Vehicle detection in aerial imagery : A small target detection benchmark

By Sébastien Razakarivony, Frédéric Jurie. Journal of Visual Communication and Image Representation, 2016

821 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f5dda7e255bd57923f7b009c47cfb94605434d9c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning from imbalanced data: open challenges and future directions (2016, background): “Target detection [45] Classification of specified targets appearing with varied frequency (multi-class problem)”
Object Detection in 20 Years: A Survey (2019, background): “VeDAI [89] 2016 Consists of ∼1,200 images (0.”
Tiny Object Detection in Aerial Images (2021, background): “, VEDAI [18] and R(2)-CNN [4]), VEDAI only focuses on vehicle detection, and dataset in R(2)-CNN is not publicly available.”
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, methodology): “…segmentation in natural scenes and remote sensing scenes respectively, the DOTA [57] and DIOR [29] datasets are proposed for generic object detection in remote sensing images, and the FGSD [4] and VEDAI [39] datasets inspire the research of ﬁne-grained object detection in remote sensing images.”
Vision Meets Drones: A Challenge (2018, neutral): “5k 640× 640 2014 VEDAI [18] satellite 1.”
SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery (2022, methodology): “The popular Vehicle Detection in Aerial Imagery (VEDAI) dataset [45] is used in the experiments, which contains cropped images obtained from the much larger Utah Automated Geographic Reference Center (AGRC) dataset.”
Cross-Modality Fusion Transformer for Multispectral Object Detection (2021, background): “On VEDAI.”
Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, background): “Despite VEDAI containing cross-modal scenarios, 186 it is a small dataset with few night scene images, which 187 results in it being less effective for detecting vehicles in dark 188 night.”
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning (2016, methodology): “Many approaches use less contemporary SVM and Boosting based methods, but apply contextual assistance such as road patch detection or motion to reduce false positives [3,11,12,13].”
YOLO-based Object Detection Models: A Review and its Applications (2024, neutral): “Other datasets that are used in previous research work include Remote sensing target detection [42] [43] [44], text detection [45] [46] [47], and Pedestrian detection [48] [49] [50].”
PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments (2020, methodology): “SZTAKI [1] Aerial ≈1:3 9 665 VEDAI [31] Aerial 1:3 1268 2950 UCAS-AOD [50] Aerial 1:1.”
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network (2017, background): “The recent car-related dataset VEDAI [20] has 2,950 cars, but these are still too few to utilize for the deep learners.”
Transformers in Remote Sensing: A Survey (2022, methodology): “HybridNetwork22 [45] Detection DOTA [49], UCAS-AOD [86], VEDAI [87] mAP Integrates multi-scale global and local information from transformers and CNNs through an adaptive feature fusion network.”