Awesome Drone Vision
- Models
-
Object Detection
-
Object Tracking
-
Segmentation
-
Datasets
Object Detection Models
- YOLO
- YOLOv1 (You Only Look Once: Unified, Real-Time Object Detection) (2015) [paper]
- YOLOv2 (YOLO9000: Better, Faster, Stronger) (2016) [paper]
- YOLOv3: An Incremental Improvement (2018) [paper]
- YOLOv4: Optimal Speed and Accuracy of Object Detection (2020) [paper] [github]
- YOLOv5 (2020) [github]
- SSD
- SSD: Single Shot MultiBox Detector (2016) [paper]
- EfficientNet
- EfficientDet: Scalable and Efficient Object Detection (2019) [paper] [github]
- Anchor-free models
- YOLOX: Exceeding YOLO Series in 2021 [paper]
- FCOS: Fully Convolutional One-Stage Object Detection (2019) [paper]
- ATSS (Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection) (2021) [paper]
- SBS
- Object Detection in Drone Imagery via Sample Balance Strategies and Local Feature Enhancement (2021) [paper]
- ZoomInNet
- ZoomInNet: A Novel Small Object Detector in Drone Images with Cross-Scale Knowledge Distillation (2021) [paper]
Object Tracking Models
- MOT
- FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking (2020) [paper] [github]
- SORT
- SORT (Simple Online and Realtime Tracking) (2016) [paper] [github]
- DeepSORT (Simple Online and Realtime Tracking with a Deep Association Metric) (2017) [paper] [github]
Segmentation Models
- SegNet
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (2015) [paper]
- DeepLab
- DeepLab V3 (Rethinking Atrous Convolution for Semantic Image Segmentation) (2017) [paper] [github]
- DeepLab V3+ (Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation) (2018) [paper]
- Crack segmentation
- CrackNet (Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network) (2017) [paper(paid)]
- CrackNet-V (Pixel-level cracking detection on 3D asphalt pavement images through deep-learning-based CrackNet-V) (2019) [paper(paid)]
- DeepCrack: A deep hierarchical feature learning architecture for crack segmentation (2019) [paper] [github]
- SDDNet: Real-Time Crack Segmentation (2019) [paper]
- SCCDNet: A Pixel-Level Crack Segmentation Network (2021) [paper] [github]
- Unet
- U-Net: Convolutional Networks for Biomedical Image Segmentation (2015) [paper]
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation (2018) [paper]
- IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks (2019) [paper] [github]
Datasets
- Drone
- Crack
- CCSD (Concrete Crack Segmentation Dataset) (2019) [home]
- CCIC (Concrete Crack Images for Classification) (2019) [home]
- SDNET2018: A concrete crack image dataset for machine learning applications [home]
- Object Tracking
- MOT (Multiple Object Tracking) [home]
- VOT (visual object tracking) [home]