Vision Meets Drones: A Challenge

By Peng Fei Zhu, Longyin Wen, Xiao Bian, Haibin Ling, Qinghua Hu. arXiv.org, 2018

533 citations recorded by the source corpus.

In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform. The images and video sequences in the benchmark were captured over various urban/suburban areas of 14 different cities across China from north to south. Specifically, VisDrone2018 consists of 263 video clips and 10,209 images (no overlap with video clips) with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc. With intensive amount of effort, our benchmark has more than 2.5 million annotated instances in 179,264 images/video frames. Being the largest such dataset ever published, the benchmark enables extensive evaluation and investigation of visual analysis algorithms on the drone platform. In particular, we design four popular tasks with the benchmark, including object detection in images, object detection in videos, single object tracking, and multi-object tracking. All these tasks are extremely challenging in the proposed dataset due to factors such as occlusion, large scale and pose variation, and fast motion. We hope the benchmark largely boost the research and development in visual analysis on drone platforms.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Endocrinology

View Paper: https://www.semanticscholar.org/paper/98bf42055160845e6f8f3c022298e3b8e4e55f80

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Endocrinology

Matej Kristan

Citations in the corpus

RemoteCLIP: A Vision Language Foundation Model for Remote Sensing (2023, background): “Visdrone [88] 2018 6,471 11 77,547 1509×849 Visdrone dataset consists of high-quality images and videos captured by UAV, along with rich object annotation information.”
Siam R-CNN: Visual Tracking by Re-Detection (2019, unknown): “VOT is commonly evaluated on benchmarks such as OTB [69, 70], VOT [36, 34], and many more [49, 30, 81, 48, 33].”
Tiny Object Detection in Aerial Images (2021, background): “5 trainval set [1], xView training set [19], VisDrone2018-Det trainval set [20], Airbus Ship trainval set1 and DIOR trainval+test sets [3].”
Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “An even more ambitious project called Vision Meets Drones [146] gathered a dataset with 2.5 million object annotations for detection and tracking in UAV urban and suburban flight environments.”
The Seventh Visual Object Tracking VOT2019 Challenge Results (2019, background): “UAV123 [73] and [110] datasets focus on drone tracking.”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, background): “A lot of research has been invested into benchmarking and performance evaluation in short-term visual object tracking [41,42,40,39,38,43,83,75,92,47,51,61,96,62,101].”
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results (2019, methodology): “Compared with the previous drone based datasets [29, 15, 9], a larger scale drone based object detection dataset [48] is proposed to evaluate detection algorithms in real scenarios.”
TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios (2021, methodology): “When we train the model using VisDrone2021 dataset [64] with data augmentation strategy (Mosaic and MixUp), we find that the results of YOLOv5x are much better than YOLOv5s, YOLOv5m and YOLOv5l, and the gap of AP value is more than 1.5%.”
Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, unknown): “VisDrone [8] consists of 263 video clips and 10, 209 images with rich annotations (such as object bounding boxes, object categories, occlusion, truncation ratios, etc.”
A Survey of Deep Learning-Based Object Detection (2019, background): “VisDrone2018 has a large amount of small objects, such as dense cars, pedestrians and bicycles, which will cause difficult detection about certain categories.”
Deep Learning for Unmanned Aerial Vehicle-Based Object Detection and Tracking: A survey (2021, background): “For more details, please refer to [21] and [201].”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “The image subset in VisDrone for object detection is not very large.”
Clustered Object Detection in Aerial Images (2019, methodology): “, 2,000×1,500 pixels in VisDrone [37]) are far from satisfactory in both accuracy and efficiency, which are caused by two challenges: (1) targets typically have small scales relative to the images; and (2) targets are generally sparsely and non-uniformly distributed in the whole image.”