Object detection, as a fundamental task in computer vision, has been developed enormously, but is still challenging work, especially for Unmanned Aerial Vehicle (UAV) perspective due to small scale of the target. In this study, the authors develop a special detection method for small objects in UAV perspective. Based on YOLOv3, the Resblock in darknet is first optimized by concatenating two ResNet units that have the same width and height. Then, the entire darknet structure is improved by increasing convolution operation at an early layer to enrich spatial information. Both these two optimizations can enlarge the receptive filed. Furthermore, UAV-viewed dataset is collected to UAV perspective or small object detection. An optimized training method is also proposed based on collected UAV-viewed dataset. The experimental results on public dataset and our collected UAV-viewed dataset show distinct performance improvement on small object detection with keeping the same level performance on normal dataset, which means our proposed method adapts to different kinds of conditions.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7218847 | PMC |
| http://dx.doi.org/10.3390/s20082238 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Optimization of x-ray dark-field CT for human-scale lung imaging.
Med Phys
January 2025
Department of Engineering Physics, Tsinghua University, Beijing, China.
Background: X-ray grating-based dark-field imaging can sense the small angle scattering caused by object's micro-structures. This technique is sensitive to the porous microstructure of lung alveoli and has the potential to detect lung diseases at an early stage. Up to now, a human-scale dark-field CT (DF-CT) prototype has been built for lung imaging.
View Article and Find Full Text PDFBinocular stereo vision-based relative positioning algorithm for drone swarm.
Sci Rep
January 2025
School of Air Traffic Management, Civil Aviation Flight University of China, Guanghan, 618300, China.
To address the challenges of high computational complexity and poor real-time performance in binocular vision-based Unmanned Aerial Vehicle (UAV) formation flight, this paper introduces a UAV localization algorithm based on a lightweight object detection model. Firstly, we optimized the YOLOv5s model using lightweight design principles, resulting in Yolo-SGN. This model achieves a 65.
View Article and Find Full Text PDFTriboelectric sensor gloves for real-time behavior identification and takeover time adjustment in conditionally automated vehicles.
Nat Commun
January 2025
Department of Traffic Management School, People's Public Security University of China, Beijing, 100038, China.
The takeover issue, especially the setting of the takeover time budget, is a critical factor restricting the implementation and development of conditionally automated vehicles. The general fixed takeover time budget has certain limitations, as it does not take into account the driver's non-driving behaviors. Here, we propose an intelligent takeover assistance system consisting of all-round sensing gloves, a non-driving behavior identification module, and a takeover time budget determination module.
View Article and Find Full Text PDFHuman-like face pareidolia emerges in deep neural networks optimized for face and object recognition.
PLoS Comput Biol
January 2025
Department of Experimental Psychology, Justus Liebig University Giessen, Giessen, Germany.
The human visual system possesses a remarkable ability to detect and process faces across diverse contexts, including the phenomenon of face pareidolia--seeing faces in inanimate objects. Despite extensive research, it remains unclear why the visual system employs such broadly tuned face detection capabilities. We hypothesized that face pareidolia results from the visual system's optimization for recognizing both faces and objects.
View Article and Find Full Text PDFQuanFormer: A Transformer-Based Precise Peak Detection and Quantification Tool in LC-MS-Based Metabolomics.
Anal Chem
January 2025
State Key Laboratory of Cellular Stress Biology, Institute of Artificial Intelligence, School of Life Sciences, Faculty of Medicine and Life Sciences, National Institute for Data Science in Health and Medicine, XMU-HBN skin biomedical research center, Xiamen University, Xiamen, Fujian 361102, China.
In metabolomic analysis based on liquid chromatography coupled with mass spectrometry, detecting and quantifying intricate objects is a massive job. Current peak picking methods still cause high rates of incorrectly picked peaks to influence the reliability and reproducibility of results. To address these challenges, we developed QuanFormer, a deep learning method based on object detection designed to accurately quantify peak signals.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!