However, their privacy must still be protected. One large study includes a blurred image of the entire cabin which allows reviewers to find passengers in the vehicle; this protects the privacy but still allows a means of answering questions regarding the impact of passengers on driver behavior. A method for automatically counting the passengers would have scientific value for transportation researchers. We investigated different image analysis methods for automatically locating and counting the non-drivers including simple face detection and fine-tuned methods for image classification and a published object detection method. We also compared the image classification using convolutional neural network and vision transformer backbones. Our studies show the image classification method appears to work the best in terms of absolute performance, although we note the closed nature of our dataset and nature of the imagery makes the application somewhat niche and object detection methods also have advantages. We perform some analysis to support our conclusion.

Peruski, Ryan↗

DOE OSTI2020

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Block segmentation in feature space for realtime object detection in high granularity images

Computer vision has applications in object detection, image recognition and classification, and object tracking. One of the challenges of computer vision is the presence of useful information at multiple distance scales. Filtering techniques may sacrifice details at small scales in order to prioritize the analysis of large-scale features of the image. We present a strategy for coarse-graining multidimensional data while maintaining fine-grained detail for subsequent analysis. The algorithm is based on fixed-size block segmentation in the feature space. We apply this strategy to solve the long-standing challenge of detecting particle trajectories at the Large Hadron Collider in real time.

Computer vision↗

DOE OSTI2013

Real-Time Vehicle-Mounted Multistatic Ground Penetrating Radar Imaging System for Buried Object Detection

A multistatic ground penetrating radar system is described, capable of real-time imaging and object detection. The radar consists of 16 transmitter and receiver pairs mounted across the front of a vehicle. The transmitters operate sequentially with all receivers activated for each transmit pulse. The resulting frame of 256 multistatic time signals is processed into an image using a tomographic reconstruction technique. In this paper we describe the system architecture, signal conditioning, and reconstruction algorithm for producing a sequence of images in real time as the vehicle travels across the ground. We demonstrate a robust image post-processing method that separates the bright spot corresponding to the dominant buried object in an image frame from the background. This is essential before calculating an energy-based statistic for automatic detection of buried objects. This spot ratio detection statistic, based on energy both inside and outside the spot, is shown to be not only more stationary than spot energy (i.e. mostly free of localized trends due to changing ground conditions), but also more powerful as a detection statistic. Finally, we demonstrate that multistatic imaging significantly improves the detection performance over more conventional monostatic array processing.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2015

WE-G-204-05: Relative Object Detectability Evaluation of a New High Resolution A-Se Direct Detection System Compared to Indirect Micro-Angiographic Fluoroscopic (MAF) Detectors

Purpose: To evaluate the task specific imaging performance of a new 25µm pixel pitch, 1000µm thick amorphous selenium direct detection system with CMOS readout for typical angiographic exposure parameters using the relative object detectability (ROD) metric. Methods: The ROD metric uses a simulated object function weighted at each spatial frequency by the detectors’ detective quantum efficiency (DQE), which is an intrinsic performance metric. For this study, the simulated objects were aluminum spheres of varying diameter (0.05–0.6mm). The weighted object function is then integrated over the full range of detectable frequencies inherent to each detector, and a ratio is taken of the resulting value for two detectors. The DQE for the 25µm detector was obtained from a simulation of a proposed a-Se detector using an exposure of 200µR for a 50keV x-ray beam. This a-Se detector was compared to two microangiographic fluoroscope (MAF) detectors [the MAF-CCD with pixel size of 35µm and Nyquist frequency of 14.2 cycles/mm and the MAF-CMOS with pixel size of 75µm and Nyquist frequency of 6.6 cycles/mm] and a standard flat-panel detector (FPD with pixel size of 194µm and Nyquist frequency of 2.5cycles/mm). Results: ROD calculations indicated vastly superior performance by the a-Se detector in imaging small aluminum spheres. For the 50µm diameter sphere, the ROD values for the a-Se detector compared to the MAF-CCD, the MAF-CMOS, and the FPD were 7.3, 9.3 and 58, respectively. Detector performance in the low frequency regime was dictated by each detector’s DQE(0) value. Conclusion: The a-Se with CMOS readout is unique and appears to have distinctive advantages of incomparable high resolution, low noise, no readout lag, and expandable design. The a-Se direct detection system will be a powerful imaging tool in angiography, with potential break-through applications in diagnosis and treatment of neuro-vascular disease. Supported by NIH Grant: 2R01EB002873 and an equipment grant from Toshiba Medical Systems Corporation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

