Dense and Small Object Detection in UAV Vision Based on Cascade Network

Zhang, Xindi; Izquierdo, Ebroul; Chandramouli, Krishna

doi:10.1109/iccvw.2019.00020

Cited by 79 publications

(45 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The UAV flying altitude inevitably causes most objects to be shown in scale diversity, small object size and dense arrangement, resulting in less feature information that can be extracted. Many work deal with the small object detection [62] Small objects VisDrone ICCV Workshops 2019 -FS-SSD [66] Small objects Stanford Drone IEEE TCSVT 2019 -SAMFR [67] Scale variation Visdrone ICCV Workshop 2019 -ClusDet [57] Scale variation VisDrone, UAVDT ICCV 2019 https://github.com/fyangneil CenterNet [58] Scale variation VisDrone -2019 -Yang et al [59] Scale variation Stanford Drone IEEE Access 2019 -Wu et al [68] Real-time CARPK DDCLS 2019 -NDFT [69] UAV-specific nuisances VisDrone, UAVDT ICCV 2019 https://github.com/VITA-Group/UAV-NDFT MSOA-Net [56] Scale variation UVSD Remote Sens. 2020 -GDF-Net [61] Scale variation VisDrone, UAVDT Remote Sens.…”

Section: Object Detection On Small Objectsmentioning

confidence: 99%

Deep Learning for UAV-based Object Detection and Tracking: A Survey

Wu,

Li,

Hong

et al. 2021

Preprint

View full text Add to dashboard Cite

This is the pre-acceptance version, to read the final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE Xplore. Owing to effective and flexible data acquisition, unmanned aerial vehicle (UAV) has recently become a hotspot across the fields of computer vision (CV) and remote sensing (RS). Inspired by recent success of deep learning (DL), many advanced object detection and tracking approaches have been widely applied to various UAV-related tasks, such as environmental monitoring, precision agriculture, traffic management. This paper provides a comprehensive survey on the research progress and prospects of DL-based UAV object detection and tracking methods. More specifically, we first outline the challenges, statistics of existing methods, and provide solutions from the perspectives of DL-based models in three research topics: object detection from the image, object detection from the video, and object tracking from the video. Open datasets related to UAV-dominated object detection and tracking are exhausted, and four benchmark datasets are employed for performance evaluation using some state-of-the-art methods. Finally, prospects and considerations for the future work are discussed and summarized. It is expected that this survey can facilitate those researchers who come from remote sensing field with an overview of DL-based UAV object detection and tracking methods, along with some thoughts on their further developments.

show abstract

Section: Object Detection On Small Objectsmentioning

confidence: 99%

Deep Learning for UAV-based Object Detection and Tracking: A Survey

Wu,

Li,

Hong

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The method in [ 6 ] introduced DeForm convolutional layers within the backbone and proposed an interleaved cascade architecture. Meanwhile, multi-model fusion was used to deal with class imbalance problems.…”

Section: Related Workmentioning

confidence: 99%

“…Most UAV visible image object detection algorithms are based on widely used and universally structured methods, such as Faster RCNN or SSD, which target the small scale and dense distribution of UAV image objects, either by complicating the network structure or the detection process [ 6 , 7 , 8 , 9 ], or by introducing novel ways of data augmentation [ 7 , 10 ], ultimately making the algorithms perform well on UAV datasets. Typically, the optimisation goal of these algorithms is to improve accuracy as much as possible, with less consideration given to efficiency, and the few fast algorithms are only somewhat faster relative to their predecessors, falling far short of the standard of real-time.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Detection Network Based on Sub-Pixel Convolution and Objectness-Aware Structure for UAV Images

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) can serve as an ideal mobile platform in various situations. Real-time object detection with on-board apparatus provides drones with increased flexibility as well as a higher intelligence level. In order to achieve good detection results in UAV images with complex ground scenes, small object size and high object density, most of the previous work introduced models with higher computational burdens, making deployment on mobile platforms more difficult.This paper puts forward a lightweight object detection framework. Besides being anchor-free, the framework is based on a lightweight backbone and a simultaneous up-sampling and detection module to form a more efficient detection architecture. Meanwhile, we add an objectness branch to assist the multi-class center point prediction, which notably improves the detection accuracy and only takes up very little computing resources. The results of the experiment indicate that the computational cost of this paper is 92.78% lower than the CenterNet with ResNet18 backbone, and the mAP is 2.8 points higher on the Visdrone-2018-VID dataset. A frame rate of about 220 FPS is achieved. Additionally, we perform ablation experiments to check on the validity of each part, and the method we propose is compared with other representative lightweight object detection methods on UAV image datasets.

show abstract

“…Sommer et al [47] exploit Faster R-CNN [12] to extend the detection task for multiple vehicle categories. Zhang et al [48] adopt Cascade R-CNN [49] to realize dense and small vehicles detection in UAV vision. However, these UAV vehicle detection methods cannot satisfy real-time requirement.…”

Section: Anchor-based Uav Vehicle Detectionmentioning

confidence: 99%

A Feature-Enhanced Anchor-Free Network for UAV Vehicle Detection

et al. 2020

View full text Add to dashboard Cite

Vehicle detection based on unmanned aerial vehicle (UAV) images is a challenging task. One reason is that the objects are small size, low-resolution, and large scale variations, resulting in weak feature representation. Another reason is the imbalance between positive and negative examples. In this paper, we propose a novel architecture for UAV vehicle detection to solve above problems. In detail, we use anchor-free mechanism to eliminate predefined anchors, which can reduce complicated computation and relieve the imbalance between positive and negative samples. Meanwhile, to enhance the features for vehicles, we design a multi-scale semantic enhancement block (MSEB) and an effective 49-layer backbone which is based on the DetNet59. The proposed network offers appropriate receptive fields that match the small-sized vehicles, and involves precise localization information provided by the contexts with high resolution. The MSEB strengthens discriminative feature representation at various scales, without reducing the spatial resolution of prediction layers. Experiments show that the proposed method achieves the state-of-the-art performance. Particularly, the main part of vehicles, much smaller ones, the accuracy is about 2% higher than other existing methods.

show abstract

Dense and Small Object Detection in UAV Vision Based on Cascade Network

Cited by 79 publications

References 10 publications

Deep Learning for UAV-based Object Detection and Tracking: A Survey

Deep Learning for UAV-based Object Detection and Tracking: A Survey

Lightweight Detection Network Based on Sub-Pixel Convolution and Objectness-Aware Structure for UAV Images

A Feature-Enhanced Anchor-Free Network for UAV Vehicle Detection

Contact Info

Product

Resources

About