Fast Multiclass Vehicle Detection on Aerial Images

By Kang Liu, Gellért Máttyus. IEEE Geoscience and Remote Sensing Letters, 2015

321 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/69b39e307d84890f817ee4ebb775460d162253d4

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

1. Guisong Xia
2. Xue Yang
3. Junwei Han
4. Junchi Yan
5. Liangpei Zhang
6. Jian Ding
7. Gong Cheng
8. Xiang Bai

Citations in the corpus

• A Survey of Deep Learning-Based Object Detection (2019, background): “NWPU VHR-10 [166], HRRSD [146], DOTA [167], DLR 3KMunich [168] andVEDAI [169] are remote sensing object detection benchmarks.”
• Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends (2020, background): “NWPU VHR-10 [182] OD multiple classes airborne platforms optical very high DarkNet + YOLO (modified: VaryBlock) [183], ResNet-101 + FPN (modified: Densely connected top-down path) + fully convolutional detector head [184] COWC [185] OD vehicle detection airborne platforms optical very high VGG16 + S”
• Learning RoI Transformer for Oriented Object Detection in Aerial Images (2019, methodology): “Instead of using horizontal bounding boxes, oriented bounding boxes have been employed to give more accurate locations of objects [37, 23, 28].”
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, background): “DLR 3K Vehicle [33] Aerial images 14,235 20 5616 2 OBB JPG N”
• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, methodology): “, [7], [15], [16], [17], [26], but they contain a limited number of instances and tend to use images taken under ideal conditions (e.”
• Perception, Guidance, and Navigation for Indoor Autonomous Drone Racing Using Deep Learning (2018, methodology): “using a number of techniques, including classical color and shape-based detection [7], ground vehicle detection [8], [9], Lucas-Kanade optical flow-based visual surveillance [10], and”
• Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery (2018, methodology): “en investigated by a number of works in the recent years. The majority of the proposed algorithms focus on object detection with a small number of classes and a limited range of GSDs. Liu and Mattyus [17] proposed histogram of oriented gradients (HOG) features and the AdaBoost method for feature cla”
• Object Detection in 20 Years: A Survey (2019, methodology): “earch/TAS/ 419 OIRDS [86] 2009 Consists for 900 images (0.08-0.3m/pixel) captured by aircraft-mounted camera and 1,800 annotated vehicle targets. url: https://sourceforge.net/projects/oirds/ 32 DLR3K [87] 2013 The most frequently used datasets for small vehicle detection. Consists of 9,300 cars and ”
• DOTA: A Large-Scale Dataset for Object Detection in Aerial Images (2017, methodology): “Annotation way #main categories #Instances #Images Image width NWPU VHR-10 [2] horizontal BB 10 3651 800 ∼ 1000 SZTAKI-INRIA [1] oriented BB 1 665 9 ∼ 800 TAS [9] horizontal BB 1 1319 30 792 COWC [20] one dot 1 32716 53 2000 ∼ 19,000 VEDAI [24] oriented BB 3 2950 1268 512, 1024 UCAS-AOD [40] oriente”
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection (2020, methodology): “Other methods [40, 26, 29, 28] leverage oriented bounding boxes as anchors to handle rotated objects.”
• Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, background): “169 DLR 3K [28], COWC [29], DOTA [8], and EAGLE [34] 170 are mainly composed of remote sensing images and generally 171 have high image resolution.”