Towards automated and real-time multi-object detection of anguilliform fishes from sonar data using YOLOv8 deep learning algorithm

Eels (Anguilla spp.), including American eels (Anguilla rostrata), European eels (Anguilla anguilla), and Japanese eels (Anguilla japonica), are species of critical management and regulatory concern due to their vulnerability to various stressors during downstream migrations. Accurate and efficient detection of migrating eels can improve our understanding of fish behaviors and fish-hydraulic structure interactions, thereby facilitating the design, operation, and optimization of more effective downstream passage facilities from both biological and economic perspectives. However, a real-time, automated framework for detecting migrating eels in real-world applications is currently lacking. Leveraging imaging sonar as a reliable technology for fish passage monitoring, field data are acquired using imaging sonar and then converted to single sonar frames/images for subsequent analysis. In this study, a framework based on the You Only Look Once Version 8 (YOLOv8)-based convolutional neural network is proposed for multi-object detection of eels and non-eel fish using the sonar images after image subtraction and additional wavelet denoising. The results from both training and testing phases demonstrate that the framework's ability can successfully detect both eels and non-eel fish in preprocessed sonar images, achieving F1-scores and mAP@0.50 exceeding 0.84. Additionally, the incorporation of wavelet denoising during preprocessing slightly improve detection performance. Furthermore, the transferability of this framework from eel to lamprey detection is demonstrated to be feasible given the similar morphological characteristics of these two species. Overall, the proposed framework achieves accurate and efficient detection of migrating eels, providing reliable and real-time information that can help conserve vulnerable eel and eel-like populations.

Deep learning↗

DOE OSTI2014

Buried object detection in GPR images

A method and system for detecting the presence of subsurface objects within a medium is provided. In some embodiments, the imaging and detection system operates in a multistatic mode to collect radar return signals generated by an array of transceiver antenna pairs that is positioned across the surface and that travels down the surface. The imaging and detection system pre-processes the return signal to suppress certain undesirable effects. The imaging and detection system then generates synthetic aperture radar images from real aperture radar images generated from the pre-processed return signal. The imaging and detection system then post-processes the synthetic aperture radar images to improve detection of subsurface objects. The imaging and detection system identifies peaks in the energy levels of the post-processed image frame, which indicates the presence of a subsurface object.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2014

Real-time system for imaging and object detection with a multistatic GPR array

47 OTHER INSTRUMENTATION↗

DOE OSTI2018

System for detecting objects in streaming 3D images formed from data acquired with a medium penetrating sensor

A detection system that detects subsurface objects within a medium and estimates various features of the objects is provided. The detection system receives a streaming sequence of image frames of the medium at various along-medium locations. An image frame contains voxel values (intensities) representing characteristics of the medium across the medium and in the depth (range) direction. The detection system depth-compensates the intensities for determining which voxels are part of an object using an unsupervised binary classifier. The detection system then connects object voxels into distinct objects and recursively estimates the features of those objects as the image frames stream based on the locations and intensities of the object voxels.

Paglieroni, David W.↗

DOE OSTI2024

Object Detection and Recognition with PointPillars in LiDAR Point Clouds – Comparisions

In the field of autonomous systems, neural networks have been leveraged for object detection and recognition in 2-dimensional images captured by cameras. Other types of sensors are available for sensing surroundings, including LiDAR sensors, and corresponding networks have been developed to perform detection and recognition in the point clouds generated by these sensors. The approaches are similar, both perform convolutions, but have distinct characteristics and challenges. In designing and configuring autonomous systems, a variety of LiDAR sensors are available, along with configurable deep neural networks to leverage their data. This work presents a review of the PointPillars network, an evolution of the seminal PointNet, comparing accuracy and training time relative to different LiDAR sensors, network and training parameters, CPU and GPU hardware, and the criticality of the use of reflective intensity as a feature. The value of using reflectivity as a predictive feature is explored and quantified to determine if it makes a significant difference in accuracy of the PointPillars network. Two separate LiDAR sensors are utilized, a 16-plane and a 32-plane, and corresponding accuracies and training times with the PointPillars network are evaluated.

LiDAR, machine learning, neural network, object re↗