An official website of the United States government
The accurate detection of chemical agents promotes many national security and public safety goals, and robust chemical detection methods can prevent disasters and support effective response to incidents. Mass spectrometry is an important tool in detecting and identifying chemical agents. However, there are high costs and logistical challenges associated with acquiring sufficient lab-generated mass spectrometry data for training machine learning algorithms, including skilled personnel, sample preparation and analysis required for data generation. These high costs of mass spectrometry data collection hinder the development of machine learning and deep learning models to detect and identify chemical agents. Accordingly, the primary objective of our research is to create a mass spectrometry data generation model whose output (synthetic mass spectrometry data) would enhance the performance of downstream machine learning chemical classification models. Such a synthetic data generation model would reduce the need to generate costly real-world data, and provide additional training data to use in combination with lab-generated mass spectrometry data when training classifiers. Our approach is a novel combination of autoencoder-based synthetic data generation combined with a fixed, apriori defined hidden layer geometry. In particular, we train pairs of encoders and decoders with an additional loss term that enforces that the hidden layer passed from the encoder to the decoder match the embedding provided by an external deep learning model designed to predict functional properties of chemicals. We have verified that incorporating our synthetic spectra into a lab-generated dataset enhances the performance of classification algorithms compared to using only the real data. Our synthetic spectra have been successfully matched to lab-generated spectra for their respective chemicals using library matching software, further demonstrating the validity of our work.
more »
« less
Boundless: Generating photorealistic synthetic data for object detection in urban streetscapes
We introduce Boundless, a photo-realistic synthetic data generation system for enabling highly accurate object detection in dense urban streetscapes. Boundless can replace massive real-world data collection and manual groundtruth object annotation (labeling) with an automated and configurable process. Boundless is based on the Unreal Engine 5 (UE5) City Sample project with improvements enabling accurate collection of 3D bounding boxes across different lighting and scene variability conditions. We evaluate the performance of object detection models trained on the dataset generated by Boundless when used for inference on a real-world dataset acquired from medium-altitude cameras. We compare the performance of the Boundless-trained model against the CARLA-trained model and observe an improvement of 7.8 mAP. The results we achieved support the premise that synthetic data generation is a credible methodology for training/fine-tuning scalable object detection models for urban scenes.
more »
« less
- Award ID(s):
- 2148128
- PAR ID:
- 10582222
- Publisher / Repository:
- arXiv:2409.03022v2 [cs.CV]
- Date Published:
- Journal Name:
- arxiv
- ISSN:
- arXiv:2409.03022v2 [cs.CV]
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Arai, Igor (Ed.)This research explores practical applications of Transfer Learning and Spatial Attention mechanisms using pre-trained models from an open-source simulator, CARLA (Car Learning to Act). The study focuses on vehicle tracking using aerial images, utilizing transformers and graph algorithms for keypoint detection. The proposed detector training process optimizes model parameters without heavy reliance on manually set hyperparameters. The loss function considers both class distribution and position localization of ground truth data. The study utilizes a three-stage methodology: pre-trained model selection, fine-tuning with a custom synthetic dataset, and evaluation using real-world aerial datasets. The results demonstrate the effectiveness of our synthetic transformer-based transfer learning technique in enhancing object detection accuracy and localization. When tested with real-world images, our approach achieved an 88% detection, compared to only 30% when using YOLOv8. The findings underscore the advantages of incorporating graph-based loss functions in transfer learning and position-encoding techniques, demonstrating their effectiveness in realistic machine learning applications with unbalanced classes.more » « less
-
Kohei, Arai (Ed.)This research explores practical applications of Transfer Learning and Spatial Attention mechanisms using pre-trained models from an open-source simulator, CARLA (Car Learning to Act). The study focuses on vehicle tracking using aerial images, utilizing transformers and graph algorithms for keypoint detection. The proposed detector training process optimizes model parameters without heavy reliance on manually set hyperparameters. The loss function considers both class distribution and position localization of ground truth data. The study utilizes a three-stage methodology: pre-trained model selection, fine-tuning with a custom synthetic dataset, and evaluation using real-world aerial datasets. The results demonstrate the effectiveness of our synthetic transformer-based transfer learning technique in enhancing object detection accuracy and localization. When tested with real-world images, our approach achieved an 88% detection, compared to only 30% when using YOLOv8. The findings underscore the advantages of incorporating graph-based loss functions in transfer learning and position-encoding techniques, demonstrating their effectiveness in realistic machine learning applications with unbalanced classes.more » « less
-
We introduce Constellation, a dataset of 13K images suitable for research on detection of objects in dense urban streetscapes observed from high-elevation cameras, collected for a variety of temporal conditions. The dataset addresses the need for curated data to explore problems in small object detection exemplified by the limited pixel footprint of pedestrians observed tens of meters from above. It enables the testing of object detection models for variations in lighting, building shadows, weather, and scene dynamics. Weevaluate contemporary object detection architectures on the dataset, observing that state-of-the-art methods have lower performance in detecting small pedestrians compared to vehicles, corresponding to a 10% difference in average precision (AP). Using structurally similar datasets for pretraining the models results in an increase of 1.8% mean AP (mAP). We further find that incorporating domain-specific data augmentations helps improve model performance. Using pseudo-labeled data, obtained from inference outcomes of the best-performing models, improves the performance of the models. Finally, comparing the models trained using the data collected in two different time intervals, we find a performance drift in models due to the changes in intersection conditions over time. The best-performing model achieves a pedestrian AP of 92.0% with 11.5 ms inference time on NVIDIA A100 GPUs, and an mAP of 95.4%.more » « less
-
In this paper, an urban object detection system via unmanned aerial vehicles (UAVs) is developed to collect real-time traffic information, which can be further utilized in many applications such as traffic monitoring and urban traffic management. The system includes an object detection algorithm, deep learning model training, and deployment on a real UAV. For the object detection algorithm, the Mobilenet-SSD model is applied owing to its lightweight and efficiency, which make it suitable for real-time applications on an onboard microprocessor. For model training, federated learning (FL) is used to protect privacy and increase efficiency with parallel computing. Last, the FL-trained object detection model is deployed on a real UAV for real-time performance testing. The experimental results show that the object detection algorithm can reach a speed of 18 frames per second with good detection performance, which shows the real-time computation ability of a resource-limited edge device and also validates the effectiveness of the developed system.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
