VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results

By Peng Fei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Haibin Ling, Qinghua Hu, Qinqin Nie, Hao Cheng, Chenfeng Liu, Xiaoyu Liu and 93 more. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019

1,010 citations recorded by the source corpus.

Recently, automatic visual data understanding from drone platforms becomes highly demanding. To facilitate the study, the Vision Meets Drone Object Detection in Image Challenge is held the second time in conjunction with the 17-th International Conference on Computer Vision (ICCV 2019), focuses on image object detection on drones. Results of 33 object detection algorithms are presented. For each participating detector, a short description is provided in the appendix. Our goal is to advance the state-of-the-art detection algorithms and provide a comprehensive evaluation platform for them. The evaluation protocol of the VisDrone-DET2019 Challenge and the comparison results of all the submitted detectors on the released dataset are publicly available at the website: http: //www.aiskyeye.com/. The results demonstrate that there still remains a large room for improvement for object detection algorithms on drones.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/80edf721b4ab5f4f4e24db69131c360d3343eaed

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

Citations in the corpus

Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark (2022, neutral): “Therefore, we select some other aerial object detection datasets which also contain a considerable number of tiny objects for further verification, including: AI-TOD (Wang et al., 2021a), VisDrone2019 (Du et al., 2019), and DOTA-v2.”
Clustered Object Detection in Aerial Images (2019, background): “The input size of the detector is set to 600 × 1 , 000 pixels on the VisDrone [35] and UAVDT [8] datasets and 1 , 000 × 1 , 000 pixels on the DOTA [31] dataset.”
A Review on Deep Learning in UAV Remote Sensing (2021, background): “Still, there are some known aerial repositories with labeled examples, which were presented in recent years, such as the DOTA [197], UAVDT [50], VisDrone [9], WHU-RS19 [171], RSSCN7 [220], RSC11 [209], Brazilian Co ff ee Scene [151] datasets.”
Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection (2022, background): “VisDrone2019-Detection [25] is an object detection dataset having 8599 images captured by drone platforms at different locations and at different heights.”
SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention (2024, positive): “Building on the above configurations, we further evaluate the proposed SCSA method’s detection performance and generalization capability on Pascal VOC [11], as well as in complex scenarios such as VisDrone [10], ExDark [34], and FLIR-ADAS V2 [13].”
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection (2021, methodology): “We conduct quantitative experiments on two object detection datasets: COCO [30] and VisDrone [74].”
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection (2021, neutral): “To reveal the effectiveness of NWD on TOD, we conduct experiments on tiny object detection datasets AI-TOD [29] and VisDrone2019 [4].”
Deep High-Resolution Representation Learning for Visual Recognition (2019, methodology): “ation, and so on. There are already followup works, e.g., image stylization [83], inpainting [50], image enhancement [62], image dehazing [1], temporal pose estimation [6], and drone object detection [190]. It is reported in [26] that a slightly-modiﬁed HRNet combined with ASPP achieved the best per”
TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios (2021, neutral): “…15.26 29.23 Cascade-RCNN[3] 16.09 31.91 FPN[28] 16.51 32.20 Light-RCNN[25] 16.53 32.78 CornetNet[24] 17.41 34.12 RRNet (2019 2 nd )[4] 29.13 55.82 DPNet-ensemble (2019 SOTA) [8] 29.62 54.00 SMPNet (2020 2 nd )[47] 35.98 59.53 DPNetV3 (2020 SOTA)[47] 37.37 Effect of extra prediction head.”